Sen Su

Venues

Frequent coauthors

Papers

1. DecIF: Improving Instruction-Following through Decomposition
   ACL 2026 ·

   Tingfeng Hui

   DBLP profile ↗ORCID search ↗
2. Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
   SIGKDD 2026 ·

   Longzhu He

   DBLP profile ↗ORCID search ↗
3. From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control
   ACL 2026 ·

   Rui Ha

   DBLP profile ↗ORCID search ↗
4. Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger
   WWW 2026 ·

   Li Sun

   DBLP profile ↗ORCID search ↗
5. Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting
   ACL 2026 ·

   Jinhu Fu

   DBLP profile ↗ORCID search ↗
6. PrivSV: Differentially Private Steering Vector for Large Language Models
   AAAI 2026 ·

   Haocheng Yang

   DBLP profile ↗ORCID search ↗
7. SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models
   ACL 2026 ·

   Yuanhe Zhang

   DBLP profile ↗ORCID search ↗
8. Separating Wheat from Chaff: Fine-Grained Defenses Against Poisoning in Multi-Perspective RAG
   SIGIR 2026 ·

   Yanxiao Zhao

   DBLP profile ↗ORCID search ↗
9. The Devil Within, The Cure Without: Securing Locally Private Graph Learning under Poisoning
   WWW 2026 ·

   Longzhu He

   DBLP profile ↗ORCID search ↗
10. Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
    ACL 2025 ·

    Yuanhe Zhang

    DBLP profile ↗ORCID search ↗
11. DSG-MCTS: A Dynamic Strategy-Guided Monte Carlo Tree Search for Diversified Reasoning in Large Language Models
    EMNLP 2025 ·

    Rui Ha

    DBLP profile ↗ORCID search ↗
12. DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
    EMNLP 2025 ·

    Pengyu Zhu

    DBLP profile ↗ORCID search ↗
13. Going Deeper into Locally Differentially Private Graph Neural Networks
    ICML 2025 ·

    Longzhu He

    DBLP profile ↗ORCID search ↗
14. Knowledge Graph-Driven Memory Editing with Directional Interventions
    EMNLP 2025 ·

    Jinhu Fu

    DBLP profile ↗ORCID search ↗
15. LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
    NeurIPS 2025 ·

    Wei Zhang

    DBLP profile ↗ORCID search ↗
16. PD³F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models
    EMNLP 2025 ·

    Yuanhe Zhang

    DBLP profile ↗ORCID search ↗
17. Residual Stream Analysis of Overfitting And Structural Disruptions
    NeurIPS 2025 ·

    Quan Liu

    DBLP profile ↗ORCID search ↗
18. SecureXGB: A Secure and Efficient Multi-party Protocol for Vertical Federated XGBoost
    SIGMOD 2025 ·

    Zongda Han

    DBLP profile ↗ORCID search ↗
19. Unlocking the Potential of Smaller Language Models as Superior Instruction Evolvers
    CIKM 2025 ·

    Tingfeng Hui

    DBLP profile ↗ORCID search ↗
20. Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
    ACL 2025 ·

    Tingfeng Hui

    DBLP profile ↗ORCID search ↗
21. Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions
    EMNLP 2024 ·

    Quan Liu

    DBLP profile ↗ORCID search ↗
22. Quantifying and Analyzing Entity-Level Memorization in Large Language Models
    AAAI 2024 ·

    Zhenhong Zhou

    DBLP profile ↗ORCID search ↗