8 papers
When Chatbots Accommodate: What AI Companions Optimize for in Vulnerable Conversations
Minh Duc Chu, Yifan Wu, Zhiyi Chen +2
Millions turn to AI companion chatbots during loneliness, grief, and personal crises. How these companion platforms respond in such moments can shape the trajectory of a user's vul…
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
Taiyu Zhu, Yifan Wu, Weilin Jin +2
LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks. However, these systems are highly sensitive to single-step execution errors…
Graph-Regularized Sparse Autoencoders for LLM Safety Steering
Jehyeok Yeon, Federico Cinus, Yifan Wu +1
Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity objective treats latent features as indep…
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
Li Huang, Zhongxin Liu, Yifan Wu +6
Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tun…
DS2SC-Agent: A Multi-Agent Automated Pipeline for Rapid Chiplet Model Generation
Yiwei Wu, Yifan Wu, Yunhao Xiong +6
Constructing behavioral-level chiplet models (e.g., SystemC) is crucial for early-stage heterogeneous architecture exploration. Traditional manual modeling is notoriously time-cons…
Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction
Juefei Pu, Xingyu Li, Zhengchuan Liang +5
Autonomous large language model (LLM) based systems have recently shown promising results across a range of cybersecurity tasks. However, there is no systematic study on their effe…