🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

💫 Toolkit to help you get started with Spec-Driven Development

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!

aider is AI pair programming in your terminal

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Making large AI models cheaper, faster and more accessible

the only cheat sheet you need

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

CLI tool for configuring and monitoring Claude Code

LLM Council works together to answer your hardest questions

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

Waymo Open Dataset

You Only Look Once for Panopitic Driving Perception.（MIR2022）

extrakto for tmux - quickly select, copy/insert/complete text without a mouse

MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.

CLIP-like model evaluation

Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

[CoRL 2022] InterFuser: Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

[ICCV'23] Hidden Biases of End-to-End Driving Models & A starter kit for the CARLA leaderboard 2.0.

BEVFormer, UniAD, VAD in Closed-Loop CARLA Evaluation with World Model RL Expert Think2Drive

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

[ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

[CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

VOXD is a speech-to-text, voice-typing, dictation software for linux distributions. It is an open-source, free of charge, USER-FRIENDLY software, for as many linux distros as possible.

Official Code for "SingularTrajectory: Universal Trajectory Predictor using Diffusion Model (CVPR 2024)"