Machine Learning · GitHub

API to run VirtualHome, a Multi-Agent Household Simulator

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

Graph Machine Learning course, Xavier Bresson, 2023

The Implementation of FastSpeech based on pytorch.

:dart: Qualify sales leads with machine learning

implement video caption based on openNMT

• data preprocessing
• Inference (translation) with batching and beam search

Traffic Flow Prediction with Neural Networks(SAEs、LSTM、GRU).

End-to-end Chinese scene-text detection and recognition with CTPN, CRNN, and CTC (legacy project).

SLICES: An Invertible, Invariant, and String-based Crystal Representation [2023, Nature Communications] MatterGPT, SLICES-PLUS

The deeplearning algorithms implemented by tensorflow

PyTorch深度学习快速入门教程（绝对通俗易懂！）

Tensorflow implementation for learning an image-to-image translation without input-output pairs. https://arxiv.org/pdf/1703.10593.pdf

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation

A VisualBasic(.NET) language kernel and runtime for scientific data computing, deep learning, LLM inference, GPU acceleration, visualization and command-line data-science applications — running on .NET (net10.0) across Windows, Linux and macOS.

• Extended VisualBasic syntax — Value(Of T) inline assignment, List(Of T) with a + append operator and rich indexers, LINQ helpers (Sequence, Iterates, which, sentinel) and Unix-shell style helpers (UnixBash.ls, cat).
• Command-line application framework — attribute-driven (<ExportAPI>, <Usage>) CLIs, automatic help generation, and InteropService to host external command-line tools.

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an agent edit code and train under governance: frozen task, scorer, and evidence.