Skip to content
Projekte

rayanrsr/RLCV-Papers

Auf GitHub ansehen

rayanrsr/RLCV-Papers has 29 GitHub stars and 1 forks. Star changes are not measured yet. Last checked 2026-11-11 08:39 UTC. Last push 2026-11-07.

So werden diese Zahlen gemessen

A curated list of papers applying Reinforcement Learning to Computer Vision

29 Sterne1 forks

Gemessener Sternzuwachs

in 24h
Aktualisierung verzögert
in 7 days
Verlauf wird gesammelt
in 15 days
Verlauf wird gesammelt
in 1 month
Verlauf wird gesammelt

Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.

README.md

Original

( Reinforcement Learning + Computer Vision ) Papers

A curated list of papers applying Reinforcement Learning to Computer Vision tasks.

Summary

Image Instance Segmentation

1985:

1992 :

2006 :

  • Farhang Sahba, Hamid R Tizhoosh, and Magdy MA Salama. A reinforcement learning framework for medical image segmentation. In The 2006 IEEE International Joint Conference on Neural Network Proceedings, pages 511–517. IEEE : https://ieeexplore.ieee.org/document/1716136
  • Leo Grady. Random walks for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 28(11):1768–1783 : https://ieeexplore.ieee.org/document/1704833

2007 :

2015 :

2016 :

  • Md Reza, Jana Kosecka, et al. Reinforcement learning for semantic segmentation in indoor scenes. arXiv preprint arXiv:1606.01178, : https://arxiv.org/abs/1606.01178
  • Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928–1937: http://proceedings.mlr.press/v48/mniha16.pdf

2017 :

2018 :

2020 :

Object Tracking

2005 :

2015 :

  • Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 : https://arxiv.org/abs/1509.02971
  • Yu Xiang, Alexandre Alahi, and Silvio Savarese. Learning to track: Online multi-object tracking by decision making. In Proceedings of the IEEE international conference on computer vision, pages 4705–4713 : https://cvgl.stanford.edu/papers/xiang_iccv15.pdf

2016 :

  • Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928–1937: https://proceedings.mlr.press/v48/mniha16.html

2017 :

  • Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, and Yizhou Wang. End-to-end active object tracking via reinforcement learning. arXiv preprint arXiv:1705.10561 : https://arxiv.org/abs/1705.10561
  • Da Zhang, Hamid Maei, Xin Wang, and Yuan-Fang Wang. Deep reinforcement learning for visual object tracking in videos. arXiv preprint arXiv:1701.08936 : https://arxiv.org/pdf/1701.08936.pdf

2018 :


 2019 :

  • Matteo Dunnhofer, Niki Martinel, Gian Luca Foresti, and Christian Micheloni. Visual tracking by means of deep reinforcement learning and an expert demonstrator. In Proceedings of the IEEE International Conference on Computer Vision Workshops : https://arxiv.org/abs/1909.08487
  • Mingxin Jiang, Tao Hai, Zhigeng Pan, Haiyan Wang, Yinjie Jia, and Chao Deng. Multi-agent deep reinforcement learning for multi-object tracker. IEEE Access, 7:32400–32407 : https://ieeexplore.ieee.org/document/8653482

Object Detection

2012 :

2015 :

  • Juan C Caicedo and Svetlana Lazebnik. Active object localization with deep reinforcement learning. In Proceedings of the IEEE international conference on computer vision, pages 2488–2496 : https://arxiv.org/abs/1511.06015

2016 :

2017 :

  • Gabriel Maicas, Gustavo Carneiro, Andrew P Bradley, Jacinto C Nascimento, and Ian Reid. Deep reinforcement learning for active breast lesion detection from dce-mri. In International conference on medical image computing and computer-assisted intervention, pages 665–673. Springer : https://cs.adelaide.edu.au/~gabriel/DRL_maicasEtAl.pdf

2018 :

2020 :

  • Burak Uzkent, Christopher Yeh, and Stefano Ermon. Efficient object detection in large images using deep reinforcement learning. In The IEEE Winter Conference on Applications of Computer Vision, pages 1824–1833 : https://arxiv.org/abs/1912.03966
  • Fernando Navarro, Anjany Sekuboyina, Diana Waldmannstetter, Jan C Peeken, Stephanie E Combs, and Bjoern H Menze. Deep reinforcement learning for organ localization in ct. arXiv preprint arXiv:2005.04974 :
  • Lijie Liu, Chufan Wu, Jiwen Lu, Lingxi Xie, Jie Zhou, and Qi Tian. Reinforced axial refinement network for monocular 3d object detection. In European Conference on Computer Vision ECCV, pages 540–556 : https://arxiv.org/abs/2008.13748

Image Registration

2000 :

2013 :

2016 :

  • Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928–1937 : https://proceedings.mlr.press/v48/mniha16.html

2017 :

2018 :

  • Shanhui Sun, Jing Hu, Mingqing Yao, Jinrong Hu, Xiaodong Yang, Qi Song, and Xi Wu. Robust multimodal image registration using deep recurrent reinforcement learning. In Asian Conference on Computer Vision, pages 511–526. Springer : https://arxiv.org/abs/2002.03733

Video Analysis

2015 :

2016 :

2018 :

  • Daochang Liu and Tingting Jiang. Deep reinforcement learning for surgical gesture segmentation and classification. In International conference on medical image computing and computer-assisted intervention, pages 247–255. Springer : https://arxiv.org/abs/1806.08089
  • Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, and Xiaodan Liang. Reinforcement cutting-agent learning for video object segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 9080–9089, 2018.
  • Vikash Goel, Jameson Weng, and Pascal Poupart. Unsupervised video object segmentation for deep reinforcement learning. In Advances in Neural Information Processing Systems, pages 5683–5694 : https://arxiv.org/abs/1805.07780
  • Yansong Tang, Yi Tian, Jiwen Lu, Peiyang Li, and Jie Zhou. Deep progressive reinforcement learning for skeleton-based action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5323–5332 : https://openaccess.thecvf.com/content_cvpr_2018/papers/Tang_Deep_Progressive_Reinforcement_CVPR_2018_paper.pdf
  • Kaiyang Zhou, Yu Qiao, and Tao Xiang. Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In Thirty-Second AAAI Conference on Artificial Intelligence : https://arxiv.org/abs/1801.00054
  • Kaiyang Zhou, Tao Xiang, and Andrea Cavallaro. Video summarisation by classification with deep reinforcement learning. arXiv preprint arXiv:1807.03089 : https://arxiv.org/abs/1807.03089

2020 :

Landmark Detection

2010 :

  • Antonio Criminisi, Jamie Shotton, Duncan Robertson, and Ender Konukoglu. Regression forests for efficient anatomy detection and localization in ct studies. In International MICCAI Workshop on Medical Computer Vision, pages 106–117. Springer, 2010.

2015 :

2016 :

  • Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928–1937 : https://proceedings.mlr.press/v48/mniha16.html

2017 :

  • Florin-Cristian Ghesu, Bogdan Georgescu, Yefeng Zheng, Sasa Grbic, Andreas Maier, Joachim Hornegger, and Dorin Comaniciu. Multi-scale deep reinforcement learning for real-time 3d-landmark detection in ct scans. IEEE transactions on pattern analysis and machine intelligence, 41(1):176–189, 2017 : https://pubmed.ncbi.nlm.nih.gov/29990011/

2019 :

  • Amir Alansary, Ozan Oktay, Yuanwei Li, Loic Le Folgoc, Benjamin Hou, Ghislain Vaillant, Konstantinos Kamnitsas, Athanasios Vlontzos, Ben Glocker, Bernhard Kainz, et al. Evaluating reinforcement learning agents for anatomical landmark detection. Medical image analysis, 53:156–164 : https://pubmed.ncbi.nlm.nih.gov/30784956/
  • Walid Abdullah Al and Il Dong Yun. Partial policy-based reinforcement learning for anatomical landmark localization in 3d medical images. IEEE transactions on medical imaging : https://ieeexplore.ieee.org/abstract/document/8863403
  • Athanasios Vlontzos, Amir Alansary, Konstantinos Kamnitsas, Daniel Rueckert, and Bernhard Kainz. Multiple landmark detection using multi-agent reinforcement learning. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 262–270. Springer : https://arxiv.org/abs/1907.00318

Survey

2021

Recent additions

2026 :

