PPaperPicks

Shiyao Cui

14 papers at tracked venues · 14 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×9ACM MM ×2SIGIR ×2AAAI ×1

Frequent coauthors

Minlie Huang
×10
Zhexin Zhang
×8
Hongning Wang
×7
Han Qiu
×6
Junxiao Yang
×4
Yida Lu
×4
Tingwen Liu
×4
Victor Shea-Jay Huang
×3
Qinglin Zhang
×3
Renmiao Chen
×3
Xuan Ouyang
×3
Yingkang Wang
×2

Papers

  1. How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
    ACL 2026 ·
    Zhexin Zhang
    ,
    Xian Qi Loye
    ,
    Victor Shea-Jay Huang
    ,
    Junxiao Yang
    ,
    Qi Zhu
    , Shiyao Cui,
    Fei Mi
    ,
    Lifeng Shang
    ,
    Yingkang Wang
    ,
    Hongning Wang
    ,
    Minlie Huang
  2. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
    ACL 2026 ·
    Junxiao Yang
    ,
    Haoran Liu
    ,
    Jinzhe Tu
    ,
    Jiale Cheng
    ,
    Zhexin Zhang
    , Shiyao Cui,
    Jiaqi Weng
    ,
    Jialing Tao
    ,
    Hui Xue
    ,
    Hongning Wang
    ,
    Han Qiu
    ,
    Minlie Huang
  3. New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
    ACL 2026 · Shiyao Cui,
    Qinglin Zhang
    ,
    Di Wang
    ,
    Yida Lu
    ,
    Zhexin Zhang
    ,
    Jinhua Gao
    ,
    Jinglin Yang
    ,
    Min He
    ,
    Han Qiu
    ,
    Minlie Huang
  4. The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
    ACL 2026 ·
    Renmiao Chen
    ,
    Yida Lu
    , Shiyao Cui,
    Xuan Ouyang
    ,
    Victor Shea-Jay Huang
    ,
    Shumin Zhang
    ,
    Chengwei Pan
    ,
    Han Qiu
    ,
    Minlie Huang
  5. When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
    AAAI 2026 · Shiyao Cui,
    Xijia Feng
    ,
    Yingkang Wang
    ,
    Junxiao Yang
    ,
    Zhexin Zhang
    ,
    Biplab Sikdar
    ,
    Hongning Wang
    ,
    Han Qiu
    ,
    Minlie Huang
  6. Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
    ACL 2025 ·
    Shujian Yang
    , Shiyao Cui,
    Chuanrui Hu
    ,
    Haicheng Wang
    ,
    Tianwei Zhang
    ,
    Minlie Huang
    ,
    Jialiang Lu
    ,
    Han Qiu
  7. Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
    ACL 2025 ·
    Junxiao Yang
    ,
    Zhexin Zhang
    , Shiyao Cui,
    Hongning Wang
    ,
    Minlie Huang
  8. JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
    ACM MM 2025 ·
    Renmiao Chen
    , Shiyao Cui,
    Xuancheng Huang
    ,
    Chengwei Pan
    ,
    Victor Shea-Jay Huang
    ,
    Qinglin Zhang
    ,
    Xuan Ouyang
    ,
    Zhexin Zhang
    ,
    Hongning Wang
    ,
    Minlie Huang
  9. LongSafety: Evaluating Long-Context Safety of Large Language Models
    ACL 2025 ·
    Yida Lu
    ,
    Jiale Cheng
    ,
    Zhexin Zhang
    , Shiyao Cui,
    Cunxiang Wang
    ,
    Xiaotao Gu
    ,
    Yuxiao Dong
    ,
    Jie Tang
    ,
    Hongning Wang
    ,
    Minlie Huang
  10. ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLM
    ACM MM 2025 · Shiyao Cui,
    Qinglin Zhang
    ,
    Xuan Ouyang
    ,
    Renmiao Chen
    ,
    Zhexin Zhang
    ,
    Yida Lu
    ,
    Hongning Wang
    ,
    Han Qiu
    ,
    Minlie Huang
  11. Exogenous and Endogenous Data Augmentation for Low-Resource Complex Named Entity Recognition
    SIGIR 2024 ·
    Xinghua Zhang
    ,
    Gaode Chen
    , Shiyao Cui,
    Jiawei Sheng
    ,
    Tingwen Liu
    ,
    Hongbo Xu
  12. Exploring the Trade-Off within Visual Information for MultiModal Sentence Summarization
    SIGIR 2024 ·
    Minghuan Yuan
    , Shiyao Cui,
    Xinghua Zhang
    ,
    Shicheng Wang
    ,
    Hongbo Xu
    ,
    Tingwen Liu
  13. LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion
    ACL 2024 ·
    Yilong Chen
    ,
    Junyuan Shang
    ,
    Zhenyu Zhang
    , Shiyao Cui,
    Tingwen Liu
    ,
    Shuohuan Wang
    ,
    Yu Sun
    ,
    Hua Wu
  14. NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time
    ACL 2024 ·
    Yilong Chen
    ,
    Guoxia Wang
    ,
    Junyuan Shang
    , Shiyao Cui,
    Zhenyu Zhang
    ,
    Tingwen Liu
    ,
    Shuohuan Wang
    ,
    Yu Sun
    ,
    Dianhai Yu
    ,
    Hua Wu