dexhand manipulation tasks build upon mjlab

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

RoTO is an open-source Reinforcement Learning benchmark environment designed to standardise and promote future research in tactile-based manipulation.

Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").

DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies

HuMI: Humanoid Manipulation Interface

Feel Robot Feels: Tactile Feedback Array Glove for Dexterous Manipulation

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

Video-Action Models for Generalizable Robot Control Beyond VLAs

Official implementation of SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

WorldEngine: Towards the Era of Post-Training for Physical AI

[CVPR 2026 Oral] Learning to Drive via Real-World Simulation at Scale

[RSS 2026] The first framework enabling humanoid robots to learn whole-body loco-manipulation from egocentric human demos

Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks

This is hardware and firmware repo of flexitac.

Tutorial on adapting BrainCo Revo2 hands for Unitree G1 robot.

EgoVerse: Egocentric Data for Robot Learning from Around the World

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FASTER: Rethinking Real-Time Flow VLAs

Implementation of HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies (Amber Xie, Haozhi Qi, Dorsa Sadigh)

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

[CVPR 2026 Highlight] XL-VLA: Cross-Hand Latent Representation for Vision-Language-Action Models

This is a official code for the benchmark of the paper "VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning" (ICLR 2025)

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos (ICML 2026)

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video

ICRA 2026: Dexora: Open-source VLA for High-DoF Bimanual Dexterity

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)