Scholar
Zhehui Huang
Google Scholar ID: vLUrmdMAAAAJ
Ph.D. Student of Computer Science, University of Southern California
Citations & Impact
Citations
296
H-index
7
i10-index
5
Publications
13
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple research papers on reinforcement learning, robot learning, and foundation models such as 'LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation', 'Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation', 'Compositional Coordination for Multi-Robot Teams with Large Language Models', etc., and presented research findings at various international conferences.
Research Experience
- Sept 2025: LAN2CB accepted to MRS 2025; July 2025: DSBench selected as an evaluation benchmark for OpenAI's most advanced LLM model o3 and their first agent ChatGPT Agent; June 2025: Successfully co-organized Resource Constrained Robotics Workshop at RSS 2025; Jan 2025: DSBench accepted to ICLR 2025; Dec 2024: HRT-ML accepted to WMAC @ AAAI 2025; MonTA accepted to LM4Plan @ AAAI 2025; Sept 2024: LLMs for Robot Routing accepted to ISRR 2024; May 2024: Started internship at Tencent America; Mar 2024: Received AI Research Grant from Cohere; Jan 2024: Two papers accepted to ICRA 2024; Nov 2023: Gave a talk at USC Robotics Seminar (URoS); Apr 2023: QuadSwarm accepted to ICRA 2023 Workshop: The Role of Robotics Simulators for Unmanned Aerial Vehicles; Mar 2023: Passed qualifying exam; May 2022: Started internship at NVIDIA; Sept 2021: Decentralized Control of Quadrotor Swarms accepted to CoRL 2021.
Education
- Currently a final-year Ph.D. student in Computer Science at the University of Southern California (USC), advised by Prof. Gaurav Sukhatme; Previously, received a master's degree in Computer Science from USC; Completed bachelor's degree in Computer Science at Harbin Institute of Technology.
Background
- Research interests include reinforcement learning, robot learning, and foundation models, aiming to develop intelligent agents that can robustly and safely perform complex tasks in unstructured environments by autonomously adapting to new situations through unsupervised and continual learning.
Miscellany
- Personal interests not mentioned
