Zekun Li

Venues

Frequent coauthors

Papers

1. Can Editing LLMs Inject Harm?
   AAAI 2026 ·

   Canyu Chen

   DBLP profile ↗ORCID search ↗
2. T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search
   AAAI 2026 ·

   Xing Cui

   DBLP profile ↗ORCID search ↗
3. WildSci: Advancing Scientific Reasoning from In-the-Wild Literature
   ACL 2026 ·

   Tengxiao Liu

   DBLP profile ↗ORCID search ↗
4. Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate
   ICLR 2025 ·

   Yexiang Liu

   DBLP profile ↗ORCID search ↗
5. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
   ICLR 2025 ·

   Xuannan Liu

   DBLP profile ↗ORCID search ↗
6. SpineBench: Benchmarking Multimodal LLMs for Spinal Pathology Analysis
   ACM MM 2025 ·

   Chenghanyu Zhang

   DBLP profile ↗ORCID search ↗
7. Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
   NeurIPS 2025 ·

   Xuannan Liu

   DBLP profile ↗ORCID search ↗
8. Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection
   EMNLP 2024 · Zekun Li
9. FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
   ACM MM 2024 ·

   Xuannan Liu

   DBLP profile ↗ORCID search ↗
10. INSTASTYLE: Inversion Noise of a Stylized Image is Secretly a Style Adviser
    ECCV 2024 ·

    Xing Cui

    DBLP profile ↗ORCID search ↗
11. Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
    ACL 2024 · Zekun Li
12. Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
    NeurIPS 2024 ·

    Xing Cui

    DBLP profile ↗ORCID search ↗