[NeurIPS2025] ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

A high-throughput and memory-efficient inference and serving engine for LLMs

LongLive: Real-time Interactive Long Video Generation

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Making large AI models cheaper, faster and more accessible

Discover Unknown Unsafe Events via Generative Simulation

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

🌐 A curated collection of vision-language-action (VLA) models for autonomous driving applications

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Enjoy the magic of Diffusion models!

[CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

Implementation for "Challenger: Affordable Adversarial Driving Video Generation"

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

[ICCV 2025] Official code of "ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Wan: Open and Advanced Large-Scale Video Generative Models

[ICCV 2025] Perspective-Invariant 3D Object Detection

Official Repository of "LOGen: Towards LiDAR Object Generation by Point Diffusion"

[ICCV 2025] Detect Anything 3D in the Wild

🌐 A curated evaluation toolkit and benchmark for state-of-the-art 3D and 4D world models

🌐 3D and 4D World Modeling: A Survey

Track 4: Cross-Modal Drone Navigation

Track 3: Sensor Placement

Track 2: Social Navigation

Track 1: Driving with Language

[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning