This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention while not compromising accuracy.
机器学习 · GitHub
发现模型训练、评估与推理框架,比较深度学习和机器学习项目的社区关注度。
实用 GitHub 项目
TF-rex
vdutor
Play Google Chrome's T-rex game with TensorFlow
vectorai
vector-ai
Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.
odyssey
VectorInstitute
An interpretable foundation model of the patient clinical timeline: event forecasting, calibrated time-to-event alerts, and concept-level interpretability, benchmarked head-to-head against tuned GBMs, tabular foundation models, and survival baselines on MIMIC-IV, eICU, and GEMINI via the MEDS standard.
AREX-Skill
VectorSpaceLab
vecstack
vecxoz
VedAstro
VedAstro
useful-java-links
Vedenin
A deep learning method for event driven stock market prediction. Deep learning is useful for event-driven stock price movement prediction by proposing a novel neural tensor network for learning event embedding, and using a deep convolutional neural network to model the combined influence of long-term events and short-term events on stock price movements
what_are_embeddings
veekaybee
DataCamp-Project-Solutions-Python
veeralakrishna
Sparse and structured neural attention mechanisms
ai-ml
venkataravuri
A collection of AI/ML articles, guides and projects.
alpha-beta-CROWN
Verified-Intelligence
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)
auto_LiRPA
Verified-Intelligence
auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs
TIM-VX
VeriSilicon
VeriSilicon Tensor Interface Module
Torchelie
Vermeille
Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch.
matrex
versilov
A blazing fast matrix library for Elixir/Erlang with C implementation using CBLAS.
data-ethics-club
very-good-science
F1-StratLab
VforVitorio

Open-source multi-agent AI platform for Formula 1 race replay, strategy simulation, and explainable race strategy recommendations. (work in progress, MVP in legacy branch)
- Lap-by-lap 2D race replay of a Grand Prix, in real time
- Six specialised strategy agents (pace, tire, race situation, pit, radio, regulations) plus a Monte Carlo orchestrator
repeng
vgel
A library for making RepE control vectors
GuidedLDA
vi3k6i5
semi supervised guided topic model with custom guidedLDA
Dosidicus
ViciousSquid
Raise a neural network as a pet - a transparent cognitive sandbox where digital squids learn, grow, and rewire via Hebbian learning & Neurogenesis
mixed-segdec-net-comind2021
vicoslab
Official PyTorch implementation for "Mixed supervision for surface-defect detection: from weakly to fully supervised learning"