  • Yixiao Wang, Peiyi Chen, Mustafa Mukadam, Shreekant Gayaka, Masayoshi Tomizuka, Son Tran. Latent RL Priors for Data-Efficient Dexterous Manipulation. arXiv preprint arXiv:2611.08458v1 : https://arxiv.org/abs/2611.08458v1
  • Roko Parac, Christos Ziakas, Leo Ardon, Alessandra Russo. RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines. arXiv preprint arXiv:2611.08308v1 : https://arxiv.org/abs/2611.08308v1
  • Zhengyang Liang, Lizi Liao. ManimCode: Learning Visual Self-Correction for Educational Animation. arXiv preprint arXiv:2611.08294v1 : https://arxiv.org/abs/2611.08294v1
  • Chenhao Zheng, Zixian Ma, Kai Li, Kanchana Ranasinghe, Jieyu Zhang, Artemis Panagopoulou, Weikai Huang, Jianxu Shangguan, Yuanyuan Tan, Silvio Savarese, Juan Carlos Niebles, Ranjay Krishna, Ran Xu, Honglu Zhou. Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds. arXiv preprint arXiv:2611.08286v1 : https://arxiv.org/abs/2611.08286v1
  • Haitao Lin, Minsi Ren, Yang Li, Xingtong Ge, Zheyuan Hu, Peiyan Hu, Tailin Wu. FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning. arXiv preprint arXiv:2611.08240v1 : https://arxiv.org/abs/2611.08240v1
  • Dengyao Shi, Tianyu Fu, Fei Hu, Anyang Su, Hanning Wang, Shuo Wang, Minghui Wu, Chenxu Zhao, Zhen Lei. BiGrounder: Bidirectional Training Unlocks the Potential of GUI Grounding. arXiv preprint arXiv:2611.07765v1 : https://arxiv.org/abs/2611.07765v1
  • Ziqiao Weng, Yuanzhi Liang, Haibing Huang, Weidong Cai, Xuelong Li. Generator-Aligned Reward Modeling with Target-Aware Bounded Optimization for Visual Generation. arXiv preprint arXiv:2611.07648v1 : https://arxiv.org/abs/2611.07648v1
  • Guanren Qiao, Ruixiang Ouyang, Sheng Xu, Yueci Deng, Yunxin Tai, Kui Jia, Guiliang Liu. Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation. arXiv preprint arXiv:2611.07532v1 : https://arxiv.org/abs/2611.07532v1
  • Chao Zhou, Shenghua He, Jiaxin Mo, Qiangguo Yu, Fengchuang Xing. RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples. arXiv preprint arXiv:2611.07512v1 : https://arxiv.org/abs/2611.07512v1
  • Nishanth Anand, Doina Precup. Permanent and Transient Representations for Continual Reinforcement Learning. arXiv preprint arXiv:2611.07327v1 : https://arxiv.org/abs/2611.07327v1
  • Caorui Li, Yangguang Ji, Shuxia Lin, Yu Chen, YiCheng Xiao, Yongliang Wu, Zhenxiang Jiang, Licheng Tang, Deng Li, Zhuxuanzi Wang, Jiahao Sun, Chonghan Liu, Lirian Su, Jay Wu, Xu Yang. ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation. arXiv preprint arXiv:2611.07301v1 : https://arxiv.org/abs/2611.07301v1
  • Kwanyoung Park, Sergey Levine. MAC-v2: Long-horizon model-based value expansion from pixels. arXiv preprint arXiv:2611.07245v1 : https://arxiv.org/abs/2611.07245v1
  • Shuai Dong, Kanghui Tian, Linghan Chen, Wenqi Shao, Hongrui Wu, Haowen Hou, Yongfu Zhu, Xuehui Wang, Ziyue Wang, Wenpu Liu, Weichu Xie, Yuqi Xu, Congcong Wang, Kaiwen Tuo, Caoyuan Ma, Taiqiang Wu, Ji Zhao, Wenzheng Chang, Dianyi Wang, Siyuan Wang, Zhongyu Wei, Yu Qiao, Jiaqi Wang. Turns Matter: Advancing Streaming Video RL via Turn-Level Credit. arXiv preprint arXiv:2611.06728v1 : https://arxiv.org/abs/2611.06728v1
  • Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu, Yunyang Ge, Sihui Ji, Yunlong Lin, Kaihang Pan, Hongru Yan, Sixiang Chen, Dianyi Wang, Julian Zhang, Weijie Kong, Changlin Li, Lanqing Guo, Zhao Zhong, Qifeng Chen, Harry Yang. EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL. arXiv preprint arXiv:2611.06518v1 : https://arxiv.org/abs/2611.06518v1
  • Shu'ang Sun, Yibo Qiu, Haoliang Ye, Zan Huang, Ao Tian, Kan Ding, Ronald Xu, Mingzhai Sun. TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics. arXiv preprint arXiv:2611.06442v1 : https://arxiv.org/abs/2611.06442v1
  • Xingchen Zou, Maonan Wang, Kemou Jiang, Jie Li, Yiqi Chen, Xi Chen, Hai Yang, Yuxuan Liang. Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control. arXiv preprint arXiv:2611.06353v1 : https://arxiv.org/abs/2611.06353v1
  • Zhiliang Zhu, Jiazheng Huang, Dawei Zhao. Beyond Scene Shortcuts: Action-Centric Video-Text Alignment for Fine-Grained Action Understanding. arXiv preprint arXiv:2611.06302v1 : https://arxiv.org/abs/2611.06302v1
  • Hongeun Kim, Jeongsol Kim, Jong Chul Ye. Learning Noise Optimization for Reward Alignment in Few-Step Generative Models. arXiv preprint arXiv:2611.06255v1 : https://arxiv.org/abs/2611.06255v1
  • Rohan Sequeira, Matthew Rosenberg, Amin Mahmoudabadbozchelou, Oleg Poliannikov, Jonathan Rubin. From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+. arXiv preprint arXiv:2611.06123v1 : https://arxiv.org/abs/2611.06123v1
  • Changyeon Lee, Kelin Yu, Zheng Wei, Shuna Ni, Ruohan Gao. OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments. arXiv preprint arXiv:2611.05738v1 : https://arxiv.org/abs/2611.05738v1
  • Junfeng Wang, Jiawei Liu, Yongchao Xu, Tao Jiang, Jiangbo Ai, Jin Zhang, Chong Wang, Qixing Zhang. Learning Where to Look: Observation Policy Optimization for Thinking with Images. arXiv preprint arXiv:2611.04943v1 : https://arxiv.org/abs/2611.04943v1
  • Zicheng Kong, Zhenbo Xu, Haoyan Zhang, Jinghan Yang, Zhenzhen Li, Yiwei Ru, Liuyu Xiang, WanTing Xu, Min Ren, Zhaofeng He. Trusting Imagined Futures: Auditing Imagined Rewards for VLA Post-Training. arXiv preprint arXiv:2611.04873v1 : https://arxiv.org/abs/2611.04873v1
  • Yiding Tian, Jiaojiao Yi, Jiayuan Lu, Pufan Xu, Jinlin Wu, Changyuan Wen, Hongyuan Yu. NightIQA: A Comprehensive Dataset and Benchmark for MLLM-Based Nighttime Image Quality Assessment. arXiv preprint arXiv:2611.04811v1 : https://arxiv.org/abs/2611.04811v1
  • Ria Shekhawat, Abhijeet Sinha, Yingtao Zhu, Dianbo Liu. Density-Aware Reward Scaling: A Reinforcement Learning Framework for Reward-Proportional Sampling. arXiv preprint arXiv:2611.04792v1 : https://arxiv.org/abs/2611.04792v1
  • Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu, Yifan Jiang, Yifan Zhang, Zexu Jin, Baolin Peng, Bolin Shen, Chetan Bansal, Dehan Kong, Deren Lei, Dongshen Peng, Fengqing Jiang, Hao Cheng, Haoqing Wang, Jiaming Shan, Jicheng Wang, Jingguang Zhou, Jixuan He, Kaide Zeng, Kangyu Zhu, Lama Moukheiber, Mufan Qiu, Peng Xia, Qihan Sun, Qingwei Lin, Qiushi Sun, Ruichen Zhang, Shuqing Luo, Si Qin, Sicheng Fan, Tao Xiong, Wenlin Yao, Xinyu Zhang, Xinyue Zeng, Xuanrui Li, Xuchao Zhang, Yian Wang, Yichao Liu, Yiming Liang, Yiyang Zhou, Yizhu Jiao, Yuetai Li, Yurun Chen, Yuxuan Zhang, Zheyuan Yang, Zhiyuan Yao, Zhongyang Li, Zihao Li, Zili Wang, Jianfeng Gao, Huaxiu Yao. WebHarbor: Docking Real Websites for Evolving GUI Agent Environments. arXiv preprint arXiv:2611.03634v1 : https://arxiv.org/abs/2611.03634v1
  • Marius Memmel, Shawn Yin, Urvi Rutia, Angad Wadhwa, Eldon Li, Gavin Angeloff, Ankit Goyal, Jesse Zhang, Dieter Fox, Fabio Ramos, Anqi Li, Abhishek Gupta. D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models. arXiv preprint arXiv:2611.03622v1 : https://arxiv.org/abs/2611.03622v1
  • Tengfei Liu, Yang Shi, Yuran Wang, Yuqi Tang, Yizhuo Jia, Zhuoran Zhang, Qixun Wang, Shujie Li, Xuanyu Zhu, Xinyu Liu, Minghui Guo, Shixuan Liu, Haotian Wang, Yuanxing Zhang, Pengfei Wan. Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning. arXiv preprint arXiv:2611.03602v1 : https://arxiv.org/abs/2611.03602v1
  • Zhihan Yin, Jianxin Liang, Yifeng Yao, Nonghai Zhang, Bingyue Peng, Chunguang Qie, Huishuai Zhang, Dongyan Zhao. MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation. arXiv preprint arXiv:2611.03087v1 : https://arxiv.org/abs/2611.03087v1
  • Marcos Antonio Obando, Tianyuan Wang, Tanja Tarvainen, Tristan van Leeuwen, Felix Lucka. Bayesian Sequential Optimal Experimental Design for Single-Pixel Imaging using Reinforcement Learning. arXiv preprint arXiv:2611.03042v1 : https://arxiv.org/abs/2611.03042v1
  • Zihao Fan, Xin Lu, Jie Huang, Hexin Zhang, Xueyang Fu, Zheng-Jun Zha. OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation. arXiv preprint arXiv:2611.02803v1 : https://arxiv.org/abs/2611.02803v1
  • Wooseok Jang, Seungryong Kim, Yan Lu, Lei Ji. Trace4D: Grounded Spatiotemporal Reasoning via 4D State Sequences. arXiv preprint arXiv:2611.02759v1 : https://arxiv.org/abs/2611.02759v1
  • Austin Wang, Lexing Ying. Do Visual RL Gains Scale at Test Time? A Quantile View of Post-Training. arXiv preprint arXiv:2611.02366v1 : https://arxiv.org/abs/2611.02366v1
  • Ke An, Shizhe Xiang, Yue Liu, Liang Chen, Pei Fu, Shaojie Zhang, Xiaoxing Hu, Yupei Wang. NAS-PO: Native Attention-Strategy Policy Optimization for Vision-Language Models. arXiv preprint arXiv:2611.02008v1 : https://arxiv.org/abs/2611.02008v1
  • Dhruv Makwana, Ananya Mantravadi. SurgQ-VLM: Question-Conditioned Dual-Stream Compression and Answer-Type-Aware Reinforcement for Surgical Video Question Answering. arXiv preprint arXiv:2611.01913v1 : https://arxiv.org/abs/2611.01913v1
  • Yuda Zou, Boxiang Zhou, Xin Zhou, Yibo Chen, Dejia Song, Xu Tang, Yao Hu, Yongchao Xu. FinishStrong: Learning to End Well after Imperfect Start in Video Temporal Grounding. arXiv preprint arXiv:2611.01765v1 : https://arxiv.org/abs/2611.01765v1
  • Hao Yang, Shuoyang Liu, Xiaoyu Lin, Zhou Fang, Maji Huang, Zhaosong Huang, Ruichao Mao, Teng Guo, Hai Rao. UI-UG 2: Advancing Mobile UI Understanding and Generation with Fine-Grained Supervision and Reinforcement Learning. arXiv preprint arXiv:2611.00926v1 : https://arxiv.org/abs/2611.00926v1
  • Songming Yang, Hong-Tao Yu, Xiu-Shen Wei. Learning to Group and Order: Cross-Instance Self-Supervised RL for Vision-Centric MLLMs. arXiv preprint arXiv:2611.00892v2 : https://arxiv.org/abs/2611.00892v2
  • Ao Chen, Shengchao Chen, Yan Luximon. Toward Counterfactual Learning for Selective Re-Examination in Agentic Visual Search. arXiv preprint arXiv:2611.00848v1 : https://arxiv.org/abs/2611.00848v1
  • T N Rickesh, Pranav Vinodh, Sowmya Kamath S. Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA. arXiv preprint arXiv:2611.00833v2 : https://arxiv.org/abs/2611.00833v2
  • T N Rickesh, Pranav Vinodh, Sowmya Kamath S. Answer Correction with Verifiable Rewards: A Gemma-Family Study of Multi-View Driving QA. arXiv preprint arXiv:2611.00828v2 : https://arxiv.org/abs/2611.00828v2
  • Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho, Jinwoo Shin. Latent Reasoning in Continuous Space for Unified Multimodal Models. arXiv preprint arXiv:2610.42149v1 : https://arxiv.org/abs/2610.42149v1
  • Zhuguanyu Wu, Congjia Chen, Ruihao Gong, Yang Yong, Shiqiao Gu, Yi Xu, Xianglong Liu. Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning. arXiv preprint arXiv:2610.41949v1 : https://arxiv.org/abs/2610.41949v1
  • Chanseul Cho, Noori Bae, Dongheon Lee, Youngmin Ro. GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning. arXiv preprint arXiv:2610.41629v1 : https://arxiv.org/abs/2610.41629v1
  • Antonio Terpin, Francesco Banelli, Alan Bonomi, Raffaello D'Andrea. ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control. arXiv preprint arXiv:2610.41304v1 : https://arxiv.org/abs/2610.41304v1
  • Guangzhi Wang, Junfu Pu, Yiran Wang, Xingyilang Yin, Honghao Chen, Cheng Cheng, Lingen Li, Yinan Zhou, Jiarui Wu, Yinuo Jiang, Hongbo Jin, Xiaodong Cun, Ying Shan. TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents. arXiv preprint arXiv:2610.40276v1 : https://arxiv.org/abs/2610.40276v1
  • Hongyu Bai, Jiaqi Zeng, Chunzheng Zhu. Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding. arXiv preprint arXiv:2610.39835v1 : https://arxiv.org/abs/2610.39835v1
  • Haotian Lyu, Haoyu Wang, Ru Wang, Feng Ji, Ziwen Li, Jiaxian Guo, Mingming Gong. Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning. arXiv preprint arXiv:2610.39439v1 : https://arxiv.org/abs/2610.39439v1
  • Shengqin Wang, Jie Jin, Xiaofan Li, Wentao Yan, Yu Cheng, Qingsong HuYihang Chen, Weilin Luo, Jingyu Gong, Xin Tan, Yuan Xie, Zhizhong Zhang. MRC-MMAgent: Reinforcement Learning for Multi-Role Collaboration in Multimodal Tool-Using Agents. arXiv preprint arXiv:2610.39324v1 : https://arxiv.org/abs/2610.39324v1
  • Zhiqiang Wu, Shuang Sun, Jiale Zhang, Jing Li, Yibo Chen, Xu Tang, Yao Hu. DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition. arXiv preprint arXiv:2610.39265v1 : https://arxiv.org/abs/2610.39265v1
  • Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols, Samy Bengio, Emmanuel Abbe. Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps. arXiv preprint arXiv:2610.39264v1 : https://arxiv.org/abs/2610.39264v1
  • Chenxi Liu, Tianyi Xiong, Yanshuo Chen, Heng Huang. Grounding Multimodal Reasoning with Evidence-Ablated Negatives. arXiv preprint arXiv:2610.39237v1 : https://arxiv.org/abs/2610.39237v1
  • Weifeng Xu, Yaxiong Wang, Zhedong Zheng. RuleForge: Inferring and Instantiating Latent Visual Rules as Executable Programs. arXiv preprint arXiv:2610.38737v1 : https://arxiv.org/abs/2610.38737v1
  • Mohammad Usaid, Deepak Silaych, Hrithik Mhatre, Archak Mittal. Vision-Based Density Estimation for Adaptive Traffic Control. arXiv preprint arXiv:2610.38497v1 : https://arxiv.org/abs/2610.38497v1
  • Jiahang Xie, Tong Jin, Lingfei Wu, Yaping You, Jie Huang, Yuanchang Jin, Weikang Gong, Wei Cheng, Jia You, Pan Sun, Jianfeng Feng, Hongcheng Guo. Fu-TCM: a multimodal large language model that learns traditional Chinese medicine diagnostic reasoning. arXiv preprint arXiv:2610.38333v1 : https://arxiv.org/abs/2610.38333v1
  • Rikuhei Umemoto, Kenjiro Ide, Soham Majumder, Ulf Brefeld, Keisuke Fujii. Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives. arXiv preprint arXiv:2610.38308v1 : https://arxiv.org/abs/2610.38308v1
  • Gagan Khandate. Echo: Scaling Visual Reinforcement Learning with Off-policy Experience. arXiv preprint arXiv:2610.37865v1 : https://arxiv.org/abs/2610.37865v1
  • Chaehyun Kim, Chi-Pin Huang, Jisoo Kim, Min-Hung Chen, Yu-Chiang Frank Wang, Seungryong Kim, Fu-En Yang. ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning. arXiv preprint arXiv:2610.37666v1 : https://arxiv.org/abs/2610.37666v1
  • Shilong Li, Xingyuan Bu, Hao Shi, Yun Xing, Weixin Feng, Qiangpeng Yang, Shilei Wen. VideoLVR: Latent Visual Reasoning over Grounded Video Evidence. arXiv preprint arXiv:2610.37613v1 : https://arxiv.org/abs/2610.37613v1
  • Dequan Ou, Austin Lopez, Quentin Missinne, Christophe De Wagter, Guido C. H. E. de Croon. Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation. arXiv preprint arXiv:2610.37543v1 : https://arxiv.org/abs/2610.37543v1
  • Mohamed Ashraf Mostafa, Taher El-Fakharany, Samir Khaled. Predict the Swing, Match the Speed: Robotic Pipe Stabbing With Learned Stereo Vision and Residual Reinforcement Learning. arXiv preprint arXiv:2610.37535v1 : https://arxiv.org/abs/2610.37535v1
  • Jiafeng Liang, Xianhao Ou, Tao Ren, Rongchuan Mu, Runxuan Liu, Dandan Tu, Ming Liu, See-Kiong Ng, Bing Qin. Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse. arXiv preprint arXiv:2610.37211v1 : https://arxiv.org/abs/2610.37211v1
  • Weichang Wang, Liyu Chen, Shuyue Guan, Jie Hu, Fei Gao, Wei Li, Nannan Wang. VGIQA: Fine-Grained Image Quality Assessment with Visual Grounding Rewards. arXiv preprint arXiv:2610.37186v1 : https://arxiv.org/abs/2610.37186v1
  • Ruilin Yao, Xinyu Qiu, Tianyu Zou, Yi Rong, Shengwu Xiong, Shuheng Shen, Changhua Meng. Learning to Look Beyond Screens: Transferable Visual Observation from GUI Grounding. arXiv preprint arXiv:2610.37093v1 : https://arxiv.org/abs/2610.37093v1
  • Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran Huang. Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception. arXiv preprint arXiv:2610.37037v1 : https://arxiv.org/abs/2610.37037v1
  • Zichen Yan, Rui Huang, Shenao Wang, Yucong Wang, Nuthasith Gerdpratoom, Lin Zhao. Omni-IGN: Onboard Image-Goal Navigation for Drones with Omnidirectional Vision. arXiv preprint arXiv:2610.36968v1 : https://arxiv.org/abs/2610.36968v1
  • Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo. Vision-Language Agents Can Learn in Their Own Latent Worlds. arXiv preprint arXiv:2610.36925v1 : https://arxiv.org/abs/2610.36925v1
  • Weihuang Lin, Xianing Chen, Zhibin Wang, Congzhi Zhang, Yiwei Ma, Jiayi Ji, Miao Chen, Jun Song, YuCheng, Bo Zheng, Xiaoshuai Sun, Rongrong Ji. MVRCap: Towards Comprehensive Video Captioning via Hierarchical Multi-Dimensional Verifiable Rewards. arXiv preprint arXiv:2610.36838v1 : https://arxiv.org/abs/2610.36838v1
  • Wentao Ye, Yali Ye, Zhiqing Xiao, Ru Peng, Xinpeng Ti, Liyao Li, Zhanming Shen, Peng Lu, Jie Zhang, Haobo Wang. From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors. arXiv preprint arXiv:2610.36146v1 : https://arxiv.org/abs/2610.36146v1
  • Rui Yang, Yanwei Li, Sili Chen, Jingjia Huang, Yi Lin, Hengshuang Zhao. Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding. arXiv preprint arXiv:2610.36022v1 : https://arxiv.org/abs/2610.36022v1
  • Haoyu Wang, Fei Zhou, Qingqing Qiu, Lei Zhang, Wei Wei, Chen Ding. S$^2$-RL: Sample-Set Dual Reinforcement Learning for Generative Semantic Segmentation Dataset Distillation. arXiv preprint arXiv:2610.35491v1 : https://arxiv.org/abs/2610.35491v1
  • Wanqi Dong, Wanyue Dong, Jingze Ge, Mehul Motani. GRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations. arXiv preprint arXiv:2610.34561v1 : https://arxiv.org/abs/2610.34561v1
  • Xiangfei Sheng, Xiaofeng Pan, Leida Li, Qian Zhang, Biao Wang, Johan Wagemans, Weisi Lin. CropReward: A Human-Preference Benchmark and Reward Model for Aesthetic Image Cropping. arXiv preprint arXiv:2610.34221v3 : https://arxiv.org/abs/2610.34221v3
