Yang Zhang

Official Implementation of "Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models" (accepted at Transaction on Machine Learning Research, TMLR)

[NIPS'25] Official Implementation of "Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective" in PyTorch.

Official Implementation of "Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach"

MAMBA with smax evaluation

No description.

Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

An end-to-end open ecosystem for robot learning

An ML research template with good documentation by Boyuan Chen, an MIT PhD student

Fast and memory-efficient exact attention

An independent Python feature port of Claude Code, entirely rewritting from scratch using oh-my-codex. Educational Purpose only.

No description.

Personal homepage of Yang Zhang

BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

No description.

RoboTwin 2.0 Offical Repo

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

record the waiting/done list of papers to read

Variant of DayDreamer: World Models for Physical Robot Learning

A PyTorch implementation of Perceiver, Perceiver IO and Perceiver AR with PyTorch Lightning scripts for distributed training

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

Code for "Temporal Difference Learning for Model Predictive Control"

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.