Stars
SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
A ROS driver for Insta360 cameras, enabling real-time image capture, processing, and publishing in ROS environments.
Official implementation of AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
🔥(CVPR 2025 Highlight) Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
Active YAM teleop leader device integration for LeRobot
open-arms-mini: cheap human like teleoperation device that supports human in the loop corrections
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
One framework to evaluate any VLA model on any robot simulation benchmark.
Robotics research demonstrating reliability and robustness in the real world (continuously updated)
Train the smallest LM you can that fits in 16MB. Best model wins!
Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.
Lighter than feather, Harder than steel, RL Framework
A unified inference and post-training framework for accelerated video generation.
SRA-VJTI / jaxsim
Forked from gradsim/gradsima tiny differentiable sim
Interactive World Simulator for Robot Policy Training and Evaluation
A lightweight inference engine supporting speculative speculative decoding (SSD).
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
100M tokens. Infinite compute. Lowest val loss wins.
Luckfox pico documentation and experiments