Publications

Publications

Research on robust, safe, and multimodal AI systems.

Google Scholar
Date Tags Title

2025

  1. NeurIPS WS

    Deep Research Brings Deeper Harm

    Shuo Chen, Zonggen Li, Han Zhen, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu

    Reliable ML from Unreliable Data Workshop @ NeurIPS

    Paper Project
  2. OpenAI 🏆 Red Teaming Reasoning Safety

    Bag of Tricks for Subverting Reasoning-based Safety Guardrails

    Shuo Chen, Han Zhen, Haokun Chen, Bailan He, Shengyun Si, Jingpei Wu, Philip Torr, Volker Tresp, Jindong Gu

    OpenAI Red-Teaming Challenge Honorable Mention Award

    Paper Project
  3. COLM Multimodal In-Context

    True Multimodal In-Context Learning Needs Attention to the Visual Context

    Shuo Chen, Jianzhe Liu, Zhen Han, Yan Xia, Daniel Cremers, Philip Torr, Volker Tresp, Jindong Gu

    Conference on Language Modeling (COLM)

    Paper Project Code Dataset
  4. EMNLP Video

    METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding

    Mengyue Wang, Shuo Chen, Kristian Kersting, Volker Tresp, Yunpu Ma

    Conference on Empirical Methods in Natural Language Processing (EMNLP) Main

    Paper
  5. COLM

    Supposedly Equivalent Facts That Aren’t? Entity Frequency in Pre-training Induces Asymmetry in LLMs

    Yuan He, Bailan He, Zifeng Ding, Alisia Lupidi, Yuqicheng Zhu, Shuo Chen, Caiqi Zhang, Jiaoyan Chen, Yunpu Ma, Volker Tresp

    COLM

  6. ACL Red Teaming Multimodal

    Multimodal pragmatic jailbreak on text-to-image models

    Tong Liu, Zhixin Lai, Jiawen Wang, Gengyuan Zhang, Shuo Chen, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu

    ACL

  7. WACV Multimodal In-Context

    Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?

    Shuo Chen, Zhen Han, Bailan He, Mark Buckley, Philip Torr, Volker Tresp, Jindong Gu

    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

2024

  1. EMNLP Multimodal

    Visual question decomposition on multimodal large language models

    Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen, Bailan He, Volker Tresp, Zhiqiang Xu, Jindong Gu

    Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings

  2. COLM Multimodal Reasoning

    Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images

    Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu

    Conference on Language Modeling (COLM) 2024

  3. SET LLM @ ICLR Red Teaming Safety

    Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?

    Shuo Chen, Zhen Han, Bailan He, Zifeng Ding, Wenqian Yu, Philip Torr, Volker Tresp, Jindong Gu

    ICLR 2024 Workshop on Secure and Trustworthy Large Language Models

  4. arXiv MoE

    PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model

    Yilun Liu, Yunpu Ma, Shuo Chen, Zifeng Ding, Bailan He, Zhen Han, Volker Tresp

    arXiv preprint arXiv:2411.08212

2023

  1. NeurIPS Robustness Multimodal

    Benchmarking robustness of adaptation methods on pre-trained vision-language models

    Shuo Chen, Jindong Gu, Zhen Han, Yunpu Ma, Philip Torr, Volker Tresp

    Conference on Neural Information Processing Systems (NeruIPS)

  2. arXiv Multimodal Prompting

    A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

    Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, Philip Torr

    arXiv preprint arXiv:2307.12980

2022

  1. arXiv

    Social Networks are Divulging Your Identity behind Crypto Addresses

    Shuo Chen, Shaikh Muhammad Uzair Norman

    arXiv preprint