Highlights
Stars
Lightweight, useful implementation of conformal prediction on real data.
[CoRL 2025] Mechanistic interpretability and activation-level steering for Vision-Language-Action models, enabling causal analysis and real-time behavioral control without fine-tuning.
A beginner-friendly yet powerful Python toolkit for financial analysis and automation — built to make modern investing accessible to everyone
[ICLR 2026 🔥] Dr.LLM: Dynamic Layer Routing in LLMs
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights"
An open-source implementation of Multitask Diffusion Transformer (DiT) Policy for robot manipulation as seen on Boston Dynamics Atlas Humanoid and in "A Careful Examination of Large Behavior Models…
Web site of the Computational Optimal Transport book
MichalZawalski / embodied-CoT
Forked from openvla/openvlaEmbodied Chain of Thought: A robotic policy that reason to solve the task.
Stanford-ILIAD / openvla-mini
Forked from openvla/openvlaOpenVLA: An open-source vision-language-action model for robotic manipulation.
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
Code for Temporal Straightening for Latent Planning
PyTorch code and models for VJEPA2 self-supervised learning from video.
AI agents running research on single-GPU nanochat training automatically
Reliable, minimal and scalable library for pretraining foundation and world models
Code for the paper Robot Data Curation with Mutual Information Estimators
Code for "Evaluating Robot Policies in a World Model".
BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx
The official implementation of flow Q-learning (FQL)
An open-source framework for training large multimodal models.
Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223
Automatically create Faiss knn indices with the most optimal similarity search parameters.
[ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.
Roboto_origin Fully Open-Source DIY Humanoid Robot/萝博头原型机全开源手搓级人形机器人