TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Make human motion capture easier.

ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping [CVPR 2025]

[CVPR 2021 Oral] Reconstructing 3D Human Pose by Watching Humans in the Mirror

Code release for paper "Reconstructing People, Places, and Cameras", In CVPR 2025 (Highlight)

Shareable model files (urdf/sdf + meshes, etc) for our robotics projects

😎 A curated list of awesome collision detection libraries and resources

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

[Humanoids 2025 Oral] Universal Humanoid Robot Pose Learning from Internet Human Videos

[RSS 2025] AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control

[ICCV 2025] ZeroStereo: Zero-Shot Stereo Matching from Single Images

Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.

ROEVO: Robust Organized Edge Feature-based Visual Odometry Using RGB-D Cameras

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

RynnEC: Bringing MLLMs into Embodied World

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

[TPAMI 2025 & CVPR 2023] IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching

Implementation of Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation, from Ye et al of UCSD

Official implementation of ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver.

Controlling diverse robots by inferring jacobian fields with deep networks! Let's make robots understand their bodies!

[RSS 2025] ROMAN: a view-invariant global localization method that matches objects from different robot views for reliable pose estimation even when a scene is observed from opposite views

【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power

NVIDIA NeMo Canary-Qwen-2.5B is an English speech recognition model that achieves state-of-the art performance on multiple English speech benchmarks.

Official Site for ManiFoundation Model

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Agent Zero AI framework

Universal memory layer for AI Agents

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.