Lihan Zha

I am a PhD student at Princeton University, advised by Anirudha Majumdar. I am interested in building generalist robots.

Previously, I graduated from Tsinghua University, where I worked with Jianyu Chen on humanoid robots. I was also a visiting student at Stanford, advised by Dorsa Sadigh.

Email: lihanzha [at] princeton [dot] edu
GitHub  /  Twitter  /  Google Scholar  /  LinkedIn  / 

Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators

We present a framework that augments real-world evaluations with simulation evaluations to provide stronger inferences on real-world policy performance that could otherwise only be obtained by scaling up real-world evaluations.

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

We introduce VLM2VLA, a VLA model training paradigm that represents low-level robot actions in natural language to better align the robot fine-tuning data with the base VLM’s representation space. VLM2VLA yields a policy with strong VQA performance and zero-shot generalization to new scenarios.

WoMAP: World Models For Embodied Open-Vocabulary Object Localization

We introduce World Models for Active Perception (WoMAP), a scalable recipe for training open-vocabulary object localization policies that are grounded in the physical world.

Guiding Data Collection via Factored Scaling Curves

We introduce Factored Scaling Curves (FSC), which model how policy performance scales with data for different environmental factors and can be extrapolated to guide principled data collection.

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.

• 2024 Outstanding Graduate in Beijing, China.
• 2023 National Scholarship. Highest honor for undergraduates
• 2023 Jiang Nan Xiang Scholarship. Highest honor for undergraduates

Design and source code from Jon Barron