  • Tianchen Guo, Tengyue Zhang, Chen Liu, Ling Chen, Xin Yu. Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?. arXiv preprint arXiv:2610.34149v1 : https://arxiv.org/abs/2610.34149v1
  • Xiangyu Peng, Jiaxin Zhang, An Yan, Yu Li, Ran Xu, Zeyuan Chen, Chien-Sheng Wu. MTA-Zero: Self-Improving Multimodal Deep Search via Online QA-Solver Co-training. arXiv preprint arXiv:2610.33799v1 : https://arxiv.org/abs/2610.33799v1
  • Sagnik Anupam, Utkarsh Lal, Aneesh Edara, Botong Zhang, Yao Tang, Jiatao Gu, Dinesh Jayaraman, Osbert Bastani. RoboReason: Boosting Robotics-Relevant VLM Reasoning Through Scalable Data Generation. arXiv preprint arXiv:2610.33778v1 : https://arxiv.org/abs/2610.33778v1
  • Dinis Fernandes, Tiago Ribeiro, António Ribeiro, Carolina Lopes, Gil Lopes, A. Fernando Ribeiro. Computer Vision Navigation for an Autonomous Vehicle Model Using Reinforcement Learning. arXiv preprint arXiv:2610.33755v1 : https://arxiv.org/abs/2610.33755v1
  • Jingmeng Zhou, Seson Sun, Binyao Xu, Lingming Zhang, Hanshi Wang, Fudong Ge, Weiming Hu, Jin Gao, Zhipeng Zhang. MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation. arXiv preprint arXiv:2610.33546v1 : https://arxiv.org/abs/2610.33546v1
  • Yixuan Li, Yuxuan Jiang, Hanwei Zhu, Hancheng Zhu, Fan Zhang, Shiqi Wang, David Bull. Of Chains and Gains: What Reinforcement Learning changes on Reasoning-based Image Quality Assessment. arXiv preprint arXiv:2610.33203v1 : https://arxiv.org/abs/2610.33203v1
  • Yuhang Han, Dingning Liu, Yujie Chen, Yaojie Zhang, Jingwei Song, Zequn Yang, Xuanming Shang, Li Ding, Zhijiang Guo, Linfeng Zhang. From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning. arXiv preprint arXiv:2610.32324v1 : https://arxiv.org/abs/2610.32324v1
  • Shibo Hong, Siyu Ren, FengJiao Chen, Zhongyuan Peng, Wei Shi, Yixin Cao. ACWM-RM: A Reference-Free Reward Model from Complementary Mismatch Preferences. arXiv preprint arXiv:2610.32222v1 : https://arxiv.org/abs/2610.32222v1
  • Khai Loong Aw, Klemen Kotar, Baihan Zhang, Yifan Liu, Lilian Chen, Atlas Kazemian, Rahul Venkatesh, Daniel Yamins. $Ψ$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model. arXiv preprint arXiv:2610.32177v1 : https://arxiv.org/abs/2610.32177v1
  • Xueyun Tian, Bingbing Xu, Jiaming Liu, Jinpeng Yu, Yang Shi, Yu Zhao, Ruihua Huang, Yuanzhuo Wang, Huawei Shen. SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding. arXiv preprint arXiv:2610.32132v1 : https://arxiv.org/abs/2610.32132v1
  • Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu. WeVisOne-VL: Unified Visual Perception from Objects to Pixels. arXiv preprint arXiv:2610.31329v1 : https://arxiv.org/abs/2610.31329v1
  • Sidhart Sami, Ali Sharjeel, Sri Atluri, Miao Zhao, Caroline Roney, Eirini Marouli, Shaheer U. Saeed. Reinforcing intra-operative tumour localisation with weak supervision from pre-operative appearances. arXiv preprint arXiv:2610.31253v1 : https://arxiv.org/abs/2610.31253v1
  • Zecong Tang, Zian Guan, Yuncheng Guo, Zhanqiu Zhang, Yiwen Guo, Bo Dai. HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games. arXiv preprint arXiv:2610.31162v1 : https://arxiv.org/abs/2610.31162v1
  • Yuanze Hu, Zhichao Yang, Junwei Jing, Xin Yang, Wenxuan Liu, Tinghai Zhang, Jia Fu, Hongzhi Zhang, Xiangyu Wu, Ruiming Tang, Tingting Gao, Han Li. Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning. arXiv preprint arXiv:2610.31111v1 : https://arxiv.org/abs/2610.31111v1
  • Mingyu Sheng, Jianan Fan, Dongnan Liu, Guoyan Zheng, Ron Kikinis, Weidong Cai. Revisiting Distribution Matching for State-to-Vision Policy Distillation in Laparoscopic Robotic Manipulation. arXiv preprint arXiv:2610.31010v1 : https://arxiv.org/abs/2610.31010v1
  • Zhaolu Kang, Tailong Luo, Chenxin Li, Yingjie He, Zhenyu Yu, Fengyu Zhou, Jiachen Qian, Lei Wei, Shuang Chen, Jiachen Li, Eric Hanchen Jiang, Rongchao Zhang, Zhengtao Yao, Hoi Leong Lee, Guansu Wang, Kaiyue Zhou. RECAP: Looking Once Is Not Enough for Vision-Language Reasoning. arXiv preprint arXiv:2610.30834v1 : https://arxiv.org/abs/2610.30834v1
  • Zhaolu Kang, Tailong Luo, Lei Wei, Guangyuan Dong, Sihan Liu, Yingjie He, Siheng Wang, Shuaibo Li, Rongchao Zhang, Zhen Tian, Richeng Xuan, Zhichao Hu. DRILL: Training World Models to Improve Policies, Not Predict Pixels. arXiv preprint arXiv:2610.30814v1 : https://arxiv.org/abs/2610.30814v1
  • Zikang Xiong, Weixin Li, Zhouchonghao Wu, Akshay Rangesh, Saarth Bonde, Grantland Hall, Chen Tang, Yihan Hu, Wei Zhan. TerraTransfer++: Demonstration-Free End-to-End Planner. arXiv preprint arXiv:2610.30319v1 : https://arxiv.org/abs/2610.30319v1
  • Likui Zhang, Zhe Zhu, Zhihao Zhan, Yibo Bai, Hanlin Wang, Dongwei Li, Bin Wang, Tianle Zhang, Xiaodan Liang, Liang Lin. AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation. arXiv preprint arXiv:2610.30097v1 : https://arxiv.org/abs/2610.30097v1
  • Mingze Sun, Ziang Cao, Yuan Fei, Qiankuan Tao, Zihan Wang, Tianqi Liu, Junhao Chen, Haiwen Diao, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu. DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations. arXiv preprint arXiv:2610.29997v1 : https://arxiv.org/abs/2610.29997v1
  • Jingzhe Zhang, Peixuan Zhang, Genying Li, Bing Ma, Shuchen Weng, Si Li, Boxin Shi. CineEvolve: An Agentic Self-Evolution Framework for Cinematic Multi-Shot Video Generation. arXiv preprint arXiv:2610.29590v1 : https://arxiv.org/abs/2610.29590v1
  • Xin Zhang, Haochen Wang, Beibei Lin, Zhaoxiang Zhang, Robby T. Tan, Jason Li, Dacheng Tao. Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding. arXiv preprint arXiv:2610.29552v1 : https://arxiv.org/abs/2610.29552v1
  • Sicong Kang, Fangao Zeng, Yuhan Li, Hao Zhou, Mengfei Xu, Wenxiang Shang, Wei Li, Bingbing Ni, Pipei Huang. AdvFidelity: Unifying Preference Alignment and Few-Step Image Generation within Reinforcement Learning. arXiv preprint arXiv:2610.29380v1 : https://arxiv.org/abs/2610.29380v1
  • Junjie Wang, Zhihao Yuan, Yunhan Tang, Sheng Xu, Jiaqi Mao, Xiaoyu Ye, Yueru Luo, Xu Yan, Chun-Mei Feng, Zhen Li. Think-Capture: Active 3D Geometry Acquisition for Spatial Reasoning in Vision-Language Models. arXiv preprint arXiv:2610.29232v1 : https://arxiv.org/abs/2610.29232v1
  • Jiachen Guo, Xinshan Zhu, Boyun Wang, Yanyan Liang, Jun Wan, Feng Lin, Ajian Liu. LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency. arXiv preprint arXiv:2610.29174v1 : https://arxiv.org/abs/2610.29174v1
  • Simran Khanuja, Rohit Gandikota, Gaurav Parmar, Graham Neubig. T-DIG: Text-Conditioned Diversity for Image Generation. arXiv preprint arXiv:2610.29003v1 : https://arxiv.org/abs/2610.29003v1
  • Yuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton. DualHeads: Reward-tilted few-step diffusion made simple. arXiv preprint arXiv:2610.28858v1 : https://arxiv.org/abs/2610.28858v1
  • Mauricio Soroco, Yuqiu Liu, Zaid Tasneem, Francesco Pittaluga, Abhishek Aich, Wuyang Chen, Manmohan Chandraker, Ziyu Jiang. HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics. arXiv preprint arXiv:2610.28829v1 : https://arxiv.org/abs/2610.28829v1
  • Yiqing Shen, Mathias Unberath. Complexity-Aware Surgical Video Reasoning Segmentation with Digital Twin and Context Memory. arXiv preprint arXiv:2610.28776v1 : https://arxiv.org/abs/2610.28776v1
  • Yuxuan Kuang, Jiashun Wang, Yixuan Sun, Yufei Ye, Sungjae Park, Umar Iqbal, Katerina Fragkiadaki, Shubham Tulsiani. Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking. arXiv preprint arXiv:2610.28628v1 : https://arxiv.org/abs/2610.28628v1
  • Siyuan Ma, Yu Qi, Cheng Ye, Ruotian Peng, Xinyi Xu, Zitiantao Lin, Zedong Cai, Yijian Huang, Weiyang Liu, Siyuan Wang, Yandong Wen. RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation. arXiv preprint arXiv:2610.27782v1 : https://arxiv.org/abs/2610.27782v1
  • Zhenxuan Wang, Jisheng Dang, Ronghao Lin, Bimei Wang, Jingwen Zhao, Wenjun Ma, Bin Hu, Qi Tian, Tat-Seng Chua. PACE-MoE: Adaptive Domain Sampling and Domain-Specific LoRA for Medical Visual Grounding. arXiv preprint arXiv:2610.27656v1 : https://arxiv.org/abs/2610.27656v1
  • Zerui Chen, Changrui Chen, Fei Ni, Jiankang Deng. Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning. arXiv preprint arXiv:2610.27341v1 : https://arxiv.org/abs/2610.27341v1
  • Shiao Xie, Siyu Chen, Jianwei Lv, Xiandong Li, Yujin Wang. Reinforcement Learning with Visually Attributable On-Policy Self-Distillation. arXiv preprint arXiv:2610.26856v1 : https://arxiv.org/abs/2610.26856v1
  • Yaqi Cai, Zuan Gao, Mengting Chen, Wei Li, Bo Zheng. CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing. arXiv preprint arXiv:2610.26740v1 : https://arxiv.org/abs/2610.26740v1
  • Hailiang Yang, Shengchao Chen. Policy-Adaptive Credit Assignment for Spatial Reasoning with Verifiable Rewards. arXiv preprint arXiv:2610.26410v1 : https://arxiv.org/abs/2610.26410v1
  • Ridouane Ghermi, Vicky Kalogeiton, Ivan Laptev. From Cause to Effect: Generating Intermediate Event Chains in Videos. arXiv preprint arXiv:2610.26275v1 : https://arxiv.org/abs/2610.26275v1
  • Mingyang Wu, Kaituo Feng, Bohao Li, Kaixiong Gong, Zihao Yin, Xiangyu Yue. AVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional Alignment. arXiv preprint arXiv:2610.26046v1 : https://arxiv.org/abs/2610.26046v1
  • Jiaxuan Sun, Biao Wang, Shuai Li. FrameGRPO: Incentivizing Video Reasoning via Multi-Frame Rollouts and Temporal Credit. arXiv preprint arXiv:2610.26022v1 : https://arxiv.org/abs/2610.26022v1
  • Zixuan Chen, Depeng Wang, Wei Chen, Ke Xu, Ya Guo, Huijia Zhu, Tanfeng Sun, Xinghao Jiang. SAPO: Self-Supervised Attention Policy Optimization for Improving Temporal Video Grounding in Vision-Language Models. arXiv preprint arXiv:2610.25923v1 : https://arxiv.org/abs/2610.25923v1
  • Zhongyu Wang, Chen Zuo, Qingxuan Sun, Jiayang Qiao, Qiuhao Qian, Songyan Cui, Guocheng Chen. MAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement Learning. arXiv preprint arXiv:2610.25748v1 : https://arxiv.org/abs/2610.25748v1
  • Shuochen Chang, Bingjie Gao, Qingyang Liu, Qianli Ma, Yibo Miao, Haonan Zhao, Zhaohe Liao, Xiaofeng Zhang, Jiangtong Li, Li Niu. From Label Priors to Task Evidence: Efficient Long-Video Frame Selection via Bayesian GRPO. arXiv preprint arXiv:2610.25418v1 : https://arxiv.org/abs/2610.25418v1
  • Junwei Wen, Deshui Miao, Guangming Lu, Ming-Hsuan Yang, Xin Li, Wenjie Pei. Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation. arXiv preprint arXiv:2610.25090v1 : https://arxiv.org/abs/2610.25090v1
  • Qijian Tian, Jiayu Ying, Ke Fan, Lizhuang Ma, Xin Tan. From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models. arXiv preprint arXiv:2610.24676v1 : https://arxiv.org/abs/2610.24676v1
  • Julius Erbach, Dominik Narnhofer, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler. PONDER: Learning to Generate in the Right Order. arXiv preprint arXiv:2610.23531v1 : https://arxiv.org/abs/2610.23531v1
  • Xuanyu Liu, Hongyan Feng, Miao Pan, Sunlai Chen, Lizhou Liang, Bing Sun, Wenqi Zhang, Xuhong Zhang. Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation. arXiv preprint arXiv:2610.23121v1 : https://arxiv.org/abs/2610.23121v1
  • Qiuhong Shen, Yiding Yang, Yuxin Zhang, Xinwei Huang, Minxuan Lin, Bo Liu, Hao Kang, Haotian Yang, Yizhi Wang, Chongyang Ma, Xinchao Wang. Routing Policy Optimization for Online Diffusion Reinforcement Learning. arXiv preprint arXiv:2610.22282v1 : https://arxiv.org/abs/2610.22282v1
  • Yufei Jiao, Jinfa Huang, Zeyue Xue, Tianyu Xie, Yuexiao Ma, Rongrong Ji, Xiawu Zheng, Jiebo Luo. SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation. arXiv preprint arXiv:2610.22264v1 : https://arxiv.org/abs/2610.22264v1
  • Huanyao Zhang, Jiepeng Zhou, Jiaye Lin, Ontai Tang, Jingtian Hao, Mugeng Liu, Ru Peng, Lang Mei, Xiaohan Yu, Liyan Liu, Chong Chen, Wentao Zhang. MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents. arXiv preprint arXiv:2610.22240v1 : https://arxiv.org/abs/2610.22240v1
  • Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Qing Yang, Zhenghao Liu, Zulong Chen, Yu Gu, Ge Yu. Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models. arXiv preprint arXiv:2610.22217v1 : https://arxiv.org/abs/2610.22217v1
  • Zhao Yang, Zezhong Qian, Yinan Shi, Longjun Liu, Yawei Jueluo. GRID-Planner: Graph-Structured Relational Reward Shaping for Diffusion Planning. arXiv preprint arXiv:2610.21984v1 : https://arxiv.org/abs/2610.21984v1
  • Yijiang Li, Bingyang Wang, Nuno Vasconcelos. Learning to Think and Explore in 3D World. arXiv preprint arXiv:2610.21783v1 : https://arxiv.org/abs/2610.21783v1
  • Yiran Zhang, Hanbo Huang, Jielan Li, Zhen Zhao, Shiyu Liang, Hongxia Hao. Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence. arXiv preprint arXiv:2610.21671v1 : https://arxiv.org/abs/2610.21671v1
  • Zhiyuan Ma, Jiabao Wei, Tianyu Wang, Hanqing Wang, Jiadong Pan, Haowen Xu, Liangliang Zhao, Ruixun Liu, Yuhan Wang, Yuwei Zhang, Liang Feng, Junhao Xiao, Kaiyan Zhang, Xuekai Zhu, Daizong Liu, Biqing Qi, Yihao Liu, Ganqu Cui, Ning Ding, Linfeng Zhang, Jianjun Li, Kun He, Xiang Bai, Bowen Zhou. Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond. arXiv preprint arXiv:2610.21539v1 : https://arxiv.org/abs/2610.21539v1
  • Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang Gan. Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs. arXiv preprint arXiv:2610.21380v1 : https://arxiv.org/abs/2610.21380v1
  • Sujie Hu, Huaisong Zhang, Pujing Yang, Qian Wang, Xiaomin Li, Xinhang Leng, Chen Li, Jing Lyu, Xiu Li, Ling Pan. Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation. arXiv preprint arXiv:2610.20794v1 : https://arxiv.org/abs/2610.20794v1
  • Xinrui Lin, Fan Li, Shumin Wang, Dehong Kong, Yanyong Zhang. When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO. arXiv preprint arXiv:2610.20089v1 : https://arxiv.org/abs/2610.20089v1
  • Tomáš Čížek, Matej Straka, Illia Volkov, Matěj Kripner, Ervin Macić, Jiri Matas, Klara Janouskova, Martin Schmid. SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking. arXiv preprint arXiv:2610.19931v1 : https://arxiv.org/abs/2610.19931v1
  • Shanyan Guan, Shiyu Li, Xin Li, Zhizhou Chen, Yunzhe Xu, Yuehao Liu, Ruixue Shen, Shiju Zhang, Min Jin, Qiang Liu, Junbo Liu, Penggang Shi, Sheng Sun, Xiao Wang, Yong Zhang, Zhongang Qi, Wei Li, Chao Ma, Ying Tai, Yanhao Ge. BluePixel: Toward Native 4K Agentic Image Editing. arXiv preprint arXiv:2610.19882v1 : https://arxiv.org/abs/2610.19882v1
  • Cheng Fan, Bingyang Zhou, Gang Yang, Zixuan Zhuang, Aoqian Zhang, Pengzhi Yang, Xin Liu, Chunzheng Wang, Yan Rui Tan, Fan Shi. E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots. arXiv preprint arXiv:2610.19627v1 : https://arxiv.org/abs/2610.19627v1
  • Diyuan Shi, Yiqi Tang, Hongyin Zhang, You Wu, Donglin Wang. VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning. arXiv preprint arXiv:2610.19517v1 : https://arxiv.org/abs/2610.19517v1
  • Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo. ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models. arXiv preprint arXiv:2610.18596v1 : https://arxiv.org/abs/2610.18596v1
  • Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li. Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes. arXiv preprint arXiv:2610.18356v1 : https://arxiv.org/abs/2610.18356v1
  • Sirui Zhang, Fangyun Wei, Dong Chen, Jinjing Zhao, Yitong Wang, Yunuo Chen, Baining Guo, Zheng-Jun Zha. APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation. arXiv preprint arXiv:2610.18097v1 : https://arxiv.org/abs/2610.18097v1
  • Shangqing Zhou, Zhennan Jiang, Ning Ma, Xin Fu, Yupeng Zheng, Shuai Tian, Huangrui Li, Jiahao Liu, Chao Yu, Zhongpu Xia, Haoran Li, Dongbin Zhao. WoVR+: World Model as Reliable Simulator for Versatile VLA Policy Optimization with RL. arXiv preprint arXiv:2610.17922v1 : https://arxiv.org/abs/2610.17922v1
  • Jiahao Meng, Zhongyuan Bao, Yue Tan, Haiquan Wen, Renrui Zhang, Anna Wang, Jason Li, Yanwei Fu, Yunhai Tong, Ming-Hsuan Yang. Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence. arXiv preprint arXiv:2610.17656v1 : https://arxiv.org/abs/2610.17656v1
  • Shuyue Stella Li, Jacqueline He, Jiahui Chen, Sreya Dutta Roy, Yulia Tsvetkov, Luke Zettlemoyer, Marjan Ghazvininejad, Xiaochuang Han. IsoVRBench: Video Reward Modeling Without Human Feedback. arXiv preprint arXiv:2610.17234v1 : https://arxiv.org/abs/2610.17234v1
  • Ekko He, Jack Hong, Shilin Yan, Xintong Zhang, Yujie Zhang, Wenjie Li, Haoran Sun, Kaixun Jiang, Jiyuan Fu, Guannan Zhang, Hongwei Xue. Neos: Learning to Interleave Search and Visual Reasoning. arXiv preprint arXiv:2610.17043v1 : https://arxiv.org/abs/2610.17043v1
  • Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Hongchen Luo, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha. MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation. arXiv preprint arXiv:2610.17009v1 : https://arxiv.org/abs/2610.17009v1
  • Lihao Zheng, Zhenwei Shao, Zhou Yu, Yan Yang, Haoyi Sun, Qian Wang, Ning Mao, Pan Zhou. VAttnPO: Visual Attention-Guided Policy Optimization. arXiv preprint arXiv:2610.16735v1 : https://arxiv.org/abs/2610.16735v1
  • Runhua Zhang, Yingjie Niu, Chao Li. DR-APO: Decoupled-Representation Advantage-Guided Policy Optimization from Continuous Control to Embodied Navigation. arXiv preprint arXiv:2610.16618v1 : https://arxiv.org/abs/2610.16618v1
