LongLive: Real-time Interactive Long Video Generation

Actuated Version of the Universal Manipulation Interface Gripper

A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models

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

A fast and differentiable model predictive control (MPC) solver for PyTorch.

JAX implementation of MeanFlow

A simulation evaluation platform for DROID

PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)

A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.

Reference PyTorch implementation and models for DINOv3

Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…

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

Grounding Image Matching in 3D with MASt3R

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.

Training VLM agents with multi-turn reinforcement learning

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

PyTorch code and models for VJEPA2 self-supervised learning from video.

EgoZero: Robot Learning from Smart Glasses

A Modular Toolkit for Robot Kinematic Optimization

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

Code release for "RoboPrompt"