Native and Compact Structured Latents for 3D Generation

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

Are Video Models Ready as Zero-shot Reasoners?

Depth Anything 3

Humanoid Robots Resources

Code for "PHUMA: Physically-Grounded Humanoid Locomotion Dataset"

[Neurips DB 2025] PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

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

Reasoning in Space via Grounding in the World

[PKU EPIC Lab] 面向小白的具身智能入门指南

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

Official implementation of OpenTrack.

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

A Paper List for Humanoid Robot Learning.

A curated list of behavior(al) foundation model (BFM) papers, articles, tutorials, slides and projects

[ICCV 2025] Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

[NeurIPS 2024 Spotlight] PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation"

[AAAI2026] X-SAM: From Segment Anything to Any Segmentation

A collection of paper/projects that trains flow matching model/policies via RL.

Reference PyTorch implementation and models for DINOv3

Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

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

verl: Volcano Engine Reinforcement Learning for LLMs

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos