starVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Contexts Optical Compression

Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.

MiMo-VL

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

Fully Open Framework for Democratized Multimodal Training

[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Spatial Reasoning with Vision-Language Models

Accessible large language models via k-bit quantization for PyTorch.

Wan: Open and Advanced Large-Scale Video Generative Models

Code of π^3: Permutation-Equivariant Visual Geometry Learning

[ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World

Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)

Official implementation of Continuous 3D Perception Model with Persistent State

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

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

Code for Streaming 4D Visual Geometry Transformer

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

Adapting VLMs to Bench2Drive.

The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'

[CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[CVPR 2025, Spotlight] SimLingo (CarLLava): Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment