Starred repositories
DeepSeek V4 深度解读 · 73 页 PPT + 20 分钟讲稿 + 发布动画 · Designed with huashu-design
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…
完全免费, 自动获取新账号,一键重置新额度, 解决机器码问题, 自动满额度
WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?
[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"
PROJ - Cartographic Projections and Coordinate Transformations Library
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
Open-source simulator for autonomous driving research.
[CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫
1 million FPS multi-agent driving simulator
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
CUDA Python: Performance meets Productivity
👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!
[ICLR 26] RAP: 3D Rasterization Augmented End-to-End Planning
🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
Fast and memory-efficient exact attention
[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions