Han Qiu

Venues

Frequent coauthors

Papers

1. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
   ACL 2026 ·

   Junxiao Yang

   DBLP profile ↗ORCID search ↗
2. LeakDojo: Decoding the Leakage Threats of RAG Systems
   ACL 2026 ·

   Maosen Zhang

   DBLP profile ↗ORCID search ↗
3. New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
   ACL 2026 ·

   Shiyao Cui

   DBLP profile ↗ORCID search ↗
4. Revisiting the Reliability of Language Models in Instruction-Following
   ACL 2026 ·

   Jianshuo Dong

   DBLP profile ↗ORCID search ↗
5. TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
   ACL 2026 ·

   Axel Delaval

   DBLP profile ↗ORCID search ↗
6. The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
   ACL 2026 ·

   Renmiao Chen

   DBLP profile ↗ORCID search ↗
7. When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
   AAAI 2026 ·

   Shiyao Cui

   DBLP profile ↗ORCID search ↗
8. "I've Decided to Leak": Probing Internals Behind Prompt Leakage Intents
   EMNLP 2025 ·

   Jianshuo Dong

   DBLP profile ↗ORCID search ↗
9. A Benchmark for Semantic Sensitive Information in LLMs Outputs
   ICLR 2025 ·

   Qingjie Zhang

   DBLP profile ↗ORCID search ↗
10. An Engorgio Prompt Makes Large Language Model Babble on
    ICLR 2025 ·

    Jianshuo Dong

    DBLP profile ↗ORCID search ↗
11. Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
    ICML 2025 ·

    Yutong Wu

    DBLP profile ↗ORCID search ↗
12. Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
    ACL 2025 ·

    Shujian Yang

    DBLP profile ↗ORCID search ↗
13. Mask Image Watermarking
    NeurIPS 2025 ·

    Runyi Hu

    DBLP profile ↗ORCID search ↗
14. ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM
    ACM MM 2025 ·

    Shiyao Cui

    DBLP profile ↗ORCID search ↗
15. Speculating LLMs' Chinese Training Data Pollution from Their Tokens
    EMNLP 2025 ·

    Qingjie Zhang

    DBLP profile ↗ORCID search ↗
16. Understanding the Dark Side of LLMs' Intrinsic Self-Correction
    ACL 2025 ·

    Qingjie Zhang

    DBLP profile ↗ORCID search ↗
17. VISO: Accelerating In-Orbit Object Detection with Language-Guided Mask Learning and Sparse Inference
    ICCV 2025 ·

    Meiqi Wang

    DBLP profile ↗ORCID search ↗
18. VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
    ICLR 2025 ·

    Runyi Hu

    DBLP profile ↗ORCID search ↗
19. When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
    EMNLP 2025 ·

    Cheng Wang

    DBLP profile ↗ORCID search ↗
20. COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
    NeurIPS 2024 ·

    Ziyuan Zhang

    DBLP profile ↗ORCID search ↗
21. Course-Correction: Safety Alignment Using Synthetic Preferences
    EMNLP 2024 ·

    Rongwu Xu

    DBLP profile ↗ORCID search ↗
22. Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
    ICML 2024 ·

    Boheng Li

    DBLP profile ↗ORCID search ↗
23. The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
    ACL 2024 ·

    Rongwu Xu

    DBLP profile ↗ORCID search ↗
24. Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
    EMNLP 2024 ·

    Rongwu Xu

    DBLP profile ↗ORCID search ↗
25. You Only Query Once: An Efficient Label-Only Membership Inference Attack
    ICLR 2024 ·

    Yutong Wu

    DBLP profile ↗ORCID search ↗