most citedRIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection

2 citations · 2 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR2026

SIR: Self-improving Red-teaming for Compute Use Agents

Chen Xiong, Zhiyuan He, Pin-Yu Chen +2

Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly dep…

cs.AI2026

Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction

Yuxuan Huang, Yihang Chen, Zhiyuan He +6

Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current…

cs.AI2026

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Zhengxu Yu, Yu Fu, Zhiyuan He +5

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupl…

cs.AI2026

InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking

Ka Yiu Lee, Yuxuan Huang, Zhiyuan He +5

Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information…

cs.CR2026

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models

Chen Xiong, Zhiyuan He, Pin-Yu Chen +2

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, develope…

cs.CV2024★ 2 cited

RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection

Zhiyuan He, Pin-Yu Chen, Tsung-Yi Ho

The rapid advances in generative AI models have empowered the creation of highly realistic images with arbitrary content, raising concerns about potential misuse and harm, such as…