Shenao Zhang

I am a first-year Ph.D. student at Northwestern University, advised by Prof. Zhaoran Wang. I received my M.S. degree from Georgia Tech, where I was fortunate to work with Prof. Tuo Zhao and Prof. Bo Dai. I obtained my Bachelor's degree from South China University of Technology and visited Berkeley EECS during my undergrad.
Previously, I was a Student Researcher at Microsoft GenAI working with Donghan Yu. I also interned at ByteDance AML, Microsoft Research, and Tencent AI Lab.

CV  /  Email  /  Google Scholar  /  LinkedIn  /  Twitter

Research

My research centers around Large Language Models (LLMs) and Reinforcement Learning (RL). I’m currently interested in the efficient alignment of LLMs with RLHF, studying active synthetic data generation and more capable training algorithms. Previously, I built autonomous LLM agents and developed data-efficient decision-making algorithms with applications to robotic and multi-agent systems.

(* indicates equal contribution, ^† indicates equal advising)

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency

Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics

Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning

Learning Meta Representation for Agents in Multi-Agent Reinforcement Learning

How Can LLM Guide RL? A Value-Based Approach

Asking Before Action: Gather Information in Embodied Decision Making with Language Models

Structure-Regularized Attention for Deformable Object Representation

Professional Service

Conference Review: NeurIPS 2020-24, ICLR 2022-24, ICML 2022-24, AISTATS 2022-24, RSS 2021.

Journal Review: Neurocomputing, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Teaching

Graduate Teaching Assistant: Head TA of CS 7648: Interactive Robot Learning (Fall 2021) at Georgia Tech.

Source code from Jon Barron's website