Shuai Zhao

Venues

Frequent coauthors

Papers

1. DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
   AAAI 2026 ·

   Man Hu

   DBLP profile ↗ORCID search ↗
2. From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning
   AAAI 2026 ·

   Yichao Feng

   DBLP profile ↗ORCID search ↗
3. P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
   ACL 2026 · Shuai Zhao
4. Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
   ACL 2026 ·

   Man Hu

   DBLP profile ↗ORCID search ↗
5. Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
   ACL 2026 ·

   Huimin Xu

   DBLP profile ↗ORCID search ↗
6. AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge
   ACL 2025 ·

   Xiaobao Wu

   DBLP profile ↗ORCID search ↗
7. Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation
   NAACL 2025 ·

   Cong-Duy T. Nguyen

   DBLP profile ↗ORCID search ↗
8. T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
   CVPR 2025 ·

   Yifei Qian

   DBLP profile ↗ORCID search ↗
9. Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education
   ACL 2025 ·

   Yanhao Jia

   DBLP profile ↗ORCID search ↗
10. Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
    ACL 2025 · Shuai Zhao
11. Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
    NAACL 2024 · Shuai Zhao
12. Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
    EMNLP 2024 · Shuai Zhao