  • Wenzhan Li, Yiran Qin, Heng Zhou, Huirui Wang, Yulan Guo, Ruimao Zhang. Trust-Calibrated VLA Policy Post-Training with Evolving Imagination. arXiv preprint arXiv:2610.16517v1 : https://arxiv.org/abs/2610.16517v1
  • Zixu Wang, Xiaoran Zhao, Yahui Liu, Feng-ao Wang, Junhao Xiao, You Shu, Bing Liu, Yiting Liu, Songlei Jian, Zhiliang Tian, Dongsheng Li. Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation. arXiv preprint arXiv:2610.16224v1 : https://arxiv.org/abs/2610.16224v1
  • Guowen Zhang, Boshen Xu, Zihao Yue, Ziheng Wang, Xiaokun Liu, Xin Tao, Wenyu Qin, Pengfei Wan, Qin Jin. EventLens: Event-Structure Reinforcement Learning for Video Understanding. arXiv preprint arXiv:2610.16172v1 : https://arxiv.org/abs/2610.16172v1
  • Seongmin Park, Jaewon Lee, Yujun Heo, Yoonsik Kim, Seheon Choi, Hyoung-rock Kim, Jungwook Choi. Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning. arXiv preprint arXiv:2610.15675v1 : https://arxiv.org/abs/2610.15675v1
  • Xin Liu, Yutong Jiang, Jian Su, Ziheng Wang, Chuang Wang, Haoran Li, Dongbin Zhao. Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating. arXiv preprint arXiv:2610.15401v1 : https://arxiv.org/abs/2610.15401v1
  • Wenxi Yang, Yuzhong Zhao, Baochang Zhang, Yunfan Liu, Qixiang Ye. Self-Evolving Visual Agent via Margin Reward. arXiv preprint arXiv:2610.15084v1 : https://arxiv.org/abs/2610.15084v1
  • Thanh Nguyen, Hee Suk Yoon, Tung Minh Luu, Eunseop Yoon, Chang D. Yoo. Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning. arXiv preprint arXiv:2610.14976v1 : https://arxiv.org/abs/2610.14976v1
  • Thanh Nguyen, Abu Hanif Muhammad Syarubany, Hwanhee Kim, Chang D. Yoo. Compositional Average Velocity Modeling for Efficient Diffusion Offline Reinforcement Learning. arXiv preprint arXiv:2610.14941v1 : https://arxiv.org/abs/2610.14941v1
  • Jiahe Feng. VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning. arXiv preprint arXiv:2610.14939v1 : https://arxiv.org/abs/2610.14939v1
  • Shutong Ding, Zhaoyang Liu, Yimiao Zhou, Jingya Wang, Jiayuan Gu, Ye Shi. CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance. arXiv preprint arXiv:2610.14936v1 : https://arxiv.org/abs/2610.14936v1
  • Xiaofeng Tan, Jiaxin Lin, Haobo Yuan, Tiancheng Shen, Zihan Su, Rui Chen, Hongsong Wang, Ming-Hsuan Yang. Getting Space Right: Agentic Rewards for Image Generation. arXiv preprint arXiv:2610.14852v1 : https://arxiv.org/abs/2610.14852v1
  • Bahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang, Akshay L Chandra, Abhinav Valada. Dream to Remember: Continual Steering of Generalist Robot Policies with World Models. arXiv preprint arXiv:2610.13816v1 : https://arxiv.org/abs/2610.13816v1
  • Changhui Jing, Haochen Tian, Hongchen Li, Tianyu Li, Caojun Wang, Zihao Zhang, Yanhao Liu, Chengen Xie, Bailin Li, Hao Zhao, Zhenjie Yang. SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models. arXiv preprint arXiv:2610.13781v1 : https://arxiv.org/abs/2610.13781v1
  • Yuechen Luo, He Chong, Fang Li, Shaoqing Xu, Hexin Zhang, Ruiqi Zhang, Ziying Song, Lei Yang, Zhi-Xin Yang, Fuxi Wen. Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving. arXiv preprint arXiv:2610.13453v1 : https://arxiv.org/abs/2610.13453v1
  • Zheming Fu, Wenbin Ning, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lianrui Mu, Chang Liu, Lei Wang, Siming Fu. VideoAWR: Reinforcing Video Flow Models with Decoupled-Timestep Advantage-Weighted Rectification. arXiv preprint arXiv:2610.13338v1 : https://arxiv.org/abs/2610.13338v1
  • Qitan Lv, Ke Fan, Hong Wang, Wen Wu, Yilin Wang, Bowen Zhou, Feng Wu, Chao Zhang. OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training. arXiv preprint arXiv:2610.13272v1 : https://arxiv.org/abs/2610.13272v1
  • Sida Li, Yuanxin Liu, Linli Yao, Shicheng Li, Xu Sun, Haoli Bai, Xiaohui Li. AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning. arXiv preprint arXiv:2610.13184v1 : https://arxiv.org/abs/2610.13184v1
  • Xu Zhang, Haohan Wang, Zheng Zhang, Yingjie Xia, Wei Feng, Honghe Zhu, Jingjing Lv, Changping Peng, Xuheng Qin, Zehua Zhang, Zheng Luo, Qicheng Li. Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment. arXiv preprint arXiv:2610.13066v1 : https://arxiv.org/abs/2610.13066v1
  • Xule Gao, Xi Wang, Zehua Zang, Rui Wang, Changwen Zheng, Chuxiong Sun. OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models. arXiv preprint arXiv:2610.12914v1 : https://arxiv.org/abs/2610.12914v1
  • Jusuk Lee, Sungha Kim, Yeonsoo Park, Jonguk Cheon, Yoonkyo Jung, Yongjun You, H. Jin Kim, Jia-Bin Huang, Furong Huang, Youngseok Jang, Seungjae Lee. Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration. arXiv preprint arXiv:2610.12470v1 : https://arxiv.org/abs/2610.12470v1
  • Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan, Zhaoxiang Zhang. DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training. arXiv preprint arXiv:2610.12468v1 : https://arxiv.org/abs/2610.12468v1
  • Hongxing Li, Yixin Li, Dingming Li, Zixuan Wang, Yuchen Yan, Wenqi Zhang, Weiming Lu, Yongliang Shen. Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models. arXiv preprint arXiv:2610.12355v1 : https://arxiv.org/abs/2610.12355v1
  • Ruicheng Zhang, Kaiwen Shen, Jiaqi Hou, Shuhan Yang, Junchao Huang, Kewei Zhang, Jun Zhou, Li Jiang, Shen Zhao. ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation. arXiv preprint arXiv:2610.12107v1 : https://arxiv.org/abs/2610.12107v1
  • Wenhao Li, Xianjing Meng, Qiangchang Wang, Zhongyi Han, Yilong Yin, Liqiang Nie. DVLA-RL++: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning. arXiv preprint arXiv:2610.12095v1 : https://arxiv.org/abs/2610.12095v1
  • Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu, Zhiyuan Gao, Yanxiang Zhan, Jeroen Schafer, Andrew Melnik, Qing Yang, Michael Beetz. CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding. arXiv preprint arXiv:2610.11971v1 : https://arxiv.org/abs/2610.11971v1
  • Filip Grigorov, Kourosh Darvish, Nandita Vijaykumar. FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment. arXiv preprint arXiv:2610.11119v1 : https://arxiv.org/abs/2610.11119v1
  • Raja Kumar, Rajat Koner, Ritwick Chaudhry, Zhuowei Li, Nishant Sankaran, Yifan Xing. SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages. arXiv preprint arXiv:2610.10889v1 : https://arxiv.org/abs/2610.10889v1
  • Gengze Zhou, Yicong Hong, Jiazhao Zhang, Xunyi Zhao, Jian Zhou, Zixing Lei, Zun Wang, Chongyang Zhao, Xionghui Chen, Stephen Gould, Anton van den Hengel, Qi Wu. NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime. arXiv preprint arXiv:2610.10787v1 : https://arxiv.org/abs/2610.10787v1
  • Meng Lu, Ligeng Zhu, Olivia Xiao, Yuchen Zhuang, Zihan Wang, Kuncheng Wu, Bangya Liu, Yu Wang, Charles Fleming, Wenqi Shi, Xuan Wang. VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning. arXiv preprint arXiv:2610.10782v1 : https://arxiv.org/abs/2610.10782v1
  • Yuxiang Xiong, Ruiyan Wang, Wenqiang Wang, Teng Hu, Songhang Shen, Bohao Feng, Hongqian Deng, Ran Yi. MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration. arXiv preprint arXiv:2610.10457v1 : https://arxiv.org/abs/2610.10457v1
  • Haoru Li, Jinmei Liu, Zhiyong Wang, Xiaoming Li, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang. Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization. arXiv preprint arXiv:2610.09943v1 : https://arxiv.org/abs/2610.09943v1
  • Mahmoud Selim, Cristina Cipriani, Karl Henrik Johansson. Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving. arXiv preprint arXiv:2610.09763v1 : https://arxiv.org/abs/2610.09763v1
  • Samuel Tetteh, Cody Fleming. It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank. arXiv preprint arXiv:2610.09517v1 : https://arxiv.org/abs/2610.09517v1
  • Eunji Shin, Dahyun Choi, Seungyeon Jo, Yejin Hong, Jiyoung Lee. TiTok: Audio-Visual LLM for Multi-Segment Temporal Grounding. arXiv preprint arXiv:2610.09408v1 : https://arxiv.org/abs/2610.09408v1
  • Songbo Hu, Qiayuan Liao, Yufeng Chi, Kevin Zakka, Yakun Sophia Shao, Pieter Abbeel, Koushil Sreenath. Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data. arXiv preprint arXiv:2610.09117v1 : https://arxiv.org/abs/2610.09117v1
  • Suxin Ji, Hungtao Wan, Mingjun Liu, An Zhang. Selective Transfer of RL Updates for Visual Reasoning. arXiv preprint arXiv:2610.08659v1 : https://arxiv.org/abs/2610.08659v1
  • Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Haitao Yang, Songchang Jin, Dianxi Shi. RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation. arXiv preprint arXiv:2610.08640v1 : https://arxiv.org/abs/2610.08640v1
  • Welf Rehberg, Kostas Alexis. Sensor-Layout-Agnostic Navigation via Geometric Observation Canonicalization. arXiv preprint arXiv:2610.08306v1 : https://arxiv.org/abs/2610.08306v1
  • George Sideris, Lucas Bessai, Heshan Fernando, Elie Ayoub, Nicolas Lemieux, Inna Sharf. Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane. arXiv preprint arXiv:2610.07613v1 : https://arxiv.org/abs/2610.07613v1
  • Youngjae Cho, Won Young Jhoo, Jongsuk Kim. Beyond Scalar IoU: Structured Verification from Rollout Groups for Video Temporal Grounding. arXiv preprint arXiv:2610.07601v1 : https://arxiv.org/abs/2610.07601v1
  • Shichao Zhai, Shuhao Ye, Rong Xiong, Yue Wang. Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study. arXiv preprint arXiv:2610.06958v1 : https://arxiv.org/abs/2610.06958v1
  • Mousumi Das, Aditeya Prajapati, Abrar Anwar, Jesse Thomason. SWAP: Stepwise Action Policy Routing for Vision-Language-Action Models. arXiv preprint arXiv:2610.06926v1 : https://arxiv.org/abs/2610.06926v1
  • Álvaro Díez, Fidel Aznar. Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design. arXiv preprint arXiv:2610.06400v1 : https://arxiv.org/abs/2610.06400v1
  • Weijie Zhu, Han Fang, Hanyu Fu, Yuzhe Zhang, Xin Wei, Zhaoyan Pan, Feiran Liu, Xunjie Jin, Hongbo Sun, Zhiyu Lin, Tianyi Gao, Tianyi Ding, Ye Yuan, Zhongjiang He, Hao Sun, Zhiheng Wu. MeSD: Multi-Evidence Self-Distillation for VideoLLM. arXiv preprint arXiv:2610.06342v1 : https://arxiv.org/abs/2610.06342v1
  • Qiutong Chen, Yuchan Guo, Zhenlong Yuan, Haobo Yang, Fangfang Lin, Xinyi Long, Yin Wang, Zijian Song, Rui Lan, Shi Qiu, Boyuan Pan, Yang Luo, Yuyin Zhou. VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction. arXiv preprint arXiv:2610.06293v1 : https://arxiv.org/abs/2610.06293v1
  • Zexin Li, Ruili Yao, Yiming Zeng, Xiaoxue Gao. Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning. arXiv preprint arXiv:2610.06083v2 : https://arxiv.org/abs/2610.06083v2
  • Shuo Chen, Fengming Huang, Yu Yao, Mingming Gong, Tongliang Liu. Scalable Minimal-Change Learning for Controllable Image Editing. arXiv preprint arXiv:2610.06021v1 : https://arxiv.org/abs/2610.06021v1
  • Bram Grooten, Joaquin Vanschoren. How (and How Not) to Use Data Augmentation in VLA Post-Training. arXiv preprint arXiv:2610.05994v1 : https://arxiv.org/abs/2610.05994v1
  • Shreshth Saini, Neil Birkbeck, Yilin Wang, Balu Adsumilli, Alan C. Bovik. MEND: RL For Flow Models via Proximal Velocity Matching. arXiv preprint arXiv:2610.05954v1 : https://arxiv.org/abs/2610.05954v1
  • Eungyeol Han, Jong-Seok Lee. Safe Image Generation via Reinforcement Learning. arXiv preprint arXiv:2610.05908v1 : https://arxiv.org/abs/2610.05908v1
  • Ali Vosoughi, Akhil Kasturi, Chenliang Xu, Axel Wismueller. Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking. arXiv preprint arXiv:2610.05425v1 : https://arxiv.org/abs/2610.05425v1
  • Runwei Guan, Rongsheng Hu, Shangshu Chen, Ningwei Ouyang, Shaofeng Liang, Heyi Lin, Jinjing Zhu, Yang Shi, Dongming Wu, Daizong Liu, Henghui Ding, Hui Xiong. Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes. arXiv preprint arXiv:2610.05274v1 : https://arxiv.org/abs/2610.05274v1
  • Yunyi Chen, Chenru Wang, Xinyi Ye, Zexin Zheng, Chi Zhang. MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset Distillation. arXiv preprint arXiv:2610.05252v1 : https://arxiv.org/abs/2610.05252v1
  • Hao Jiang, Zhanyu Guo, Chenwei Wu, Yichen Guo, Qizhe Zhang, Junchi Yao, Jixian Wu, Jinhao You, Kai Tang, Jiajun Cao, Tinghao Wang, Mengyu Wang, Leo Anthony Celi, Shanghang Zhang. ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory. arXiv preprint arXiv:2610.05097v1 : https://arxiv.org/abs/2610.05097v1
  • Zhexin Lou, Guancheng Lu, Zeyu Zhang, Yi Zhang, Yang Zhao, Hao Tang. PWM: Personalized World Models with Online Reinforcement Learning. arXiv preprint arXiv:2610.04920v1 : https://arxiv.org/abs/2610.04920v1
  • Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Jianyu Wang, XueLin Zheng. Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning. arXiv preprint arXiv:2610.04918v1 : https://arxiv.org/abs/2610.04918v1
  • Wenxin Zhan, Yizheng Jiao, Haifeng Song, Shuai Xu, Chencheng Pan, Jiayi Feng, Anjie Xie. TrustMed-RL: Long-Horizon Reinforcement Learning for Evidence-Grounded Clinical Diagnosis. arXiv preprint arXiv:2610.04387v1 : https://arxiv.org/abs/2610.04387v1
  • Tahira Kazimi, Shubhankar Borse, Munawar Hayat, Fatih Porikli, Pinar Yanardag. HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation. arXiv preprint arXiv:2610.02197v1 : https://arxiv.org/abs/2610.02197v1
  • Haibo Wang, Jiteng Mu, Jialu Li, Jingru Yi, Yuanjun Xiong, Jianming Zhang, Lifu Huang, Mingze Xu. OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning. arXiv preprint arXiv:2610.02181v1 : https://arxiv.org/abs/2610.02181v1
  • Guangyu Yang, Jingbiao Mei, Mingsheng Sun, Jinghong Chen, Yingtong Bu, Pengda Qin, Da Chen, Bill Byrne. Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization. arXiv preprint arXiv:2610.02019v1 : https://arxiv.org/abs/2610.02019v1
  • Yifan Wang, Gordon Guocheng Qian, Yanyu Li, Anil Kag, Yun Fu. Token-Level Video Reinforcement Learning. arXiv preprint arXiv:2610.01973v1 : https://arxiv.org/abs/2610.01973v1
  • Akshit Singh, Shyam Marjit, Wei Lin, Leonid Karlinsky, M. Jehanzeb Mirza. Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models. arXiv preprint arXiv:2610.01687v1 : https://arxiv.org/abs/2610.01687v1
  • Zhen Zhou, Zhiwei Ning, Puhua Jiang, Sheng Zhang, Yifei Tang, Jie Yang, Xintong Han, Wei Liu, Chunchao Guo. Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization. arXiv preprint arXiv:2610.01233v1 : https://arxiv.org/abs/2610.01233v1
  • Hao Wu, Shengju Qian, Weiyan Wang, Fan Xu, Fan Zhang, Yuanpeng He, Qingsong Wen, Yuxuan Liang. FutureWorlds: Learning Robotic World Models from Alternative Futures. arXiv preprint arXiv:2610.01019v1 : https://arxiv.org/abs/2610.01019v1
  • Kaixuan Fan, Kaituo Feng, Tianshuo Peng, Yilei Jiang, Manyuan Zhang, Junke Wang, Xiangyu Yue. EviRover: Reinforcing Agentic Perception Beyond a Glance. arXiv preprint arXiv:2609.40230v1 : https://arxiv.org/abs/2609.40230v1
  • Guangzhi Xiong, Xinyuan Zhang, Xiao Yang, Hyokun Yun, Kai Zhang, Shiun-Zu Kuo, Hyeonjeong Ha, Xilun Chen, Kai Sun, Lucas Liang, Guangqiang Dong, Ejaz Ahmed, Ahmed A Aly, Anuj Kumar, Raffay Hamid, Aidong Zhang, Xin Luna Dong. MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories. arXiv preprint arXiv:2609.40195v1 : https://arxiv.org/abs/2609.40195v1
  • Jinhao Chen, Benlei Cui, Ruijian Jia, Ziheng Wang, Tianyu Wo, Pengfei Sun, Longtao Huang, Hui Xue, Yitong Yang, Haiwen Hong. Grounding with Confidence: Controllable Generative Video Temporal Grounding. arXiv preprint arXiv:2609.39883v2 : https://arxiv.org/abs/2609.39883v2
  • Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang, Yixiao Ge, Shuchang Zhou, Shilong Liu, Xianming Liu, Ping Luo, Shiyu Huang. GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives. arXiv preprint arXiv:2609.39601v1 : https://arxiv.org/abs/2609.39601v1
  • Minye Shao, Chaohui Yu, Yixuan Wu, Fan Wang, Ling Shao, Yang Long. From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning. arXiv preprint arXiv:2609.39566v1 : https://arxiv.org/abs/2609.39566v1
  • Shu Yu, Chaochao Lu. CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models. arXiv preprint arXiv:2609.39441v1 : https://arxiv.org/abs/2609.39441v1
  • Gengyuan Zhang, Xiao Han, Xinyu Xie, Tong Liu, Volker Tresp. Rethinking Multi-Image Re-Representation in Multi-Image Understanding. arXiv preprint arXiv:2609.39363v1 : https://arxiv.org/abs/2609.39363v1
  • Pengzhan Sun, Shiu-hong Kao, Shijie Li, Yongyi Su, Junbin Xiao, Arjun Reddy Akula, Angela Yao. Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift. arXiv preprint arXiv:2609.39183v1 : https://arxiv.org/abs/2609.39183v1
  • Haiying He, Xin Zheng, Shaoli Hu, Shijun Xiao, Xuanhe Liu, Bing Li, Harry Yang. Frame Differential On-Policy Self-Distillation for Video Reasoning. arXiv preprint arXiv:2609.39021v1 : https://arxiv.org/abs/2609.39021v1
  • Haoyu Wang, Siyuan Qian, Yanjun Li, Zeyu Zhang, Yandong Guo, Boxin Shi, Hao Tang. DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation. arXiv preprint arXiv:2610.00360v1 : https://arxiv.org/abs/2610.00360v1
  • Jialu Pi, Yanan Ma, Weijie Chen, Owen Crystal, Shubham Trivedi, Stephen Xie, Anna Silverman, Matthew Stib, Chadi Ayoub, Reza Arsanjani, Imon Banerjee. From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning. arXiv preprint arXiv:2609.38924v1 : https://arxiv.org/abs/2609.38924v1
