Publications

HeroWorld: Long-Horizon Action-Conditioned World Models for Third-Person Games
Mingjia Huo, Kaiqin Kong, Minshen Zhang, Shaoxiong Duan, Junda Su, Will Lin, Hao Zhang
F2S@ICML 2026 Workshop.
Paper GitHub

LMGame-Bench: How Good are LLMs at Playing Games?
Lanxiang Hu*, Mingjia Huo*, Yuxuan Zhang, Haoyang Yu, Eric P. Xing, Ion Stoica, Tajana Rosing, Haojian Jin, Hao Zhang
ICLR 2026.
Paper GitHub

Multi-Modal Large Language Model Enables Protein Function Prediction
Han Guo, Mingjia Huo, Xingyi Cheng, Digvijay Singh, Hamidreza Rahmani, Shen Li, Philipp Gerlof, Trey Ideker, Danielle A. Grotjahn, Elizabeth Villa, Le Song, Pengtao Xie
Paper GitHub

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
Mingjia Huo*, Sai Ashish Somayajula*, Youwei Liang, Ruisi Zhang, Farinaz Koushanfar, Pengtao Xie
ICML 2024.
Paper GitHub

All Eyes On Me: Inside Trackers’ Exfiltration of PHI from Healthcare Providers’ Online Systems.
Mingjia Huo, Maxwell Bland, Kirill Levchenko
Proceedings of the 21st Workshop on Privacy in the Electronic Society (WPES), 2022.
Paper HHS(US HHS Bulletin after our notification) Letter(HHS & FTC letter)