[NeurIPS 2025] Official implementation for "Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling"

SOME/IP Java API based on vsomeip

Release for Improved Denoising Diffusion Probabilistic Models

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

An elegant PyTorch deep reinforcement learning library.

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

open llm for multimodal

Multimodal chatbot with computer vision capabilities integrated

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

TigerBot: A multi-language multi-task LLM

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM

General technology for enabling AI capabilities w/ LLMs and MLLMs

open llm for multimodal

This repository is an official implementation of HVDetFusion

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Highly cited and useful papers related to machine learning, deep learning, AI, game theory, reinforcement learning

A translation extension.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

PyTorch CTC Decoder bindings

Convolutional neural network model for video classification trained on the Kinetics dataset.

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase