AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
ICLR 2026
Academic Homepage
Hanjun Luo
Ph.D. Student in Computer Science, New York University
I am a first-year PhD student in Computer Science of New York University Abu Dhabi (Courant Track). My research focuses on Trustworthy AI and Agentic AI. I am passionate about creating a harmony future of human and AI. I also have long term collaborations with researchers in Nanyang Technology University and Zhejiang University. I am actively looking for research collaborations in LLM safety, trustworthy AI, and human-AI interaction.
Education
- New York University Abu Dhabi | Ph.D. in Computer Science (Expected 2030)
- Zhejiang University | B.E. in Computer Engineering (2025)
- University of Illinois Urbana-Champaign | B.S. in Computer Engineering (2025)
Recent Work
Publication
PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction
arXiv 2026
HAI-Eval: Measuring Human-AI Synergy in Collaborative Coding
arXiv 2025
AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents
NeurIPS 2025
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
EMNLP 2025 Main
A Comprehensive Survey in LLM(-agent) Full Stack Safety: Data, Training and Deployment
arXiv 2025
AutoDebias: Automated Framework for Debiasing Text-to-Image Models
arXiv 2025
BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
arXiv 2024
FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models
arXiv 2024
VersusDebias: Universal Zero-shot Debiasing for Text-to-Image Models via SLM-based Prompt Engineering and Generative Adversary
arXiv 2024
Uniap: Towards Universal Animal Perception in Vision via Few-shot Learning
AAAI 2024
Contact
If you are interested in collaboration on LLM safety and trustworthy AI, feel free to reach out.