The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Official code of RDT 2

Code for FastVGGT: Training-Free Acceleration of Visual Geometry Transformer

PyTorch code and models for the DINOv2 self-supervised learning method.

React + Next.js template for research websites (for PhD students, researchers, etc)

Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"

MinRL provides clean, minimal implementations of fundamental reinforcement learning algorithms in a customizable GridWorld environment. The project focuses on educational clarity and implementation…

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Reference PyTorch implementation and models for DINOv3

Cameras as Relative Positional Encoding

verl: Volcano Engine Reinforcement Learning for LLMs

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Official implementation of Continuous 3D Perception Model with Persistent State

Code for Streaming 4D Visual Geometry Transformer

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

[RSS 2025] Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation

[ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

OpenMMLab Model Compression Toolbox and Benchmark.

LeRobot sim2real code. Train in fast simulation and deploy visual policies zero shot to the real world

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

RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

A simulation platform for versatile Embodied AI research and developments.

this project provide a verity of code help you collect data from your robotic arm, have fun!

Automatic change of about and name in Telegram

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

Preliminary version of AutoBio (https://arxiv.org/abs/2505.14030)

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Let us control diffusion models!