  • Kai Yan, Xiangyu Chen, Yulong Cao, Alex Naumann, Peter Karkus, Yan Wang, Jef Packer, Alex Schwing, Yuxiong Wang, Boris Ivanovic, Wenjie Luo, Marco Pavone. Vision-Language-Action Autonomous Driving Agent with Language-based Memory. arXiv preprint arXiv:2609.38641v1 : https://arxiv.org/abs/2609.38641v1
  • Shengyun Zhong, Xinkang Zhao, Ziyuan Chu, Linchao Zhu. MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary. arXiv preprint arXiv:2609.38428v2 : https://arxiv.org/abs/2609.38428v2
  • Zheng Jiang, Houde Qian, Yiming Chen, Ling Li, Chaoyang Li, Yueqi Li, Yuxuan Liu, Lifeng Sun. VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal Agents. arXiv preprint arXiv:2609.38086v1 : https://arxiv.org/abs/2609.38086v1
  • Huan Rong, Chao Yin, Anouar Imel, Yijie Xia, Tinghuai Ma. Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy. arXiv preprint arXiv:2609.38016v1 : https://arxiv.org/abs/2609.38016v1
  • Tongbo Chen, Junbo Niu, Zhengxi Lu, Niu Lian, Fei Tang, Yuchen Yan, Yike Hong, Yong Du, Yizhou Liu, Bofan Chen, Yongliang Shen. HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents. arXiv preprint arXiv:2609.38008v1 : https://arxiv.org/abs/2609.38008v1
  • Haozhe Liu, Tian Ye, Shuchen Xue, Yitong Li, Junsong Chen, Haopeng Li, Jincheng Yu, Duomin Wang, Ruihua Zhang, Lei Zhu, Song Han, Enze Xie. SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video. arXiv preprint arXiv:2609.37969v1 : https://arxiv.org/abs/2609.37969v1
  • Xijun Wang, Xin Li, Zirui Lang, Suhang Yao, Haoran Li, Zhibo Chen. RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution. arXiv preprint arXiv:2609.37850v1 : https://arxiv.org/abs/2609.37850v1
  • Yazhen Xie, Xingsong Ye, Zhineng Chen. Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering. arXiv preprint arXiv:2609.37569v1 : https://arxiv.org/abs/2609.37569v1
  • Heyu Huang, Chi Chen, Zonghao Guo, Yuhua Li, Maosong Sun, Ruixuan Li. MG-Thinker: Bi-Axial Self-Reflection for Multi-Image Reasoning Grounding. arXiv preprint arXiv:2609.37374v1 : https://arxiv.org/abs/2609.37374v1
  • Xuehai Bai, Zhenchen Tang, Yang Shi, Dianyi Wang, Tengfei Liu, Wanshun Su, Xuanyu Zhu, Ruohui Wang, Haiwen Diao, Haotian Wang, Xiaoling Gu, Yuanxing Zhang. Think Before You Score: Thinking Reward Model for Visual Generation. arXiv preprint arXiv:2609.37372v1 : https://arxiv.org/abs/2609.37372v1
  • Songlin Yang, Xiaotong Zhao, Jiacheng Zhang, Zhe Wang, Toyota Li, Eric Liu, Alan Zhao, Anyi Rao. Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL. arXiv preprint arXiv:2609.37200v1 : https://arxiv.org/abs/2609.37200v1
  • Zhangquan Chen, Yaoxin Niu, Xiang An, Mingze Sun, Zhumei Wang, Chih-Ting Liao, Hongkun Cao, Ruqi Huang. HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent. arXiv preprint arXiv:2609.37190v1 : https://arxiv.org/abs/2609.37190v1
  • Haoran Xu, Xingzhuo Guo, Yuchen Zhang, Jincheng Zhong, Jianmin Wang, Mingsheng Long. NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters. arXiv preprint arXiv:2609.37038v1 : https://arxiv.org/abs/2609.37038v1
  • Hongbin Lin, Chaoda Zheng, Yiming Yang, Xiangyu Li, Shijia Chen, Jinhao Deng, Kangjie Chen, Dongbin Zhang, Jie Feng, Yu Zhang, Xianming Liu, Shuguang Cui, Boyang Wang, Zhen Li. RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts. arXiv preprint arXiv:2609.36851v2 : https://arxiv.org/abs/2609.36851v2
  • Yueran Ma, Ronghao Lin. Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs. arXiv preprint arXiv:2609.36798v1 : https://arxiv.org/abs/2609.36798v1
  • Cheng Ye, Weidong Chen, Bingyan Xu, Zhendong Mao. DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning. arXiv preprint arXiv:2609.36775v1 : https://arxiv.org/abs/2609.36775v1
  • Hanwen Lu, Jun He, Mingjia Yang, Hao Wei, Jinhao Huang, Yi Lin, Xiang Zhang. CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation. arXiv preprint arXiv:2609.36616v1 : https://arxiv.org/abs/2609.36616v1
  • Youngjun Jun, Kyumin Choi, Youngmin Kim, Seonghyun Jin, Sunwoo Park, Jangho Park, Jong Chul Ye. DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies. arXiv preprint arXiv:2610.00317v1 : https://arxiv.org/abs/2610.00317v1
  • Ziyi Yin, Sangmin Woo, Kang Zhou, Sungyeon Kim, Aosong Feng, Haibo Ding, Jun Huan. StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks. arXiv preprint arXiv:2609.36352v1 : https://arxiv.org/abs/2609.36352v1
  • Wentao Zhou, Weijie Gan, Jiayun Wang. Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models. arXiv preprint arXiv:2609.36224v1 : https://arxiv.org/abs/2609.36224v1
  • Bang Xiao, Wenqi Jia, Ozgur Kara, Tiancheng Shen, Yibo Yang, Bolin Lai, Junho Kim, James Matthew Rehg. LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning. arXiv preprint arXiv:2609.36219v1 : https://arxiv.org/abs/2609.36219v1
  • Xin Chen, Anan Du, Feng Feng, Pei Fu, Jian Luan, Longwei Xu, Shaojie Zhang, Hang Li, Heng Qu, Cheng Tan. Xiaomi-OCR-0 Technical Report. arXiv preprint arXiv:2609.36136v1 : https://arxiv.org/abs/2609.36136v1
  • Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li, Zimo Wen, Wanqi Yin, Haiwen Diao, Ziwei Liu. Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning. arXiv preprint arXiv:2609.35767v1 : https://arxiv.org/abs/2609.35767v1
  • Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov, Luke Zettlemoyer. Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts. arXiv preprint arXiv:2609.35641v1 : https://arxiv.org/abs/2609.35641v1
  • Jiazhou Zhou, Hu Zhou, Yucheng Chen, Jinyuan Qu, Ying-Cong Chen, Lei Zhang. PIVOT: Pivot-Aware On Policy Self Distillation for Multi-Turn VLM Agents. arXiv preprint arXiv:2609.35303v1 : https://arxiv.org/abs/2609.35303v1
  • Xingming Long, Jie Zhang, Yuecong Min, Shiguang Shan, Xilin Chen. Beyond Saying Less: Fine-Grained Alignment for Informative and Faithful Vision-Language Models. arXiv preprint arXiv:2609.35294v1 : https://arxiv.org/abs/2609.35294v1
  • Zhe Sun, Ziyi Luo, Yehao Lu, Lei Zhou, Xi Li. RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving. arXiv preprint arXiv:2609.35078v1 : https://arxiv.org/abs/2609.35078v1
  • Yaowen Zhang, Xiangyu Qiu, Junyi Hu, Zhi Lu, Wenwen Tian, Aoqin Wang, Junhai Luo, Zhenming Peng. ReSight-SMC: Two-Stage Power Sampling via Island SMC with Visual Scouts. arXiv preprint arXiv:2609.34905v1 : https://arxiv.org/abs/2609.34905v1
  • Cilin Yan, Yilun Qiu, Wanyang Zhang, Rui Zu, Xiaolong Jiang, Jiayin Cai, Yao Hu. Revisit to Segment: Working Memory Distillation for Reasoning Segmentation. arXiv preprint arXiv:2609.34863v2 : https://arxiv.org/abs/2609.34863v2
  • Guanghao Zhu, Zeyu Liu, Zhitian Hou, Pengkai Wang, Zhijie Sang, Shuo Cai, Yang Yu, Yuanyi Wang, Yanggan Gu, Congkai Xie, Jianmin Wu, Hongxia Yang. InfiMed2: A Generalist Medical Multimodal Foundation Model from Contextual Evidence and Stability-Aware Supervision. arXiv preprint arXiv:2609.34798v1 : https://arxiv.org/abs/2609.34798v1
  • Zhiyuan Ma, Jiaming Li, Lingzhen Li, Yu Liu, Xuekai Zhu, Dingkang Liang, Kaiyan Zhang, Jianjun Li, Bowen Zhou, Xiang Bai. Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization. arXiv preprint arXiv:2609.34688v1 : https://arxiv.org/abs/2609.34688v1
  • Nanxing Hu, Xiaoyue Duan, Qiwei Yan, Kailin Lyu, Jinchao Zhang, Guoliang Kang. Summarize Before Grounding: Query-Guided Chunk Condensation for Long-Video Temporal Grounding. arXiv preprint arXiv:2609.34598v1 : https://arxiv.org/abs/2609.34598v1
  • Omri Kaduri, Kate Feingold, Phillip Isola, Tali Dekel. Reinforcement Learning from Intermediate Renders for Image-to-Code Generation. arXiv preprint arXiv:2609.34587v1 : https://arxiv.org/abs/2609.34587v1
  • Wenhan Yang, Nilay Naharas, Ali Payani, Baharan Mirzasoleiman. Distilling Visual Reasoning into Text Space. arXiv preprint arXiv:2609.34408v1 : https://arxiv.org/abs/2609.34408v1
  • Xiaolei Chen, Zhuolin He, Yuxuan Liang, Xu Li, Haotian Chen, Fan Shi, Mengyang Zhao, Wenjuan Meng, Zisheng Chen, Zhihao Zhu, Zhounan Jin, Hengli Wang, Qingfan Wang, Jiamei Liang, Bin Li, Xiangyang Xue. CAR-VLA: Complexity-Aware and Risk-Adaptive Reasoning for Autonomous Driving. arXiv preprint arXiv:2609.34387v2 : https://arxiv.org/abs/2609.34387v2
  • Zhang Ruiyang, Ou Jinpeng, Xie Yifan, Zhou Jingang, Pan Lirui, Guo Qingpei, Zheng Zhedong. Marathoner: Ultra-Long-Horizon Autonomous Intelligence. arXiv preprint arXiv:2609.34378v1 : https://arxiv.org/abs/2609.34378v1
  • Chengyang Zhang, Wenchuan Zhang, Bo Li, Mengran Li, Xinyu Liu, Jiaming Yang, Jie Chen, Zhang Zhang, Yuhao Yi, Hong Bu, Jiancheng Lv. See, Measure, and Reason: Learning Visually Grounded Reasoning in Pathology. arXiv preprint arXiv:2609.34277v1 : https://arxiv.org/abs/2609.34277v1
  • Ivan Kapelyukh, Xiaohan Zhang, Stephen James, Laura Herlant, Edward Johns. ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim. arXiv preprint arXiv:2609.34010v1 : https://arxiv.org/abs/2609.34010v1
  • Haruki Watase, Shunya Nagashima, Takayuki Nishimura. PoE-Fuse: Precision-Weighted Expert Fusion for Bi-Temporal Change Understanding. arXiv preprint arXiv:2609.37485v1 : https://arxiv.org/abs/2609.37485v1
  • Toyota Li, David Zhao, Alan Zhao. Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning. arXiv preprint arXiv:2609.33444v1 : https://arxiv.org/abs/2609.33444v1
  • Shuning Wang, Zhiheng Wu, Xun Zhou, Chongyang Cui, Chen Jia, Bowen Liu, Chuanjie Li, Xiang Chen, Yi Yang, Yumeng Zhang, Wenjie Huang. TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models. arXiv preprint arXiv:2609.33414v1 : https://arxiv.org/abs/2609.33414v1
  • Peixi Wu, Mingzhou Jiang, Feipeng Ma, Biao Yang, Yunhao Zhou, Wei Yuan, Bosong Chai, Huizu Lin, Jie Chen, Zhangchi Hu, Fan Yang, Wenwu Ou, Hebei Li, Xiaoyan Sun. VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings. arXiv preprint arXiv:2609.33402v1 : https://arxiv.org/abs/2609.33402v1
  • Jiali Chen, Zhengteng Lin, Zuqi Wang, Shirong Lin, Xi Yu, Xusen Hei, DingBa Fu, Jiayuan Xie, Yi Cai. SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation. arXiv preprint arXiv:2609.33399v2 : https://arxiv.org/abs/2609.33399v2
  • Zhizhen Zhang, Yuxia Fu, Zijian Wang, Helen Huang, Yadan Luo. Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface. arXiv preprint arXiv:2609.33125v1 : https://arxiv.org/abs/2609.33125v1
  • Long Qian, Bingke Zhu, Jiaqi Wei, Yu Li, Yingying Chen, Jinqiao Wang. CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models. arXiv preprint arXiv:2609.32781v1 : https://arxiv.org/abs/2609.32781v1
  • Qinwei Ma, Jingzhe Shi, Simin Fan, Ling Li, Mengdi Wang, Alex Lamb. Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL. arXiv preprint arXiv:2609.32665v1 : https://arxiv.org/abs/2609.32665v1
  • Junxian Li, Ruixuan Yang, Tianao Zhang, Tiange Xu, Weisheng Dong, Yulun Zhang. Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction. arXiv preprint arXiv:2609.32353v2 : https://arxiv.org/abs/2609.32353v2
  • Zhengyi Lu, Ming Lu, Chongyu Qu, Junchao Zhu, Junlin Guo, Marilyn Lionts, Yanfan Zhu, Yuechen Yang, Tianyuan Yao, Jayasai Rajagopal, Bennett Allan Landman, Xiao Wang, Xinqiang Yan, Yuankai Huo. OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI. arXiv preprint arXiv:2609.32343v1 : https://arxiv.org/abs/2609.32343v1
  • Yunkai Yang, Yudong Zhang, Xinying Chen, Bin Luo, Jienan Lyu, Kunquan Zhang, Weitao Wan, Runmin Dong. SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO. arXiv preprint arXiv:2609.32340v1 : https://arxiv.org/abs/2609.32340v1
  • Zhenhao Zhang, Zhaoyu Fan, Haohan Ying, Jingwen Hu, Hancen Fan, Junhao Zhou, Zitian Chen, Linchao Zhu. CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs. arXiv preprint arXiv:2609.31957v1 : https://arxiv.org/abs/2609.31957v1
  • Denis Musinguzi, Andrew Katumba, Prasenjit Mitra. Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning. arXiv preprint arXiv:2609.31911v1 : https://arxiv.org/abs/2609.31911v1
  • Hyungjin Chung, Byeongjun Park, Joonseok Lee, Hojun Kim, Jaeho Choi, Byung-Hoon Kim. MVVBench: Benchmarking 4D Reasoning in Vision-Language Models. arXiv preprint arXiv:2609.30952v1 : https://arxiv.org/abs/2609.30952v1
  • Peipei Li, Shuhan Xia, Shengyang Liu, Zekun Li, Ran He. MM-VeriAgent: Learning to Use Extensive Tools to Verify Multimodal Misinformation with Reinforcement Learning. arXiv preprint arXiv:2609.30698v1 : https://arxiv.org/abs/2609.30698v1
  • Yubo Zhu, Yawen Shao, Ziyun Dai, Zixun Fang, Kai Zhu, Siyang Sun, Haolan Xue, Chuxin Wang, Tingyu Weng, Jingming Luo, Chen Shi, Lianghua Huang, Yufeng Ai, Yuzheng Wang, Wenyuan Zhang, Yu Shang, Yuxiang Bao, Zoubin Bi, Jie Xiao, Jinbo Xing, Jiaxing Zhao, Chongyang Zhong, Hengjian Chen, Chenwei Xie, Akide Liu, Zhehan Kan, Yu Liu, Wei Zhai, Sheng Zhong, Wei Tong. WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation. arXiv preprint arXiv:2609.30221v1 : https://arxiv.org/abs/2609.30221v1
  • Zhiyu Xu, Weilong Yan, Yufei Shi, Shiyang Li, Yihao Liu, Kin-Man Lam, Yuewen Cao. AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation. arXiv preprint arXiv:2609.29816v1 : https://arxiv.org/abs/2609.29816v1
  • Mehmet Turan Yardımcı, Yunus Emre Çoğurcu. Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy. arXiv preprint arXiv:2609.28838v1 : https://arxiv.org/abs/2609.28838v1
  • Rishabh Choudhary, Shreyansh Raj, Umesh Goyal, Shubh Kashyap, Shrestha Kumar, Sushovan Jena, Komal Kumar, Hisham Cholakkal, Aditya Nigam. Small yet Assistive: Spatially-Aware Post-Training for Low Vision. arXiv preprint arXiv:2609.28757v1 : https://arxiv.org/abs/2609.28757v1
  • Tara Sadjadpour, Siming He, C. K. Wolfe, Haozhi Qi, Lea Wilken, S. Shankar Sastry, Claire Tomlin, Jitendra Malik. Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy. arXiv preprint arXiv:2609.28660v1 : https://arxiv.org/abs/2609.28660v1
  • Heyun Chen, Xiaohan Lan, Jiaxi Li, Zhilin Lu, Qi She, Weiwen Xu, Fei Yu, Yujie Zhong, Jinghuan Chen, Zijian Feng, Siyu Jiao, Yiheng Lin, Xinhao Wang, Sihan Yang, Jieyu You, Changbin Zhang, Hengyu Zhang, Xudong Zhang, Yunqing Zhao, Shuai Zheng. Pistis Technical Report. arXiv preprint arXiv:2609.28554v1 : https://arxiv.org/abs/2609.28554v1
  • Jiahang Cao, Hanye Zhao, Hang Lai, Shenyu Zhang, Xiaoshen Han, Xinghang Li, Futeng Liu, Wanli Peng, Heyun Wang, Yunhong Wang, Jason Li, Yong Yu, Weinan Zhang. Dissecting Advantage-Guided Post-Training for Vision-Language-Action Policies. arXiv preprint arXiv:2609.28161v1 : https://arxiv.org/abs/2609.28161v1
  • Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam Aboian, Sena Azamat, Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze, Marc Edgar, Yufan He, Pengfei Guo, Daguang Xu. NV-Reason-CT: 3D Visual Language Model for CT Analysis. arXiv preprint arXiv:2609.27511v1 : https://arxiv.org/abs/2609.27511v1
  • Xueji Fang, Boqiang Duan, Hua Wu, Jingdong Wang, Guo-Jun Qi. Latent evolving World Action Model. arXiv preprint arXiv:2609.27455v2 : https://arxiv.org/abs/2609.27455v2
  • Weihui Zhao, Xiaohan Yan, Zunian Wan, Xuan Du, Zhaozhan Chi, Jianbo Mao, Ruipu Wu, Rushuai Yang, Houlin Li, Shukai Yang, Jing Wu, Yuxiang Yan, Yongcheng Liu, Chuankang Li, Guanghui Ren, Wei Shan, Maoqing Yao. BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models. arXiv preprint arXiv:2609.27450v1 : https://arxiv.org/abs/2609.27450v1
  • Abbas Mammadov, Jerry Y. Huang, Justin Lin, Partha Kaushik, Sheel Shah, Kartik Nair, Yee Whye Teh, Nicholas M. Boffi. WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps. arXiv preprint arXiv:2609.27033v1 : https://arxiv.org/abs/2609.27033v1
  • Dohyun Kim, Sungjun Han, Hyungguk Kim, Yusik Kim, Jamin Shin, Paul Hongsuck Seo, Hongjoon Ahn. Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding. arXiv preprint arXiv:2609.26638v1 : https://arxiv.org/abs/2609.26638v1
  • Shuangzhi Li, Qiaoqiao Jia, Xingxin Chen, Guile Wu, Dongfeng Bai. GeoComposer: Geometry-Grounded Photographic Composition Instruction. arXiv preprint arXiv:2609.26620v1 : https://arxiv.org/abs/2609.26620v1
  • Chongyu Zhu, Jaden Hinds, Hyegang Kim, Juan Sebastian Rojas, Ramy Elmallah, Chi-Guhn Lee. RouteRLT: Learning When and Which RL Specialist Should Control a Vision-Language-Action Policy. arXiv preprint arXiv:2609.26467v1 : https://arxiv.org/abs/2609.26467v1
  • Junlong Wu, Zijun Li, Yuting Hu, Jia Sun, Pengcheng Wei, Yimin Zhou, Honglie Wang, Huaiqing Wang, Dewen Fan, Fei Zuo, Haixuan Gao, Lihui Peng, Tingxuan She, Yuqing Li, Boheng Zhang, Fan Yang, Wenwu Ou. KwaiMind Technical Report. arXiv preprint arXiv:2609.26375v1 : https://arxiv.org/abs/2609.26375v1
  • Zihan Chen, Hengguang Zhou, Yuan Kang, Yiming Zhang, Wenhui Fang, Zenghui Ding, Yining Sun, Cho-Jui Hsieh. BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception. arXiv preprint arXiv:2609.25891v1 : https://arxiv.org/abs/2609.25891v1
  • Yuling Xi, Haokai Zhang, Muzhi Zhu, Hao Zhong, Zongze Du, Hengyu Zhao, Chenchen Jing, Yufei Yin, Bin Qin, Yongjie Yang, Zhenbo Luo, Hao Chen, Chunhua Shen. Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes. arXiv preprint arXiv:2609.25841v1 : https://arxiv.org/abs/2609.25841v1
  • Yuqi Ye, Shangkun Sun, Junhong Lin, Jiayi Zhao, Changhao Peng, Wei Zheng, Guoqing Liu, Tiesong Zhao, Wei Gao. Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving. arXiv preprint arXiv:2609.25831v1 : https://arxiv.org/abs/2609.25831v1
  • Trung Nguyen Quang, Yuhao Dong, Shuo Sun, Shuai Liu, Shulin Tian, Kim-Hui Yap, Ziwei Liu. Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models. arXiv preprint arXiv:2609.25773v1 : https://arxiv.org/abs/2609.25773v1
