Publications publications by categories in reversed chronological order
All topics Agent AI for Science AI Safety Alignment Evaluation & Benchmarks LLM Synthetic Data Memory Modularity Multilingual / Multimodal LM Post-training Pre-training Reinforcement Learning
★ Spotlight Agentic Evaluation of Copyright Law Compliance Zheng Hui , Doni Bloomfield, Noam Kolt
Agent AI Safety
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law Zheng Hui , Yijiang River Dong, Ehsan Shareghi, Nigel Collier
AI Safety Evaluation & Benchmarks
Language-Dependent Miscalibration in Multilingual LLM Evaluators Ej Zhou, Lucas Resck, Zheng Hui* , Anna Korhonen*
Multilingual / Multimodal LM AI Safety
MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization Weizhi Zhang, Xiaokai Wei, Wei-Chieh Huang, Zheng Hui , Chen Wang, Michelle Gong, Philip S. Yu
Memory Agent Evaluation & Benchmarks
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang, Yuanchen Bei, Yankai Chen, Tao Feng, Zhen Tan, Yu Wang, Zheng Hui , others
Memory Agent
★ Oral Value of Information: A Framework for Human-Agent Communication Yijiang River Dong, Tiancheng Hu, Zheng Hui , Caiqi Zhang, Ivan Vulic, Andreea Bobu, Nigel Collier
Agent Alignment
Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning Zheng Hui , Yijiang River Dong, Sanhanat Sivapiromrat, Ehsan Shareghi, Nigel Collier
Post-training Agent AI Safety Reinforcement Learning
Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation Reza Shirkavand, Xiaokai Wei, Chen Wang, Zheng Hui , Heng Huang, Michelle Gong
Modularity Pre-training Post-training
MATCHA: Can Multi-Agent Collaboration Build a Trustworthy Conversational Recommender? Zheng Hui , Xiaokai Wei, Yexi Jiang, Kevin Gao, Chen Wang, Frank Ong, Se-eun Yoon, Rachit Pareek, Michelle Gong
Agent AI Safety Post-training
The Mind in the Machine: A Survey of Incorporating Psychological Theories in LLMs Zizhou Liu*, Ziwei Gong*, Lin Ai*, Zheng Hui* , Run Chen*, Colin Wayne Leach, Michelle R. Greene, Julia Hirschberg
Post-training Pre-training Alignment
Cross-cultural Sentiment Analysis of Social Media Responses to a Sudden Crisis Event Zheng Hui , Zihang Xu, John Kender
Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI)
Multilingual / Multimodal LM Post-training
★ Oral WinClick: GUI Grounding with Multimodal Large Language Models Zheng Hui , Yinheng Li, Dan zhao, Tianyi Chen, Colby Banbury, Kazuhito Koishida
Agent Multilingual / Multimodal LM LLM Synthetic Data Post-training
Windows agent arena: Evaluating multi-modal os agents at scale Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, Arthur Bucker, Lawrence Jang, Zheng Hui
2025 International Conference on Machine Learning (ICML)
Agent Multilingual / Multimodal LM Evaluation & Benchmarks
Solving the Content Gap in Roblox Game Recommendations: LLM-Based Profile Generation and Reranking Chen Wang, Xiaokai Wei, Frank Yexi and
Ong Jiang, Kevin Gao, Xiao Yu, Zheng Hui , Se-eun Yoon, Philip Yu, Michelle Gong
LLM Synthetic Data
Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation Xiaofeng Zhang, Fanshuo Zeng, Yihao Quan, Zheng Hui , Jiawei Yao
Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. No. 10. 2025.
Multilingual / Multimodal LM Post-training
ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data? Zheng Hui , Zhaoxiao Guo, Hang Zhao, Juanyong Duan, Lin Ai, Yinheng Li, Julia Hirschberg, Congrui Huang
LLM Synthetic Data Post-training AI Safety
★ Oral PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent Jiateng Liu, Lin Ai, Zizhou Liu, Payam Karisani, Zheng Hui , May Fung, Preslav Nakov, Julia Hirschberg, Heng Ji
Proceedings of the 31st International Conference on Computational Linguistics
AI Safety LLM Synthetic Data
★ Oral ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information Zheng Hui , Zhaoxiao Guo, Hang Zhao, Juanyong Duan, Congrui Huang
Findings of the Association for Computational Linguistics: EMNLP 2024
LLM Synthetic Data AI Safety
Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension Lin Ai, Zheng Hui , Zizhou Liu, Julia Hirschberg
In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Post-training Pre-training
Defending Against Social Engineering Attacks in the Age of LLMs Lin Ai, Tharindu Kumarage, Amrita Bhattacharjee, Zizhou Liu, Zheng Hui , Michael Davinroy, James Cook, Laura Cassani, Kirill Trapeznikov, Matthias Kirchner, others
In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
AI Safety Alignment
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery Zimian Wei, Lujun Li, Peijie Dong, Zheng Hui , Anggeng Li, Menglong Lu, Hengyue Pan, Zhiliang Tian, Dongsheng Li
Modularity
LL-Diff: Low-Light Image Enhancement Utilizing Langevin Sampling Diffusion Boren Ding, Xiaofeng Zhang, Zekun Yu, Zheng Hui
International Journal of Pattern Recognition and Artificial Intelligence
Multilingual / Multimodal LM
BIB
TweetIntent@ Crisis: A Dataset Revealing Narratives of Both Sides in the Russia-Ukraine Crisis Lin Ai, Sameer Gupta, Shreya Oak, Zheng Hui , Zizhou Liu, Julia Hirschberg
Proceedings of the International AAAI Conference on Web and Social Media
LLM Synthetic Data
BIB
NTIRE 2023 challenge on efficient super-resolution: Methods and results Yawei Li, Yulun Zhang, Radu Timofte, Luc Van Gool, Lei Yu, Youwei Li, Xinpeng Li, Ting Jiang, Qi Wu, Mingyan Han, others
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Multilingual / Multimodal LM
BIB
Federation learning optimization using distillation Zheng Hui , Dingjie Chen, Zihang Xu
2021 Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS)
Modularity
BIB
Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison: A case study in hangzhou, China Rui Feng, Hui Zheng, An-ran Zhang, Chong Huang, Han Gao, Yu-cheng Ma
Environmental pollution, Volume 252, 366--378, 2019
AI for Science
BIB
