Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

Official Implementation of Paper "ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment"

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

Training and inference code for "Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning"

🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton

Next-gen Foundation Model for Embodied AI

Displaying code blocks with line numbers and line highlighting.

Pretraining code for a large-scale depth-recurrent language model

[NeurIPS 2024] Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation

Official PyTorch Implementation of "History-Guided Video Diffusion"

Official implementation of Trifle

Probabilistic programming with HuggingFace language models

👌[ICLR 2025] TFG-Flow: Training-free Guidance in Multimodal Generative Flow

Daily ArXiv Papers.

Personal python toolbox.

⚡⚡ Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecraft 🏝️

[ICLR 2025] LAPA: Latent Action Pretraining from Videos

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Programmatic generation of high-quality CVs

cursor IDE enjoy VIP

Implementation of a framework for Genie2 in Pytorch

Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).

[ICLR25] High-performance Image Tokenizers for VAR and AR

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

MineStudio: A Streamlined Package for Minecraft AI Agent Development

Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)

[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization