123D: A Unified Library for Multi-Modal Autonomous Driving Data

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

PyTorch code and models for VJEPA2 self-supervised learning from video.

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

Code for the paper "Conditional Representation Learning for Customized Tasks" (NeurIPS 2025 Spotlight)

[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

A Training-free Model for Video Understanding

FreeVA: Offline MLLM as Training-Free Video Assistant

[ECCV 2024] Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving

TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[NeurIPS 2025]⭐️ Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning.

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Deep Reinforcement Learning

1 million FPS multi-agent driving simulator

[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Generative Agents: Interactive Simulacra of Human Behavior

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

Emergency Index (EI): A two-dimensional surrogate safety measure considering vehicles' interaction depth

[CoRL 2024 Oral] FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality