A summary of related works about flow matching, stochastic interpolants

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…

Codebase of Predictive Preference Learning from Human Interventions

An Algorithm-Agnostic Framework for Online Reinforcement Learning with Generative Policies

Code for "Closing the Train-Test Gap in World Models for Gradient-Based Planning"

Multi-Joint dynamics with Contact. A general purpose physics simulator.

1st place solution of 2025 BEHAVIOR Challenge

The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

Repository for our paper: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics

Jax Codebase for Evolutionary Strategies at the Hyperscale

Code for paper 'Safe-FinRL: A Low Bias and Variance Deep Reinforcment Learning Implementation For High-Freq Stock Trading'

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

Interactive visualizations of the geometric intuition behind diffusion models.

A lightweight suite of motion imitation methods for training controllers.

Simulated experiments for "Real-Time Execution of Action Chunking Flow Policies".

[ICML 2023] Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics

Multi-turn RL framework for aligning models to be tutors instead of answerers. EMNLP 2025 Oral

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

[AAAI'26 Oral] DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

Code for the paper "Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models"

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

Code for "Transitive RL: Value Learning via Divide and Conquer"

Official repository for NeurIPS 2025 publication "Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization"

Code Release for floq: Training Critics via Flow-Matching for Scaling Compute In Value-Based RL

Controlling diverse robots by inferring jacobian fields with deep networks! Let's make robots understand their bodies!