  • Hangyu Ran, Yuhao Zheng, Yingying Zhang, Kevin Qinghong Lin, Han Peng. RULER: Instance-aware Rubric Rewards for SVG Generation. arXiv preprint arXiv:2609.25270v1 : https://arxiv.org/abs/2609.25270v1
  • Binxu Li, Haoyi Duan, Yuhui Zhang, Yaohui Zhang, Zihao Lin, Kaituo Feng, Suozhi Huang, Xiangyi Li, Yu Li, Chunyuan Li, Shilong Liu, Mengdi Wang. VideoGen-Agent: Reinforcing Video Generation Agents. arXiv preprint arXiv:2609.24997v1 : https://arxiv.org/abs/2609.24997v1
  • Abhinav Jain, Cindy Grimm, Stefan Lee. Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning. arXiv preprint arXiv:2609.24906v1 : https://arxiv.org/abs/2609.24906v1
  • Foundation Model, Li Auto Inc. ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination. arXiv preprint arXiv:2609.24526v2 : https://arxiv.org/abs/2609.24526v2
  • Florian Krone, Elena Hoemann, Sven Hallerbach. Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision. arXiv preprint arXiv:2609.24249v1 : https://arxiv.org/abs/2609.24249v1
  • Lijian Wu, Henry Hengyuan Zhao, Zijian Zhang, Jiahao Tang, Jiajun Wu, Alex Jinpeng Wang. ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation. arXiv preprint arXiv:2609.24210v1 : https://arxiv.org/abs/2609.24210v1
  • Sanchit Sinha, Oana Frunza, Kashif Rasul, Aidong Zhang. Monitorable Chart Reasoning Agents via Verifiable Process Rewards. arXiv preprint arXiv:2609.24071v1 : https://arxiv.org/abs/2609.24071v1
  • Kanzhong Yao, Jinyi Leng, Hao Zhang, Zhe Sun, Xuelong Li. AquaOrbit: Sim-to-Real Reinforcement Learning for Underwater Target Orbiting under Intermittent Visual Feedback. arXiv preprint arXiv:2609.24054v1 : https://arxiv.org/abs/2609.24054v1
  • Kejia Hu, Wentong Zhai, Bo Zhao, Shuai Liang. Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning. arXiv preprint arXiv:2609.24033v1 : https://arxiv.org/abs/2609.24033v1
  • Howard Wang, Han Zheng, Cathy Wu. Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents. arXiv preprint arXiv:2609.23269v1 : https://arxiv.org/abs/2609.23269v1
  • Ziming Xu, Shuang Liang, Ruobing Han, Ziqiao Xi, Mingxing Rao, Kun Zhou, Zijun Zhang, Yuchen Yan, Yufan Wei, Junbo Huang, Yifei Shao, Fang Nan, Biwei Huang. CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model. arXiv preprint arXiv:2609.23184v2 : https://arxiv.org/abs/2609.23184v2
  • Chenhui Pan, Tong Xu, Xuesu Xiao. Verti-WM: A Physics-Aided Exteroceptive World Model for Off-Road Reinforcement Learning. arXiv preprint arXiv:2609.23118v1 : https://arxiv.org/abs/2609.23118v1
  • Lei Zhang, Chun Ye, Le Yang, Zhaozhong Wang, Deng-Ping Fan, Hang Dai, Binglu Wang. General Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems. arXiv preprint arXiv:2609.22967v1 : https://arxiv.org/abs/2609.22967v1
  • Zhenchen Tang, Yang Li, Songlin Yang, Bo Peng, Xiaotong Zhao, Shuai Li, Haotian Fan, Alan Zhao, Jing Dong. RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling. arXiv preprint arXiv:2609.22947v2 : https://arxiv.org/abs/2609.22947v2
  • Yichen Wang, Chaoyang Zhang, Xuqi Su, Jun Ma, Haiyue Zhu, Xiaocong Li. ForceRFT: Refining VLA Actions through Force-Guided Residual Reinforcement Learning. arXiv preprint arXiv:2609.22840v1 : https://arxiv.org/abs/2609.22840v1
  • Damiano Da Col, Maximilian Igl, Peter Karkus, Kashyap Chitta, Boris Ivanovic, Marco Pavone, Konrad Schindler, Christos Sakaridis. OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher. arXiv preprint arXiv:2609.20756v1 : https://arxiv.org/abs/2609.20756v1
  • Thomas Steinecker, Denis Trescher, Alexander Bienemann, Thorsten Luettel, Mirko Maehlisch. MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving. arXiv preprint arXiv:2609.20747v1 : https://arxiv.org/abs/2609.20747v1
  • Aashish Sahu, R Prasanth Kumar. RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier. arXiv preprint arXiv:2609.20629v1 : https://arxiv.org/abs/2609.20629v1
  • Yilang Liu, Haoxiang You, Qian Wang, Daniel Rakita, Ian Abraham. Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control. arXiv preprint arXiv:2609.20575v1 : https://arxiv.org/abs/2609.20575v1
  • Yuang Tu, Runjia Tan, Yujie Yan, Jinghan Hu, Chen Lv. AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention. arXiv preprint arXiv:2609.20106v1 : https://arxiv.org/abs/2609.20106v1
  • Yin Wu, Jiarong Wei, Carl Esselborn, Shubham Phoolari, Ahmed Abouelazm, Daniel Slieter, J. Marius Zöllner. Safety-Critical Scenanrio Emerges from Initial Scene. arXiv preprint arXiv:2609.20103v1 : https://arxiv.org/abs/2609.20103v1
  • Yuheng Shi, Xiaohuan Pei, Minjing Dong, Chang Xu. Region-Level Policy Optimization for Fine-grained MLLM Perception. arXiv preprint arXiv:2609.19745v1 : https://arxiv.org/abs/2609.19745v1
  • Shunyu Yao, Xiaohan Zhang, Zhuoran Yang, Haoqi Lai, Qi Ming, Xiaoxi Hu, Hui-Liang Shen, Si-Yuan Cao. Towards Active Cross-View Object Geo-Localization. arXiv preprint arXiv:2609.19662v1 : https://arxiv.org/abs/2609.19662v1
  • Sitong Chen, Fatemeh Zargarbashi, Jin Cheng, Tianxu An, Stelian Coros. KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation. arXiv preprint arXiv:2609.18869v1 : https://arxiv.org/abs/2609.18869v1
  • Remo Steiner, Vikram Ramasamy, David Tingdahl, Sam Mady, Karl Van Wyk, Nathan Ratliff, David Recasens Lafuente, Soha Pouya, Tuur Stuyck, Alex Millane. WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning. arXiv preprint arXiv:2609.18685v1 : https://arxiv.org/abs/2609.18685v1
  • Qilin Wang, Mingyu Li, Hao Tang. VibeAvatar: Aligning Phonetic Kinematics and Human Aesthetics for High-Fidelity Talking Avatar Synthesis. arXiv preprint arXiv:2609.18632v1 : https://arxiv.org/abs/2609.18632v1
  • Kailing Li, Yu Han, Tianwen Qian, Yuqian Fu, Jingyu Gong, Jiangming Shi, Xiaoling Wang. GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation. arXiv preprint arXiv:2609.18581v1 : https://arxiv.org/abs/2609.18581v1
  • Dohwan Ko, Ji Soo Lee, Pierce Chuang, Debojeet Chatterjee, Ashish Shenoy, Yichao Lu, Seungwhan Moon, Xin Luna Dong, Vikas Bhardwaj, Hyunwoo J. Kim. SVMemAgent: A Streaming Video Memory Agent for Query-Agnostic Online Frame Selection. arXiv preprint arXiv:2609.18540v1 : https://arxiv.org/abs/2609.18540v1
  • Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn. Reinforcement Learning for Real-Time Vision-Language-Action Policies. arXiv preprint arXiv:2609.18207v1 : https://arxiv.org/abs/2609.18207v1
  • Zhixin Cheng, Jiacheng Deng, Xiaotian Yin, Baoqun Yin, Richang Hong, Tianzhu Zhang. Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration. arXiv preprint arXiv:2609.18088v1 : https://arxiv.org/abs/2609.18088v1
  • Xinxin Song, Siyuan Li, Tingxiong Xiao, Jinli Suo. Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning. arXiv preprint arXiv:2609.18057v1 : https://arxiv.org/abs/2609.18057v1
  • Ahmed Rafid, Fariya Ahmed, Rumman Adib, Mehedi Ahamed, Ajwad Abrar, Tareque Mohmud Chowdhury. AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection. arXiv preprint arXiv:2609.17800v1 : https://arxiv.org/abs/2609.17800v1
  • Nanjie Yao, Hao Wang, Chong Cheng, Zhikang Chen, Wenzhe Li, Jiafei Lyu, Li Shen, Peilin Zhao, Zongqing Lu, Gao Huang, Steven Hoi, Dacheng Tao, Deheng Ye. World Models for Embodied Intelligence: From Plausible to Controllable to Actionable. arXiv preprint arXiv:2609.16697v1 : https://arxiv.org/abs/2609.16697v1
  • Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang, Guansu Wang, Wei Zhang. SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation. arXiv preprint arXiv:2609.16601v1 : https://arxiv.org/abs/2609.16601v1
  • Hyesung Lee, Si-Hwan Heo, Sungwook Yang. UniDex-ViTac: Learning Unified Visuo-Tactile Dexterous Manipulation Policy from Human Video Data. arXiv preprint arXiv:2609.16504v1 : https://arxiv.org/abs/2609.16504v1
  • Yucheng Shen, Lingyong Yan, Jiulong Wu, Shuaiqiang Wang, Jianmin WU, Dawei Yin, Min Cao. Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation. arXiv preprint arXiv:2609.15800v1 : https://arxiv.org/abs/2609.15800v1
  • Weixin Xu, Zhenyu Yang, Bing Wang, Shengsheng Qian, Changsheng Xu. VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding. arXiv preprint arXiv:2609.15606v1 : https://arxiv.org/abs/2609.15606v1
  • Yizhou Liu, Fei Tang, Yuchen Yan, Zhengxi Lu, Songqin Nong, Tao Jiang, Wenhao Xu, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen. Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding. arXiv preprint arXiv:2609.15307v1 : https://arxiv.org/abs/2609.15307v1
  • Kaiyan Chen, Junbin Xiao, Xun Yang. Long-to-Short Video Evidence Reasoning for Grounded Question Answering. arXiv preprint arXiv:2609.15224v1 : https://arxiv.org/abs/2609.15224v1
  • Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang. AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference. arXiv preprint arXiv:2609.15131v1 : https://arxiv.org/abs/2609.15131v1
  • Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng, Ivan Laptev, Danfei Xu, Benjamin Riviere, Giuseppe Loianno, Eric Xing, Xingxing Zuo. World-Action Models for Robot Learning and Control: A Survey. arXiv preprint arXiv:2609.16074v1 : https://arxiv.org/abs/2609.16074v1
  • Jiaming Tan, Mingliang Zhai, Zhen Li, Yuwei Wu, Chuanhao Li, Kaipeng Zhang. AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video. arXiv preprint arXiv:2609.14462v1 : https://arxiv.org/abs/2609.14462v1
  • Yirong Zeng, Zhang Sai, Yuxian Wang, Yutai Hou, Yufei Liu, Xiao Ding, Bibo Cai. Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation. arXiv preprint arXiv:2609.16059v1 : https://arxiv.org/abs/2609.16059v1
  • Zhongyu Wang. GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning. arXiv preprint arXiv:2609.14066v1 : https://arxiv.org/abs/2609.14066v1
  • Yuzhe Li, Hao Yan, Hao Wang, Xingchen Liu, Ya-Qi Yu, Jihao Wu, Minghui Liao, Wei Chen, Yuliang Liu. UniCAR-RL: Seeing Better before Thinking Deeper in Visual Mathematics. arXiv preprint arXiv:2609.13849v1 : https://arxiv.org/abs/2609.13849v1
  • Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo, Weichen Fan, Wenhao Jia, Wenjie Gao, Xiangli Kong, Yan Li, Yang Yong, Zimo Wen, Zixuan Qian, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin. SenseNova-U1.5: Towards Native Unified Visual Intelligence. arXiv preprint arXiv:2609.11929v1 : https://arxiv.org/abs/2609.11929v1
  • Niange Yu, Ye Tian, Biaolong Chen, Miao Lu, Aixi Zhang, Hao Jiang, Yunhai Tong, Pipei Huang. Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation. arXiv preprint arXiv:2609.11507v1 : https://arxiv.org/abs/2609.11507v1
  • Meng Luo, Yicheng Liu, Jiahao Wang, Yuanxing Zhang, Xin Tao, Pengfei Wan, Kun Gai, Hao Fei. From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models. arXiv preprint arXiv:2609.11242v1 : https://arxiv.org/abs/2609.11242v1
  • Yang Wu, Stefano Petrangeli, Ishita Dasgupta, Yu Shen. CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation. arXiv preprint arXiv:2609.10943v1 : https://arxiv.org/abs/2609.10943v1
  • Nisarga Nilavadi, Ralf Römer, Moritz Reuss, Michael Krawez, Tobias Jülg, Angela P. Schoellig, Rudolf Lioutikov, Wolfram Burgard. DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation. arXiv preprint arXiv:2609.10506v1 : https://arxiv.org/abs/2609.10506v1
  • Sheng Li, Peng Liu, Qianqian Zhang, Tiancheng Zhao. VLX-VR: An Agentic-Aware Video Reasoning Model. arXiv preprint arXiv:2609.09985v1 : https://arxiv.org/abs/2609.09985v1
  • Zengjue Chen, Peidong Liu, Jiawei Li, Qi Wang. HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy. arXiv preprint arXiv:2609.09941v1 : https://arxiv.org/abs/2609.09941v1
  • Yansen Han, Shengyi Liao, Peng Sun, Deyuan Liu, Yuanxing Zhang, Pengfei Wan, Tao Lin. FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models. arXiv preprint arXiv:2609.09905v1 : https://arxiv.org/abs/2609.09905v1
  • Zhenxin Qin, Peng Shi, Cong Han, Yinlong Qian, Zequn Jie, Lin Ma. Video-MOPD: Multi-Teacher On-Policy Distillation for Video Understanding. arXiv preprint arXiv:2609.09300v1 : https://arxiv.org/abs/2609.09300v1
  • Yang Wan, Xihang Yue, Zhirui Liu, Ziyuan Chu, Shuxun Wang, Yuhan Chen, Xiaonan Jiang, Xukun Zhu, Yubo Dong, Linchao Zhu. No Free Checker: A Survey of Verifiers for Robot Policies. arXiv preprint arXiv:2609.09250v1 : https://arxiv.org/abs/2609.09250v1
  • Saurbh Singh Jamwal, Nived Chebrolu. Learning to Fly: Stable Vision-Guided UAV Servoing with Compact Target-Centric Cues and Reinforcement Learning. arXiv preprint arXiv:2609.09234v1 : https://arxiv.org/abs/2609.09234v1
  • Yuncong Yang, Zhengtao Han, Furkan Ozyurt, Zeyuan Yang, Han Yang, Junyi Cao, Haoyu Zhen, Yilun Du, Chuang Gan. SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators. arXiv preprint arXiv:2609.09155v1 : https://arxiv.org/abs/2609.09155v1
  • Linnan Zhao, Xu Liu, Lingling Li, Licheng Jiao, Fang Liu, Wenping Ma. SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation. arXiv preprint arXiv:2609.08867v1 : https://arxiv.org/abs/2609.08867v1
  • Aoting Zhang, Mingze Gao, Dongbao Yang, Longyi Chen, Daoxin Zhang, Yi Wu, Yao Hu, Yu Zhou. From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment. arXiv preprint arXiv:2609.08316v1 : https://arxiv.org/abs/2609.08316v1
  • Bozhou Li, Jiahang Zhang, Yue Ding, Yushuo Guan, Bohan Zeng, Yiyan Ji, Xinlong Chen, Yang Shi, Yifan Dai, Yuran Wang, Chengzhuo Tong, Pengfei Wan, Yuanxing Zhang, Wentao Zhang. Human-Centric Image Captioning with Subject-Centered Spatial Understanding. arXiv preprint arXiv:2609.08300v1 : https://arxiv.org/abs/2609.08300v1
  • Vishwas Sathish, Viresh Ranjan, Xinliang Zhu, Arnab Dhua, Douglas Gray. Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning. arXiv preprint arXiv:2609.08025v1 : https://arxiv.org/abs/2609.08025v1
  • Wanli Liuchen, Fangyuan Wang, Bin Li, Anqing Duan, Yunhui Liu, Peng Zhou, David Navarro-Alarcon. Phase-and-First-Arrival VLM Feedback for Sparse-Reward Reinforcement Learning in Surgical Manipulation. arXiv preprint arXiv:2609.07211v1 : https://arxiv.org/abs/2609.07211v1
  • Zhiwei Ning, Zhen Zhou, Puhua Jiang, Xintong Han, Gengming Zhang, Jie Yang, Zhonglong Zheng, Yuanjie Zheng, Wei Liu, Chunchao Guo. Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer. arXiv preprint arXiv:2609.07137v1 : https://arxiv.org/abs/2609.07137v1
  • Jiangning Zhu, Bowen Li, Shenyu Qiao, Yima Gu, Zhao Zhang, Yuhui Yuan, Shixia Liu. Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection. arXiv preprint arXiv:2609.07072v1 : https://arxiv.org/abs/2609.07072v1
  • Jia-Jen Lee, Shih-Yen Hou, Kee Koon Ng, Wei-Chun Wang, Shih-Sheng Chang. CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation. arXiv preprint arXiv:2609.06931v1 : https://arxiv.org/abs/2609.06931v1
  • Yinming Huang, Shuyuan Tu, Xi Yan, Jiahao Zhan, Zihan Yang, Zhen Xing, Hui Zhang, Tiehua Zhang, Yu-Gang Jiang, Zuxuan Wu. Agentic Visual Generation: From Generative Models to Agentic Control. arXiv preprint arXiv:2609.06758v1 : https://arxiv.org/abs/2609.06758v1
  • Xiao Zhang, Wang Zeng, Sheng Jin, Wentao Liu, Chen Qian, Shichao Kan. Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding. arXiv preprint arXiv:2609.06475v1 : https://arxiv.org/abs/2609.06475v1
  • Yangyang Xie, Ke Hao, Jiaqi Liu, Yun Gu, Xinglin Zhang. Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models. arXiv preprint arXiv:2609.06419v1 : https://arxiv.org/abs/2609.06419v1
  • Junyi Hu, Shuaihang Yuan, Yi Fang. CST-WM: A Causally Structured World Model for Embodied Visual Tracking. arXiv preprint arXiv:2609.06302v1 : https://arxiv.org/abs/2609.06302v1
  • Ting Huang, Yue Huang, Zeyu Zhang, Shuicheng Yan, Hao Tang. MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control. arXiv preprint arXiv:2609.06251v1 : https://arxiv.org/abs/2609.06251v1
  • Hao He, Chengcheng Hu, Zirun Su, Heng Zhang, Haisong Liu, Jinke Li, Haochen Tian, Zhenwei Shen, Hongyang Li, Zhichao Li, Yunchen Yang, Bochao Huang, Siyu Zhang, Kuangye Chen, Xiongjie Zhang, Wentao Dai, Hengchen Dai, Siyuan Liu, Zehao Huang, Naiyan Wang. DriveZero: End-to-End Driving Beyond Human Demonstrations. arXiv preprint arXiv:2609.06055v1 : https://arxiv.org/abs/2609.06055v1
  • Xin Xie, Fan Zhang, Dong Gong. Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models. arXiv preprint arXiv:2609.05968v1 : https://arxiv.org/abs/2609.05968v1
  • Jiaoyang Chen, Bin Hu, Jingyu Hu, Kun Zhou, Qin Zhang, Zhengzhe Liu. FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection. arXiv preprint arXiv:2609.05876v1 : https://arxiv.org/abs/2609.05876v1
  • Yibin Wang, Zehan Wang, Junshu Tang, Zhimin Li, Yujie Zhou, Jiazi Bu, Pengyang Ling, Feng Han, Zhixiong Zhang, Long Xing, Shengyuan Ding, Ziang Li, Cheng Jin, Yuhang Zang, Jiaqi Wang, Tianyu Pang. WorldReward: Reward Modeling for Camera-Conditioned World Models. arXiv preprint arXiv:2609.03952v1 : https://arxiv.org/abs/2609.03952v1
  • Marco Cipriano, Leonardo Zini, Alexandra Schild, Valentin Teutschbein, Afsana Mimi, Marcella Cornia, Lorenzo Baraldi, Gerard de Melo. SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation. arXiv preprint arXiv:2609.03806v1 : https://arxiv.org/abs/2609.03806v1
  • Yijun Yang, Shenghe Zheng, Wenbo Li, Jianhui Liu, Haoze Sun, Yanbing Zhang, Jiaxiu Jiang, Lin Song, Haoyang Huang, Nan Duan, Lei Zhu. Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning. arXiv preprint arXiv:2609.03729v1 : https://arxiv.org/abs/2609.03729v1
  • Juntao Xu, Shihong Li, Hoi Fan Au, Ning Zhu. ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion Models. arXiv preprint arXiv:2609.03688v1 : https://arxiv.org/abs/2609.03688v1
