YW
Yutao Wu
cs.AIcs.CLcs.CVcs.CRcs.LGcs.RO
On Valency
published · living versionsW_8hf6h7cw·v1 · currentpublished
SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents
with Cheng Gui, Xiang Zheng, Hanxun Huang, Yige Li +3
1 version
Preprints & journals
8 papers in the corpus · 2026HazardAuditor: From Executable Threats to Safer Computer-Use Agents2609.15134v1 · Yunhao Feng, Ruixiao Lin, Ming Wen et al.2026 · 0 citationsarXiv
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification2607.01793v2 · Yunhao Feng, Ruixiao Lin, Ming Wen et al.2026 · 0 citationsarXiv
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs2608.14577v1 · Zhouyuan Ma, Yutao Wu, Hanxun Huang et al.2026 · 0 citationsarXiv
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents2604.02947v2 · Yunhao Feng, Yifan Ding, Yingshui Tan et al.2026 · 0 citationsarXiv
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses2605.02900v2 · Xiao Li, Xiang Zheng, Yifeng Gao et al.2026 · 0 citationsarXiv
Internal Safety Collapse in Frontier Large Language Models2603.23509v1 · Yutao Wu, Xiao Liu, Yifeng Gao et al.2026 · 0 citationsarXiv
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models2602.01025v1 · Kaiyuan Cui, Yige Li, Yutao Wu et al.2026 · 0 citationsarXiv
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.52601.10527v2 · Xingjun Ma, Yixu Wang, Hengyuan Xu et al.2026 · 0 citationsarXiv
Career total: 10 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.