YANG, YAO

小船今已遠航，我最憂鬱的朋友。

Biography

Completed MSc in Artificial Intelligence at HKU and BEng in Data Science and Big Data Technology at NEU, YANG, YAO combines a solid theoretical grounding in mathematics and statistics with deep practical experience in algorithm programming. His research interests focus on (1) (Multimodal) Large Language Models, (2) Agents, and (3) Safe and Trustworthy AI, while staying OPEN to exploration across broader AI topics. Currently, He is pursuing PhD opportunities to further contribute to these domains.

Education

The University of Hong Kong 香港大學

Master of Science in Artificial Intelligence 人工智能理學碩士
Faculty of Science 理學院

  • Supervised by Prof. Yunwen Lei and Dr. Yue Xie

  • Sep 2023 to Jun 2025

    • Northeastern University 東北大學

    Bachelor of Engineering in Data Science and Big Data Technology
    數據科學與大數據技術工學學士
    School of Mathematics and Statistics 數學與統計學院

  • Supervised by Prof. Mingwei Li and Dr. Yushan Jiang

  • Sep 2019 to Jun 2023

    • Publications

    [ACL 2025] A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos

    Yang Yao, Xuan Tong, Ruofan Wang, Yixu Wang, Lujundong Li, Liang Liu, Yan Teng, Yingchun Wang

    ACL 2025, Findings, Vienna, Austria [#Poster] [#Resources]

    [ACM Multimedia 2025] Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

    Yang Yao, Lingyu Li, Jiaxin Song, Chiyu Chen, Zhenqi He, Yixu Wang, Xin Wang, Tianle Gu, Jie Li, Yan Teng, Yingchun Wang

    ACM Multimedia 2025, Dublin, Ireland [#Oral] [#Resources]

    [Technical Report] SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law

    Shanghai Artificial Intelligence Laboratory: Yang Yao (Core Contributor), et al.

    Intern Technical Report 2025, Shanghai, China [#Resources]

    [Under Review] Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports

    Yang Yao, Yixu Wang, Yuxuan Zhang, Yi Lu, Tianle Gu, Lingyu Li, Dingyi Zhao, Keming Wu, Haozhe Wang, Ping Nie, Yan Teng, Yingchun Wang

    arXiv Preprint 2025 [#Resources]

    [ICML 2026] Towards Context-Invariant Safety Alignment for Large Language Models

    Yixu Wang, Yang Yao, Xin Wang, Yifeng Gao, Yan Teng, Xingjun Ma, Yingchun Wang

    ICML 2026, Seoul, South Korea [#Poster]

    [AAAI 2026] The Other Mind: How Language Models Exhibit Human Temporal Cognition

    Lingyu Li, Yang Yao, Yixu Wang, Chunbo Li, Yan Teng, Yingchun Wang

    AAAI 2026, Singapore [#Poster] [#Resources]

    [ACL 2026] AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models

    Yixu Wang, Xin Wang, Yang Yao, Xinyuan Li, Xibang Yang, Yan Teng, Xingjun Ma, Yingchun Wang

    ACL 2026, Findings, San Diego, USA

    [ICLR 2026] GhostEI-Bench: Do Mobile Agent Resilience to Environmental Injection in Dynamic On-Device Environments?

    Chiyu Chen, Xinhao Song, Yunkai Chai, Yang Yao, Haodong Zhao, Lijun Li, Jie Li, Yan Teng, Gongshen Liu, Yingchun Wang

    ICLR 2026, Rio de Janeiro, Brazil [#Poster] [#Resources]

    [NeurIPS 2025] SafeVid: Toward Safety Aligned Video Large Multimodal Models

    Yixu Wang, Jiaxin Song, Yifeng Gao, Xin Wang, Yang Yao, Yan Teng, Xingjun Ma, Yingchun Wang, Yu-Gang Jiang

    NeurIPS 2025, San Diego, USA [#Poster] [#Resources]

    [Technical Report] OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

    Xin Wang, Yunhao Chen, Juncheng Li, Yixu Wang, Yang Yao, Tianle Gu, Jie Li, Yan Teng, Xingjun Ma, Yingchun Wang, Xia Hu

    OpenRT Technical Report 2026, Shanghai, China [#Resources]

    [ACL 2026] Probing the Safety Robustness of LLMs in Latent Space

    Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang

    ACL 2026, San Diego, USA [#Resources]

    [AAAI 2026] CADiff: Context-Aware Diffusion for Controllable Anomaly Generation in Anomaly Detection

    Xuan Tong, Yuxuan Lin, Junxiong Lin, Xinji Mai, Haoran Wang, Zeng Tao, Yang Yao, Ruofan Wang, Wenqiang Zhang

    AAAI 2026, Singapore [#Poster]

    [Under Review] Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models

    Ruofan Wang, Xin Wang, Yang Yao, Juncheng Li, Xuan Tong, Xingjun Ma

    arXiv Preprint 2025

    [Under Review] Paint Your Prompt: From Sequential Text to Structured Blueprints for Enhanced Image Synthesis

    Lujundong Li, Dazhong Shen, Yang Yao, Zhonggai Wang, Guanglu Song, Ying Sun

    Preprint Not Released

    Internship

    Shanghai Artificial Intelligence Laboratory
    上海人工智能實驗室

    Large Model Algorithm Intern 大模型算法實習生
    Safety and Trustworthy AI Center, Research Department

  • Supervised by Prof. Yingchun Wang and Dr. Yan Teng

  • Nov 2024 to Present

    • Pastimes

    Travel, Plays and Meditation

    Travel has long been a profound passion of mine. My journeys have carried me to the edge of the world—to Longyearbyen and Ny-Ålesund in the Arctic, where silence reigns, glaciers breathe, and the horizon stretches into a quiet infinity. Besides, theatre and film offer imaginative passageways into lives unchosen, unfolding parts of myself I might never meet. I also find solace in writing and meditation.

    # Voyage Stamps

    Beyond my homeland mainland, the following are the countries and regions I have explored in recent years. With a heart full of wanderlust, I eagerly look forward to discovering many more places in the years to come. P.S. Longyearbyen is my favorite : )

    Hong Kong

    Macao

    Taiwan

    Germany

    France

    Italy

    Switzerland

    Vatican

    Japan

    Egypt

    Norway

    Longyearbyen

    Finland

    Sweden

    Denmark

    Austria

    Czech

    Slovakia

    Hungary

    Turkey

    South Korea

    Ireland

    Australia

    Qatar

    Saudi Arabia