Zheng Fang
3 papers · Latest:
Software Engineering
From Chat to Interview: Agentic Requirements Elicitation with an Experience Ontology
OntoAgent is an LLM-powered agent that uses an experience ontology to conduct structured, efficient, and effective requirements elicitation interviews.
2605.05828
Cryptography & SecuritySparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
This paper shows that sparse, token-aware gradient optimization can effectively jailbreak Audio Language Models, proving dense updates are redundant.
2605.04700
Information RetrievalEA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment
EA-Agent uses structured multi-step reasoning and triple selection with LLMs for efficient, interpretable, and state-of-the-art entity alignment.
2604.11686
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.