Lihan Zha

I am a senior undergraduate student at Weiyang College in Tsinghua University, double majoring in Mathematics and Physics and Energy and Power Engineering. My research goal is to enable robots to interact with the physical world.

I was a visiting researcher at Stanford Intelligent and Interactive Autonomous Systems Group (ILIAD), advised by Prof. Dorsa Sadigh, where I work on foundation models for robotics. Prior to that, I worked with Prof. Jianyu Chen on reinforcement learning for complex dynamics. I was also very fortunate to be advised by Prof. Dongxiang Jiang, where I worked on time series analysis.

I'm actively seeking PhD in robotics for Fall 2024!

Email  /  GitHub  /  Google Scholar  /  LinkedIn

Publications

(*: Equal contribution. Listed alphabetically.)

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections

We propose DROC that can respond effectively to online human language corrections, distill generalizable knowledge from corrections, and retrieve usable knowledge for future tasks.

DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment

We show how to leverage LLMs to generate constraints that can indicate misalignment during execution, and use VLMs to detect constraint violations continuously.

An Ultra-Short-Term and Short-Term Wind Power Forecasting Approach Based on Optimized Artificial Neural Network with Time Series Reconstruction

We propose using time series reconstruction to process serial wind power data and achieve state-of-the-art wind power prediction accuracy.

Awards

• National Scholarship, 2023.
• Jiang Nan Xiang Scholarship, Tsinghua University, 2022
• Innovation Award of Science and Technology, Tsinghua University, 2022-2023.
• Social Work Excellence Award, Tsinghua University, 2021.
• Comprehensive Excellence Award, Tsinghua University, 2021.

Design and source code from Leonid Keselman's website