  • Alejandro Barón García, Feng Wang, Emilia Garcia Casademont, Han Xiao. Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards. arXiv preprint arXiv:2609.03181v1 : https://arxiv.org/abs/2609.03181v1
  • Adrienne Deganutti, Purvanshi Mehta, Simon Hadfield, Andrew Gilbert. GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design. arXiv preprint arXiv:2609.02813v1 : https://arxiv.org/abs/2609.02813v1
  • Song Jin, Zhongtao Jiang, Chenglei Shen, Huanxuan Liao, Haozhe Chi, Zhiwei Wang, Kun Xu, Yong Liu. Allocate Before You Embed: Adaptive Visual Input Allocation for Video Embeddings. arXiv preprint arXiv:2609.01778v1 : https://arxiv.org/abs/2609.01778v1
  • Giovanni Bonetta, Matteo Merler, Davide Zago, Rossella Cancelliere, Bernardo Magnini. Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers. arXiv preprint arXiv:2609.01567v2 : https://arxiv.org/abs/2609.01567v2
  • Christian Greisinger, Zhixue Zhao, Steffen Eger. EdiTikZ: Scientific Figure Editing from Revision Trajectories. arXiv preprint arXiv:2609.01409v1 : https://arxiv.org/abs/2609.01409v1
  • Jiayu Ding, Zhuodong Liu, Lei Zhang, Manyu Xiong, Hongbo Jin, Haoran Tang, Hongbo Zhang, Changen Zhu, Wenbo Xing. Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models. arXiv preprint arXiv:2609.01059v1 : https://arxiv.org/abs/2609.01059v1
  • Ahmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur Arief. A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies. arXiv preprint arXiv:2609.00718v1 : https://arxiv.org/abs/2609.00718v1
  • Jongyeop Hyun, Taeyoung Kim, Hyounghun Kim. Controllable Image Captioning with Prompt-Conditioned Scene Rewards. arXiv preprint arXiv:2609.00709v1 : https://arxiv.org/abs/2609.00709v1
  • Suryaansh Jain, Rahasya Barkur, Vishal G, Ryan Rossi, Franck Dernoncourt, Jack Wang, Koustava Goswami, Nedim Lipka, Puneet Mathur, Samyadeep Basu, Seunghyun Yoon. A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss. arXiv preprint arXiv:2609.00591v1 : https://arxiv.org/abs/2609.00591v1
  • Ce Zhang, Jing Bi, Jinxi He, Jianshu Zhang, Jingyang Lin, Yunzhong Xiao, Minghao Fu, Yaqi Xie, Zhentao Xie, Weicong Chen, Katia Sycara, Ming Zhou. StreamScout: Learning When to Look Deeper for Streaming Video Understanding. arXiv preprint arXiv:2609.00291v1 : https://arxiv.org/abs/2609.00291v1
  • Jiashu Zhu, Yanhao Zheng, Ruitian Tian, Rujing Dang, Shen Zhang, Bingze Song, Jiachen Lei, Ruimin Lin, Jiahong Wu, Xiangxiang Chu. DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution. arXiv preprint arXiv:2608.31106v1 : https://arxiv.org/abs/2608.31106v1
  • Xingjian Wang, Shijian Wang, Yibo Wang, Zihao Yu, Runhao Fu, Xuelian Cheng, Zongyuan Ge. Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum. arXiv preprint arXiv:2608.30584v1 : https://arxiv.org/abs/2608.30584v1
  • Jiani Guo, Junjie Wang, Jie Wu, Pengxiang Zhao, Dongdong Zhang, Shaohan Huang, Yujiu Yang, Furu Wei. Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry. arXiv preprint arXiv:2608.30457v1 : https://arxiv.org/abs/2608.30457v1
  • Aryan Vijay Bhosale, Vaibhavi Lokegaonkar, Vishnu Raj, Gouthaman KV, Sreyan Ghosh, Ramani Duraiswami, Lie Lu, Dinesh Manocha. VIBE: Video Instruction-aligned Background music gEneration. arXiv preprint arXiv:2608.30125v1 : https://arxiv.org/abs/2608.30125v1
  • Tian Zhang, Zhuo Huang, Hongrui Ye, Yu Wu, Zengmao Wang, Kaixuan Zhou. Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving. arXiv preprint arXiv:2608.30122v1 : https://arxiv.org/abs/2608.30122v1
  • Kaidong Zhang, Yukang Ding, Xiaoyu Liu, Ying Chen. Beyond Global Realism: Virtual Try-On Evaluation and Optimization with Dimension-wise Garment Fidelity Assessment. arXiv preprint arXiv:2608.29804v1 : https://arxiv.org/abs/2608.29804v1
  • Weifei Chen, Honghao Zhang, Zhiyuan You, Xinyi Le. InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection. arXiv preprint arXiv:2608.29783v1 : https://arxiv.org/abs/2608.29783v1
  • Hao Feng, Zhi Zuo, MingJian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang, Zhengzhe Liu. FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation. arXiv preprint arXiv:2608.29519v1 : https://arxiv.org/abs/2608.29519v1
  • Yu Cheng, Arushi Goel, Hakan Bilen. Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs. arXiv preprint arXiv:2608.29374v1 : https://arxiv.org/abs/2608.29374v1
  • Yuhan Li, Xianfeng Tan, Fangao Zeng, Wenxiang Shang, Pipei Huang, Hao Zhou, Zhiyu Jin, Wenjun Zhang, Bingbing Ni. RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation. arXiv preprint arXiv:2608.29280v1 : https://arxiv.org/abs/2608.29280v1
  • Ziyue Wang, Shiqi Huang, Weiwen Xu, Bihan Wen, Xudong Jiang. Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models. arXiv preprint arXiv:2608.27065v1 : https://arxiv.org/abs/2608.27065v1
  • Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu. RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing. arXiv preprint arXiv:2608.26956v1 : https://arxiv.org/abs/2608.26956v1
  • Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim. Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs. arXiv preprint arXiv:2608.26684v1 : https://arxiv.org/abs/2608.26684v1
  • Yogesh Kulkarni, Pooyan Fazli. Video-FLAIR: Not Whether to Reason, But How. arXiv preprint arXiv:2608.26495v1 : https://arxiv.org/abs/2608.26495v1
  • Junxiang Xu, Ruisi Wang, Fanyi Pu, Maijunxian Wang, Ran Ji, Tongxi Zhou, Chenyang Gu, Jing Zuo, Hongcan Xiao, Yimeng Geng, Wanqi Yin, Wei Chen, Oscar Qian, Zhengan Yan, Ziqi Huang, Haiwen Diao, Liang Pan, Bo Li, Xiangyu Fan, Dezhi Luo, Fengyuan Yu, Zehong Zhao, Qingying Gao, Tinghui Zhu, Yilan Zhang, Jingqi Tong, Pinyuan Feng, Zhengze Jiang, Letian Wang, Ziyu Guo, Renrui Zhang, Jieneng Chen, Sonia Joseph, Constantin Venhoff, Saman Motamed, Mengyue Yang, Chandra Sripada, Alan Yuille, Philip Torr, Lvmin Zhang, Vikash Kumar, Daniel Khashabi, Nikolaus Kriegeskorte, Raphaël Millière, Vincent C. Müller, Anyi Rao, Quan Wang, Ziwei Liu, Dahua Lin, Lei Yang, Hokin Deng, Zhongang Cai. VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning. arXiv preprint arXiv:2608.26105v1 : https://arxiv.org/abs/2608.26105v1
  • Shulin Tian, Minglun Li, Yuhao Dong, Hao Ding, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu. V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning. arXiv preprint arXiv:2608.25580v1 : https://arxiv.org/abs/2608.25580v1
  • Xintong Zhang, Xiaomeng Fan, Shilin Yan, Ekko He, Zicheng Liu, Zijian Zou, Guannan Zhang, Yuwei Wu, Zhi Gao, Hongwei Xue. AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research. arXiv preprint arXiv:2608.25559v1 : https://arxiv.org/abs/2608.25559v1
  • Longteng Jiang, DanDan Zheng, Qianqian Qiao, Heng Huang, Huaye Wang, Yihang Bo, Bao Peng, Jingdong Chen, Jun Zhou, Xin Jin. VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation Quality. arXiv preprint arXiv:2608.25452v1 : https://arxiv.org/abs/2608.25452v1
  • Srivalli Katkuri, Maxwell Kawada, Juan Wachs. Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learning. arXiv preprint arXiv:2608.25350v1 : https://arxiv.org/abs/2608.25350v1
  • Jingyang Su, Pu Cao, Xiuze Jin, Longyue Zhang, Qing Song, Lu Yang. PointRL: Learning Point-Level Vision-Language Grounding from Verifiable Annotation Evidence. arXiv preprint arXiv:2608.25299v1 : https://arxiv.org/abs/2608.25299v1
  • Wei Zhou, Xiongwei Zhu, Lingdong Kong, Bo Chen, Lei Zhang, Yongyuan Liang, Xiaoxia Hou, Ye Tian, Xian Sun, Yingshuo Wang, Linfeng Li, Shengqiong Wu, Leigang Qu, Feng Li, Wei Liu, Julian McAuley, Tat-Seng Chua. On-Policy Self-Distillation in Diffusion Models. arXiv preprint arXiv:2608.24646v1 : https://arxiv.org/abs/2608.24646v1
  • Wenqi Liu, Shijie Ma, Yunxiao Wang, Meng Liu, Qile Su, Han Liu, Bohan Hou, Zeyu Wang, Xuanyu Zheng, Changyi Liu, Tianke Zhang, Haonan Fan, Kaiyu Jiang, Yingxin Li, Jiankang Chen, Xu Wang, Hongyi Fu, Jianxiong Wang, Bin Wen, Tingting Gao, Han Li, Jianhua Yin, Yinwei Wei, Xuemeng Song. Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents. arXiv preprint arXiv:2608.23329v2 : https://arxiv.org/abs/2608.23329v2
  • Tong Wang, Huan Deng, Mucheng Yang, Yang He, Xiaohui Kuang, Gang Zhao. From Generation to Simulation: How Far Are World Models from Being True Simulators?. arXiv preprint arXiv:2608.23070v1 : https://arxiv.org/abs/2608.23070v1
  • Simon Hakenes, Tobias Glasmachers. Macro-Action Topological Navigation under Noisy Localization using Reinforcement Learning. arXiv preprint arXiv:2608.23055v1 : https://arxiv.org/abs/2608.23055v1
  • Qichao Ma, Jikang Cheng, Ling Liang, Zhaofei Yu, Tiejun Huang, Renye Yan. Can We Perform Online RL for Image Editing without Editing Rewards?. arXiv preprint arXiv:2608.22780v1 : https://arxiv.org/abs/2608.22780v1
  • Yucheng Chen, Yang Yu, Jiazhou Zhou, Yufei Shi, Yongying Lan, Yichi Zhang, Liyi Li, Si Yong Yeo. UR$^{2}$-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report Generation. arXiv preprint arXiv:2608.22217v1 : https://arxiv.org/abs/2608.22217v1
  • Wen Luo, Xiaohan Yi, Xiaotao Huang, Liqun Huang. VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression. arXiv preprint arXiv:2608.21883v2 : https://arxiv.org/abs/2608.21883v2
  • Md Asaduzzaman Jabin, Zihao Wu, Tianming Liu. BioMed-Agent-RL: A Meta Learning, All You Need for Biomedical Applications. arXiv preprint arXiv:2608.21864v1 : https://arxiv.org/abs/2608.21864v1
  • Qiqian Fu. Hints, Critics, and Teachers: Prior Injection for Sparse-Reward RL in Vision-Language Math Reasoning. arXiv preprint arXiv:2608.21811v1 : https://arxiv.org/abs/2608.21811v1
  • Long Shu, Shuochen Liu, Wei Chen, Junda Lin, Zhi Zheng, Huijun Hou, Tong Xu. SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering. arXiv preprint arXiv:2608.21796v1 : https://arxiv.org/abs/2608.21796v1
  • Taihang Hu, Zhao Wang, Zuan Gao, Tao Liu, Hao Yan, Zhengze Xu, Yuhang Yu, Yongchao Du, Xingjian Wang, Jun Zheng, Qinye Zhou, Zhengrui Chen, Chao Lin, Yefeng Shen, Zhengtao Wu, Ge Wu, Xiaoli Xu, Denghui Yang, Huayu Zhang, Mingzhou Zhang, Mengting Chen. Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models. arXiv preprint arXiv:2608.20334v1 : https://arxiv.org/abs/2608.20334v1
  • Shiao Xie, Siyu Chen, Jianwei Lv, Bo Yuan, Yujin Wang, Xiandong Li. G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation. arXiv preprint arXiv:2608.20331v1 : https://arxiv.org/abs/2608.20331v1
  • Yunseo Lee, Hyun Jun Kim, Heeseung Shin, Changwon Lim. Towards Clinically Faithful Medical Image Captioning via Enhanced Vision-Language Alignment. arXiv preprint arXiv:2608.19825v1 : https://arxiv.org/abs/2608.19825v1
  • Johannes Künzel, Peter Eisert, Anna Hilsmann. RIPE++: Reinforced Keypoint Learning from Positive Pairs Only. arXiv preprint arXiv:2608.19693v1 : https://arxiv.org/abs/2608.19693v1
  • Haoqiang Kang, Yinpeng Chen, Luyang Liu, Jesper Sparre Andersen, Abhijit Ogale, Baochen Sun, Lichan Hong, Ed H. Chi. Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning. arXiv preprint arXiv:2608.19669v1 : https://arxiv.org/abs/2608.19669v1
  • Sofian Chaybouti, Yasser Dahou, Ngoc Dung Huynh, Reda Alami, Hilde Kuehne. Falcon Perception-HD: High Density Perception via Reinforcement Learning. arXiv preprint arXiv:2608.18881v1 : https://arxiv.org/abs/2608.18881v1
  • Kangning Ye, Yunhao Li, Sijing Wu, Yucheng Zhu, Guangtao Zhai. PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning. arXiv preprint arXiv:2608.18627v1 : https://arxiv.org/abs/2608.18627v1
  • Yinming Huang, Shuyuan Tu, Xi Yan, Zihan Yang, Jianhua Han, Xu Hang, Yu-Gang Jiang, Zuxuan Wu. VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation. arXiv preprint arXiv:2608.18607v2 : https://arxiv.org/abs/2608.18607v2
  • Amir Arsalan Nematollahi, Shayan Ahmadi, Mehdi Tale Masouleh, Ahmad Kalhor. Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision. arXiv preprint arXiv:2608.17628v1 : https://arxiv.org/abs/2608.17628v1
  • Zeyun Deng, Yuzhe Lu, Yawei Wang, Linbo Liu, Qing Ping, Han Ding, Guande Wu, Panpan Xu, Jun Huan. Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups. arXiv preprint arXiv:2608.17423v1 : https://arxiv.org/abs/2608.17423v1
  • Yuanbang Liu, Chenxi Ruan, Yihan Hou, Qiong Luo, Wei Zeng. REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models. arXiv preprint arXiv:2608.17414v1 : https://arxiv.org/abs/2608.17414v1
  • Yunhao Yang, Yuexin Bian, Yunjie Tian, Di Fu, Tianjin Huang, Yuanyuan Shi, Ziang Xiao, Nuno Vasconcelos, Yijiang Li. Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL. arXiv preprint arXiv:2608.17253v2 : https://arxiv.org/abs/2608.17253v2
  • Mohamad Mohamad, Francesco Ponzio, Maxime Gassier, Nicolas Pote, Xavier Descombes. Interactive Whole Slide Images for RL-based Tumour Segmentation. arXiv preprint arXiv:2608.16607v1 : https://arxiv.org/abs/2608.16607v1
  • Tristan Gottwald, Maximilian Schier, Melanie Schaller, Bodo Rosenhahn. FLEET: Token-Based Feature Extraction for Event Camera-based Reinforcement Learning. arXiv preprint arXiv:2608.16523v1 : https://arxiv.org/abs/2608.16523v1
  • Keming Wu, Baoyi Wang, Kaichen Zhang, Xiang An, Zuhao Yang, Sudong Wang, Haowei Zhu, Tingxuan Huang, Hongcheng Gao, Bin Wang. StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding. arXiv preprint arXiv:2608.16320v1 : https://arxiv.org/abs/2608.16320v1
  • Xiaoan Liu, Lichen Ma, Zipeng Guo, Yu He, Xiaoyan Su, Shaojie Guo, Jingling Fu, Xiaolong Fu, Hao Yang, Tongxuan Liu, Yu Guo, Fei Wang, Xinyi Liu, Yongjun Zhang, Junshi Huang. PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster. arXiv preprint arXiv:2608.16289v3 : https://arxiv.org/abs/2608.16289v3
  • Xiaoan Liu, Lichen Ma, Zipeng Guo, Yu He, Xiaoyan Su, Shaojie Guo, Hao Yang, Jingling Fu, Xiaolong Fu, Zhen Chen, Yu Guo, Fei Wang, Xinyi Liu, Yongjun Zhang, Ke Zhang, Junshi Huang. TransAnyText: Translating Arbitrary Text in E-commerce Images via Structured Visual Generation. arXiv preprint arXiv:2608.16284v1 : https://arxiv.org/abs/2608.16284v1
  • Bowen Deng, Jiahui Zhan, Yikun Ji, Haozhen Yan, Jianfu Zhang. Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection. arXiv preprint arXiv:2608.16259v1 : https://arxiv.org/abs/2608.16259v1
  • Alam Noor, Luis Almeida, Kai Li, Jiyan Wu, Miguel Gutiérrez Gaitán, Eduardo Tovar. Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System. arXiv preprint arXiv:2608.16142v1 : https://arxiv.org/abs/2608.16142v1
  • Zesheng Yang, Lingling Zhang, Xinyu Zhang, Cheng Zhang, Pengyu Li, Heng Wang, Lin Wu. GLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning. arXiv preprint arXiv:2608.15517v2 : https://arxiv.org/abs/2608.15517v2
  • Penghao Yin, Haomin Wang, Qihong Tang, Xiaoye Qu, Hongjie Zhang, Xiao-Ping Zhang. MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems. arXiv preprint arXiv:2608.15006v1 : https://arxiv.org/abs/2608.15006v1
  • Yi-Chung Chen, Philip Jacobson, Tom Lampo, Yiren Lu, Jin Yao, David I. Inouye, Jing Gao, Danhua Guo, Burhan Yaman. TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval. arXiv preprint arXiv:2608.13495v1 : https://arxiv.org/abs/2608.13495v1
  • Hao Dou. FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving. arXiv preprint arXiv:2608.13395v1 : https://arxiv.org/abs/2608.13395v1
  • Yao Zhou, Hang Gao, Fengge Wu, Changwen Zheng, Wenwen Qiang. Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning. arXiv preprint arXiv:2608.13026v1 : https://arxiv.org/abs/2608.13026v1
  • Ankita Joshi. A Deep RL based Framework for Targeted White Matter Tractography. arXiv preprint arXiv:2608.12960v1 : https://arxiv.org/abs/2608.12960v1
  • Yicheng Bao, Xiahui Guo, Xuhong Wang, Xin Tan. SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data. arXiv preprint arXiv:2608.12876v1 : https://arxiv.org/abs/2608.12876v1
  • Quan-Dung Pham, Anh Dao, The-Anh Nguyen, Minh Nguyen-Dinh, Phuong Nam Dang, Tri Pham, Hung Tran, Bach Dao, Tuyen P. Le, Truong Nguyen, Quan Nguyen. HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments. arXiv preprint arXiv:2608.12860v1 : https://arxiv.org/abs/2608.12860v1
  • Xinming Wang, Weinong Wang, Hongming Yang, Yansong Lin, Zheng Ruan, Shangpin Peng, Qiming Peng, Nan Qiao, Fengyuan Lu, Guoqing Ma, Marito Li, Songyang Zhang, Saiyong Yang, Han Hu, Yonglong Tian, Xu-Yao Zhang. Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs. arXiv preprint arXiv:2608.12781v1 : https://arxiv.org/abs/2608.12781v1
  • Zile Zhou, Huining Yuan, Weichen Zhang, Xinlei Chen, Xiao-ping Zhang. SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward. arXiv preprint arXiv:2608.12220v1 : https://arxiv.org/abs/2608.12220v1
  • Wenshuo Peng, Kaipeng Zhang. HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion. arXiv preprint arXiv:2608.11913v1 : https://arxiv.org/abs/2608.11913v1
  • Xinhao Zhong, Yuxia Qiao, Junhao Li, Hao Fang, Yi Sun, Bin Chen. LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection. arXiv preprint arXiv:2608.11691v1 : https://arxiv.org/abs/2608.11691v1
  • Bowei Liu, Zheng Lu, Yuhan Bian, Xinchen Zhang, Xingming Shui, Yuesheng Huang, Xuhuan Li, Zihao Liu, Yifan Yang, Jun Zhou, Xiu Li. VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics. arXiv preprint arXiv:2608.11201v1 : https://arxiv.org/abs/2608.11201v1
  • Shiyu Xuan, Zechao Li. Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation. arXiv preprint arXiv:2608.11191v1 : https://arxiv.org/abs/2608.11191v1
