OSCAR — public inference release

This repository provides a structured set of tutorials for learning and applying the Pinocchio rigid-body dynamics library.

From Imitation to Refinement -- Residual RL for Precise Assembly

Token usage reactive horse pet for Claude Code statuslines and Codex CLI sessions

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing

(ICLR 2026) TwinVLA : Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models

Agents' Last Exam

Code for paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

Implementation of "FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles"

AI Worker: FFW (Freedom From Work)

🤗 LeLab: A web UI interface on top of LeRobot

Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.

A Simple Baseline for Video World Models with Memory

WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation

Code Release for GraspGenX

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Self-Supervised LiDAR Ground Segmentation [CVPR 2026]

Open-H-Embodiment is a community‑driven dataset initiative building the open, shared foundation needed to train and evaluate a generalist Vision‑Language‑Action (VLA) model for healthcare robotics

MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

Official implementation of "Turning Video Models into Generalist Robot Policies"