1 citations · 2 across the 11 of their papers we have counts for
11 papers
VeriScene: Reconstructing Crime Scenes from Legal Evidence via World-Model Agent
Kevin Chuanpu Fu, Yongsen Zheng, Zee Kin Yeong +1
World models take multimodal inputs like text, photos, and diagrams to generate dynamic scenes in accordance with the laws of physics, thus opening a compelling application: fusing…
UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs
Xuexiong Yin, Zechuan Chen, Yongsen Zheng +5
Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level personal…
How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence
Yue Chen, Yihao Wang, Ziyi Tang +2
Document Layout Analysis (DLA) pipelines provide structured page representations for retrieval-augmented generation, long-document question answering, and related applications. Yet…
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
Xuanye Zhang, Yongsen Zheng, Zhuqin Xu +5
LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong too…
Process-of-Thought Reasoning for Videos
Jusheng Zhang, Kaitong Cai, Jian Wang +3
Video understanding requires not only recognizing visual content but also performing temporally grounded, multi-step reasoning over long and noisy observations. We propose Process-…
Spectral Gating Networks
Jusheng Zhang, Yijia Fan, Kaitong Cai +5
Gating mechanisms are ubiquitous, yet a complementary question in feed-forward networks remains under-explored: how to introduce frequency-rich expressivity without sacrificing sta…
The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
Chen Chen, Kim Young Il, Yuan Yang +7
Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue ob…
Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey
Yuqing Zhao, Ziyao Liu, Yongsen Zheng +1
Large Language Models (LLMs)-based question answering (QA) systems play a critical role in modern AI, demonstrating strong performance across various tasks. However, LLM-generated…
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
Kaiyu Zhou, Yongsen Zheng, Yicheng He +5
The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-…
FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
Si Qi Goh, Yongsen Zheng, Ziyao Liu +2
Machine unlearning (MU) seeks to eliminate the influence of specific training examples from deployed models. As large language models (LLMs) become widely used, managing risks aris…
Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens
Ziliang Chen, Tianang Xiao, Jusheng Zhang +2
Contrastive Language-Image Pre-training (CLIP) delivers strong cross modal generalization by aligning images and texts in a shared embedding space, yet it persistently fails at com…