works on

From the 1 of 50 linked papers with an AI index.

activity
20242026
most citedA Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

1 citations · 1 across the 10 of their papers we have counts for

collaborators

50 papers

cs.AI2026

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Xiangning Lin, Shenzhe Zhu, Shu Yang +23

The paper presents AISPA, a user‑centric framework for auditing the system prompts that guide large language model behavior in commercial AI products, and reports findings from ana…

cs.CL2026

Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing

Shenzhe Zhu, Haoqian Zhang, Xu Yang +7

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cann…

cs.LG2026

Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories

Hengyu Jin, Shu Yang, Di Wang

Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning. However, these opaque hidden…

cs.CL2026

ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration

Shu Yang, Difei Xu, Jiaxin Pei +1

Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explicit user requests rather than…

cs.CL2026

SelfMem: Self-Optimizing Memory for AI Agents

Shu Yang, Junchao Wu, Derek F. Wong +1

While current AI agents support increasingly long context windows, tool use, and skill execution for long-horizon tasks, they still require memory systems to effectively leverage h…

cs.CV2026

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models

Juangui Xu, Zikun Guo, Jingwei Lv +5

Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a…