Muhao Chen
Scholar

Muhao Chen

Google Scholar ID: k79yEZkAAAAJ
Assistant Professor of Computer Science, University of California, Davis
Natural Language ProcessingRobust MLAI SafetyVision-language Models
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
8,947
 
H-index
47
 
i10-index
112
 
Publications
20
 
Co-authors
42
list available
Contact
GitHubOpen ↗
Publications
46 items
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
2026
Cited
0
Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics
2026
Cited
0
DebugLM: Learning Traceable Training Data Provenance for LLMs
2026
Cited
0
Reinforced Attention Learning
2026
Cited
0
ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
2026
Cited
0
Automating API Documentation from Crowdsourced Knowledge
2026
Cited
0
Unbiased Visual Reasoning with Controlled Visual Inputs
2025
Cited
0
FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models
2025
Cited
0
Resume (English only)
Research Experience
  • Directs the Language Understanding and Knowledge Acquisition (LUKA) Lab; recently focusing on robustness and safety issues with large (multi-modal) language models and foundation model agents.
Background
  • Research interests include robust and accountable machine learning methods for natural language processing and multi-modal data processing.
Co-authors
42 total
Wenxuan Zhou
Wenxuan Zhou
Google Deepmind
Fei Wang
Fei Wang
Research Scientist, Google
Chaowei Xiao
Chaowei Xiao
University of Wisconsin - Madison/NVIDIA
Co-author 4
Co-author 4
Kai-Wei Chang
Kai-Wei Chang
Associate Professor, UCLA
Dan Roth
Dan Roth
Professor of Computer Science, University of Pennsylvania
Zequn Sun
Zequn Sun
Nanjing University
Nan Xu
Nan Xu
Ph.D. Student of Computer Science, University of Southern California