Zhuoran Yang Research Group

university

https://zhuoranyang.github.io/

AI & ML interests

Reinforcement Learning, Language Models, Diffusion Models

zhuoranyang

authored 9 papers 3 months ago

A Theoretical Analysis of Deep Q-Learning

Paper • 1901.00137 • Published Jan 1, 2019

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Paper • 2305.18459 • Published May 29, 2023

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

Paper • 2312.01127 • Published Dec 2, 2023

In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention

Paper • 2503.12734 • Published Mar 17, 2025

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders

Paper • 2506.14002 • Published Jun 16, 2025 • 5

On Computation and Generalization of Generative Adversarial Imitation Learning

Paper • 2001.02792 • Published Jan 9, 2020 • 1

Muon Outperforms Adam in Tail-End Associative Memory Learning

Paper • 2509.26030 • Published Sep 30, 2025 • 19

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning

Paper • 2510.14095 • Published Oct 15, 2025 • 5

Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation

Paper • 2510.15624 • Published Oct 17, 2025 • 14

zhuoranyang

authored a paper 11 months ago

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

Paper • 2502.16707 • Published Feb 23, 2025 • 13

zhuoranyang

authored a paper about 1 year ago

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?

Paper • 2412.02611 • Published Dec 3, 2024 • 25

zhuoranyang

authored a paper about 2 years ago

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

Paper • 2207.14800 • Published Jul 29, 2022