  • Xinrui Lin, Sha Zhang, Shumin Wang, Zenghuan Zhu, Jiajun Deng, Yanyong Zhang. ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes. arXiv preprint arXiv:2608.10981v1 : https://arxiv.org/abs/2608.10981v1
  • Yuetian Du, Yucheng Wang, Zhenyuan Chen, Luyuan Chen, Rongyu Zhang, Jinjian Zhang, Wei Zhou, Zhijie Xu, Ming Kong, Zhan Zhou, Jie Liu, Qiang Zhu. CARE: Confidence-Aware Reasoning for Reliable Medical VQA. arXiv preprint arXiv:2608.10964v1 : https://arxiv.org/abs/2608.10964v1
  • Zhaoyang Wei, Bowen Jiang, Xumeng Han, Jiashu Li, Xuehui Yu, Yuling Liu, Guorong Li, Zhenjun Han, Jianbin Jiao. Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes. arXiv preprint arXiv:2608.10954v1 : https://arxiv.org/abs/2608.10954v1
  • Shengzhi Wang, Jun Yang, Kai Wu, Xiaozhong Ji, Yiwen Ye, Ziyang Chen, Mingliang Xiong, Wen Fang, Mingqing Liu, Mengyuan Xu, Miaoxuan Shan, Caiyan Liu, Bin He, Qingwen Liu. MIRA: Medical Image Reflection for Agentic Diagnosis. arXiv preprint arXiv:2608.10827v1 : https://arxiv.org/abs/2608.10827v1
  • Fufangchen Zhao, Jinhu Fu, Jiachen Lei, Jiahong Wu, Xiangxiang Chu, Danfeng Yan. FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding. arXiv preprint arXiv:2608.10764v1 : https://arxiv.org/abs/2608.10764v1
  • Caoyuan Ma, Wenpu Liu, Weichu Xie, Tian Gu, Shilei Zhao, Lingxi Min, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Yinqiang Zheng. SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning. arXiv preprint arXiv:2608.10513v1 : https://arxiv.org/abs/2608.10513v1
  • Dongchi Huang, Hongyin Zhang, Bohan Hou, Siteng Huang, Zhian Su, Hang Guo, Tong Lu, Zhaofeng Xu, Jiahao Tang, Jianfei Yang, Donglin Wang, Peixi Peng, Mingxiu Chen, Deli Zhao, Xin Li. RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance. arXiv preprint arXiv:2608.09853v1 : https://arxiv.org/abs/2608.09853v1
  • Renshan Zhang, Haoyang Meng, Yixiao He, Rui Shao, April Hua Liu, Liqiang Nie. LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection. arXiv preprint arXiv:2608.09723v1 : https://arxiv.org/abs/2608.09723v1
  • Guolei Huang, Tengfei She, Yuxuan Lu, Yao Huang, Yuqi Ye, Yongjun Shen. FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving. arXiv preprint arXiv:2608.09591v1 : https://arxiv.org/abs/2608.09591v1
  • Zeyuan Ma, Jiaxin Chen, Di Huang. From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation. arXiv preprint arXiv:2608.09564v1 : https://arxiv.org/abs/2608.09564v1
  • Boxiong Wang, Hui Kang, Geng Sun, Jiahui Li, Chao Yu, Daxin Tian. RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation. arXiv preprint arXiv:2608.09467v1 : https://arxiv.org/abs/2608.09467v1
  • Zhi Zeng, Cheng Zhang, Zesheng Yang, Rendong Pi, Jiaying Wu, Di Zhang, Zihan Ma, Guodong Li, Zhou Yang, Yu Xiang, Yifei Zheng, Minnan Luo. Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models. arXiv preprint arXiv:2608.09435v1 : https://arxiv.org/abs/2608.09435v1
  • Mingfeng Lin, Chengfei Cai, Lin Xu, Yuxiang Wei, Liang Han. DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models. arXiv preprint arXiv:2608.09233v2 : https://arxiv.org/abs/2608.09233v2
  • Yuhan Li, Fangao Zeng, Sicong Kang, Mengfei Xu, Hao Zhou, Wei Li, Pipei Huang, Bingbing Ni. RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation. arXiv preprint arXiv:2608.09226v1 : https://arxiv.org/abs/2608.09226v1
  • Jiaye Fu, Weiqi Li, Qiankun Gao, Yanchen Zhao, Xiandong Meng, Jian Zhang, Siwei Ma, Jiaqi Zhang. CodecArena: Codec Quality Assessment via Visual Reinforcement Learning. arXiv preprint arXiv:2608.09139v1 : https://arxiv.org/abs/2608.09139v1
  • Jingyun Chen, Fengchun Liu, Linghan Cai, Songhan Jiang, Shenjin Huang, Hongpeng Wang, Lequan Yu, Yongbing Zhang. Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception. arXiv preprint arXiv:2608.08648v1 : https://arxiv.org/abs/2608.08648v1
  • Prishita Ray. Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies. arXiv preprint arXiv:2608.08545v1 : https://arxiv.org/abs/2608.08545v1
  • Hwanhee Kim, Jaehyun Jang, Seungmin Cha, Hyeonseo Yun, Donghoon Lee, Chang D. Yoo. Action- and Language-Conditioned Video Assessment for Embodied Control. arXiv preprint arXiv:2608.08273v1 : https://arxiv.org/abs/2608.08273v1
  • Rui Wang, Yeteng Wu, Xianling Zhang, Mengshi Qi. VTO: Visual Tool Orchestration for Video Anomaly Detection. arXiv preprint arXiv:2608.08219v1 : https://arxiv.org/abs/2608.08219v1
  • Jie Huang, Xiaohe Li, Jiahao Li, Fangli Mou, Chen Qian, Yuqiang Fang, Junhao Fan, Kaixin Zhang, Zide Fan. PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets. arXiv preprint arXiv:2608.08053v1 : https://arxiv.org/abs/2608.08053v1
  • Haojie Huang, Xinlei Yu, Chengming Xu, Zhangquan Chen, Cheng Yang, Qingdong He, Yu Yang, Jiangning Zhang, Xiaobin Hu. Evidence-RL: Towards Evidence-intensive Visual Reasoning. arXiv preprint arXiv:2608.08021v1 : https://arxiv.org/abs/2608.08021v1
  • Liangliang Zhao, Junying Wang, Danni Yang, Yifan Chang, Bin Fu, Yu Qiao, Bowen Zhou, Yihao Liu. Distilling Physical Priors into Streaming World Models. arXiv preprint arXiv:2608.07981v1 : https://arxiv.org/abs/2608.07981v1
  • Donghu Kim, Youngdo Lee, Hojoon Lee, Johan Obando-Ceron, Byungkun Lee, Aaron Courville, Pablo Samuel Castro, Jaegul Choo, Clare Lyle. V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control. arXiv preprint arXiv:2608.07870v1 : https://arxiv.org/abs/2608.07870v1
  • Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel. iARCS: Iterative Agentic RL for Controllable 3D Scene Generation. arXiv preprint arXiv:2608.06161v1 : https://arxiv.org/abs/2608.06161v1
  • Rui Li, Yuanzhi Liang, Ke Hao, Ziqiao Weng, Haibin Huang, Chi Zhang, XueLong Li. Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training. arXiv preprint arXiv:2608.06125v1 : https://arxiv.org/abs/2608.06125v1
  • He Kong, Zengjue Chen, Qi Wang, Qianli Xing, Runliang Niu, Peidong Liu, Jiawei Li, Shiqi Wang, Yi Chang. Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation. arXiv preprint arXiv:2608.05999v1 : https://arxiv.org/abs/2608.05999v1
  • Katrin Schmid, Iuri Frosio. Training a Conditioned Video Game Agent on a VLM Annotated Dataset. arXiv preprint arXiv:2608.05954v1 : https://arxiv.org/abs/2608.05954v1
  • Yingqing Guo, Hui Yuan, Zijian He, Mengdi Wang, Zheng Ding. LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction. arXiv preprint arXiv:2608.05600v1 : https://arxiv.org/abs/2608.05600v1
  • Bohai Gu, Yueyang Yuan, Taiyi Wu, Dazhao Du, Jian Liu, Xiaoyi Pang, Jie Zhang, Xiaocheng Lu, Haobin Zhong, Xiaotong Zhao, Alan Zhao, Song Guo. WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models. arXiv preprint arXiv:2608.04964v1 : https://arxiv.org/abs/2608.04964v1
  • Xuzheng Yang, Jun Ling, Tao Huang, Caiyan Qin, Peng Wang. Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO. arXiv preprint arXiv:2608.04698v1 : https://arxiv.org/abs/2608.04698v1
  • De Jiang, Zhengyang Zhang, Kehong Yuan, Shaohua Ma. CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language Models. arXiv preprint arXiv:2608.04509v1 : https://arxiv.org/abs/2608.04509v1
  • Shuo Liu, Huixiang Cai, Weiru Zhang, Xiaoyi Zeng. GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction. arXiv preprint arXiv:2608.04504v1 : https://arxiv.org/abs/2608.04504v1
  • Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun, Fengwei Teng, Chengwei Qin, Xiaobin Hu, Jun Xu, Shuicheng Yan. ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation. arXiv preprint arXiv:2608.04436v1 : https://arxiv.org/abs/2608.04436v1
  • Yuanshen Guan, Zipeng Feng, Chengru Song, Zhiwei Xiong, Peiqin Sun. Latent Reward Registers for Diffusion Preference Alignment. arXiv preprint arXiv:2608.03929v2 : https://arxiv.org/abs/2608.03929v2
  • Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Prasanth V, Abhyuday Kumara Swamy, Pranay Narhari Umredkar, Pradeep Narayan, Vivek Rajagopal, Tanuja Ganu. CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement. arXiv preprint arXiv:2608.03890v1 : https://arxiv.org/abs/2608.03890v1
  • Pyrros Koussios, Chenhao Li, Xin Chen, Andreas Krause. Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning. arXiv preprint arXiv:2608.03875v1 : https://arxiv.org/abs/2608.03875v1
  • Shuoqin Zhang, Tongtong Cheng, Xiru Gao, Jinzhuo Peng, Bin Zheng, Jiahao Tu, Ke Wang, Jia Pan, Zhe Hu, Kai Liu. EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement Learning. arXiv preprint arXiv:2608.03872v1 : https://arxiv.org/abs/2608.03872v1
  • Andrea Protopapa, Davide Buoso, Francesca Pistilli, Georgia Chalvatzaki, Giuseppe Averta. GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon Manipulation. arXiv preprint arXiv:2608.03753v1 : https://arxiv.org/abs/2608.03753v1
  • Weichen Xu, Zhenhua Liu, Lin Luo, Yaobo Liang, Chengtang Yao, Qingyu Mei, Jian Cao, Xixin Cao, Xing Zhang, Jiaolong Yang, Baining Guo. Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution. arXiv preprint arXiv:2608.03483v1 : https://arxiv.org/abs/2608.03483v1
  • Inkyu Sa, Konstantin Stulov, Rajat Bhageria. ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies. arXiv preprint arXiv:2608.02958v1 : https://arxiv.org/abs/2608.02958v1
  • Yizheng Wu, Jiashen Hua, Bing Deng, Jieping Ye. VC-Tooler: Learning Compositional and Adaptive Visual Tool Use. arXiv preprint arXiv:2608.02217v1 : https://arxiv.org/abs/2608.02217v1
  • Wei Jia, Zhicong Lu, Yu Chen, Xiang Wang, Shuai Li, Wenqian Lv, Jiayue Cao, Huaxing liu. CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding. arXiv preprint arXiv:2608.02078v1 : https://arxiv.org/abs/2608.02078v1
  • Jingqi Tian, Haoji Zhang, Lin Chen, Hongbo Jin, Haonan Xu, Tianrui Zhu, Xingming Shui, Shilin Ma, Wenjing Yang, Yansong Tang. AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning. arXiv preprint arXiv:2608.01980v1 : https://arxiv.org/abs/2608.01980v1
  • Jianmin Chen, Jiaqi Tang, Wei Wei, Xiaogang Xu, Jiafei Wu, Zhe Liu, Qianzhou Wang, Yingying Yan, Botong Geng, Yuyang Xia, Lei Zhang, Qifeng Chen. Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning. arXiv preprint arXiv:2608.01314v1 : https://arxiv.org/abs/2608.01314v1
  • Xinheng Han, Jianfei Wang, Yu Chen, Xiang Wang, Shuai Li, Weixing Li, Feng Pan. Credit the Right Box: Marginal Contribution Assignment for Structured Visual Perception. arXiv preprint arXiv:2608.01055v1 : https://arxiv.org/abs/2608.01055v1
  • Damir Nurtdinov, Alexei Kornaev, Alexander Maloletov. RL Bootstrapping of OpenVLA-OFT for a Novel Robot Embodiment. arXiv preprint arXiv:2608.01013v1 : https://arxiv.org/abs/2608.01013v1
  • Jiaxuan Kang, Siyu Chen, Mingda Li, Mingjie Liu, Tianyue Wang, Zhaoyang Wei, Yongheng Zhang, Yanchao Hao, Zheng Wei. LUT: Latent Utility Training for Visual Reasoning. arXiv preprint arXiv:2608.00743v1 : https://arxiv.org/abs/2608.00743v1
  • Jingtong Chen, Jiahui Wang, Xue Zhao, ShaoGuo Liu, Minghao Li. Element-Aware Group Learning for E-Commerce Image Generation. arXiv preprint arXiv:2608.00584v1 : https://arxiv.org/abs/2608.00584v1
  • Yunhao Wang, Binghong Wu, Zhenyu Huang, Jiacheng Shi, Shuo Huang, Tinghao Yu, Feng Zhang. DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards. arXiv preprint arXiv:2608.00536v2 : https://arxiv.org/abs/2608.00536v2
  • Yufei Zhang, Chenlu Zhan, Donghui Sun, Xiaoxin Chen, Hongwei Wang. SpatialAfford: Teaching Compact VLMs Where to Look and Where to Ground for Affordance. arXiv preprint arXiv:2608.00502v1 : https://arxiv.org/abs/2608.00502v1
  • Song Tang, Shuming Hu, Xincheng Shuai, Henghui Ding, Yu-Gang Jiang. Seek to Segment: Active Perception for Panoramic Referring Segmentation. arXiv preprint arXiv:2607.02497v1 : https://arxiv.org/abs/2607.02497v1
  • Liyan Tang, Fangcong Yin, Greg Durrett. Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning. arXiv preprint arXiv:2607.02490v1 : https://arxiv.org/abs/2607.02490v1
  • Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang. Optimizing Visual Generative Models via Distribution-wise Rewards. arXiv preprint arXiv:2607.02291v1 : https://arxiv.org/abs/2607.02291v1
  • Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov. Rank-Then-Act: Reward-Free Control from Frame-Order Progress. arXiv preprint arXiv:2607.01897v1 : https://arxiv.org/abs/2607.01897v1
  • Hexian Ni, Tao Lu, Yinghao Cai. CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning. arXiv preprint arXiv:2607.01721v1 : https://arxiv.org/abs/2607.01721v1
  • Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, Kai Lv. From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training. arXiv preprint arXiv:2607.00811v1 : https://arxiv.org/abs/2607.00811v1
  • Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv. Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos. arXiv preprint arXiv:2607.00808v1 : https://arxiv.org/abs/2607.00808v1
  • Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv. Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization. arXiv preprint arXiv:2607.00796v1 : https://arxiv.org/abs/2607.00796v1
  • Kuan-Chen Chen, Winston Chen, Wei-Fang Sun, Min-Chun Hu. VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning. arXiv preprint arXiv:2607.00483v2 : https://arxiv.org/abs/2607.00483v2
  • Lang Cao, Renhong Chen, Luyi Li, Peng Wang, Mofan Peng, Yitong Li. Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models. arXiv preprint arXiv:2606.31846v1 : https://arxiv.org/abs/2606.31846v1
  • Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang. Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning. arXiv preprint arXiv:2606.31825v1 : https://arxiv.org/abs/2606.31825v1
  • Yaozhi Zheng, Yilei Jiang, Manyuan Zhang, Yuxuan Wan, Kaituo Feng, Tianshuo Peng, Bo Zhang, Xiangyu Yue. UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization. arXiv preprint arXiv:2606.31732v1 : https://arxiv.org/abs/2606.31732v1
  • Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng, Shangquan Sun, Chunfeng Song, Xiaosong Wang, Mu Zhou, Mianxin Liu. Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning. arXiv preprint arXiv:2606.31599v1 : https://arxiv.org/abs/2606.31599v1
  • Mohammad Mahdi Abootorabi, Sina Namazi, Armin Saadat, Lyuyang Wang, Obed Dzikunu, Paul F. R. Wilson, Zhuoxin Guo, Brian Wodlinger, Parvin Mousavi, Purang Abolmaesumi. Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection. arXiv preprint arXiv:2606.30951v1 : https://arxiv.org/abs/2606.30951v1
  • Hyunwoo Park, Sang-Hyun Lee. Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data. arXiv preprint arXiv:2606.30192v1 : https://arxiv.org/abs/2606.30192v1
  • Eric Peh, Debaditya Roy, Basura Fernando. H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual Reasoning. arXiv preprint arXiv:2606.29915v1 : https://arxiv.org/abs/2606.29915v1
  • Siyao Chen, Jiakang Yuan, Jiaxin Wang, Tao Chen. Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models. arXiv preprint arXiv:2606.29892v1 : https://arxiv.org/abs/2606.29892v1
  • Tianshu Zhang, Yan Wang, Ji Qi, Lijie Wen. Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification. arXiv preprint arXiv:2606.29023v1 : https://arxiv.org/abs/2606.29023v1
  • Fatma Youssef Mohammed, Grzegorz Malczyk, and Kostas Alexis. Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation. arXiv preprint arXiv:2606.20491v1 : https://arxiv.org/abs/2606.20491v1
  • Chengwen Liu, Hao Peng, Jisheng Dang, Hong Peng, Bin Hu, and Tat-Seng Chua. CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs. arXiv preprint arXiv:2606.19927v1 : https://arxiv.org/abs/2606.19927v1
  • Seyed Alireza Azimi, Homayoon Farrahi, Abhishek Naik, Colin Bellinger, and A. Rupam Mahmood. Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation. arXiv preprint arXiv:2606.18594v1 : https://arxiv.org/abs/2606.18594v1
  • Mukund Khanna, Raj Singh Yadav, and Kunal Singh. ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL. arXiv preprint arXiv:2606.19103v1 : https://arxiv.org/abs/2606.19103v1
  • Yilian Liu, Sicong Leng, Guoshun Nan, Junyi Zhu, Jiayu Huang, Minghao Sun, Xuancheng Zhu, Yisong Chen, Zexian Wei, and Xiaofeng Tao. See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL. arXiv preprint arXiv:2606.17678v1 : https://arxiv.org/abs/2606.17678v1
  • Saraswathy Amjith. Self-Questioning Vision-Language Models: Reinforcement Learning for Compositional Visual Reasoning. arXiv preprint arXiv:2606.15651v1 : https://arxiv.org/abs/2606.15651v1
  • Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor, Abul Hasnat, and Firoj Alam. Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes. arXiv preprint arXiv:2606.15307v1 : https://arxiv.org/abs/2606.15307v1

Contribute

A paper is missing ? don't hesitate to open an issue or pull-request to keep the repository updated 😊

Ähnliche Projekte entdecken

sindresorhus/awesome

😎 Awesome-Listen zu allen möglichen interessanten Themen [HINWEIS: Pull Requests sind vorübergehend deaktiviert, bis ich dazu komme, die vorhandenen abzuarbeiten]

535,183 Sterne

EbookFoundation/free-programming-books

:books: Frei verfügbare Programmierbücher

401,490 Sterne

nilbuild/developer-roadmap

Interaktive Roadmaps, Leitfäden und weitere Bildungsinhalte, die Entwicklern helfen, in ihrer Karriere zu wachsen.

371,804 Sterne

vinta/awesome-python

Die maßgebliche Liste, die die Frage beantwortet: „Ich möchte X in Python machen – welches Tool soll ich verwenden?“

334,000 Sterne