Mingyu Jin

Venues

Frequent coauthors

Papers

1. SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
   EACL 2026 ·

   Jiaojiao Han

   DBLP profile ↗ORCID search ↗
2. Data-centric NLP Backdoor Defense from the Lens of Memorization
   NAACL 2025 ·

   Zhenting Wang

   DBLP profile ↗ORCID search ↗
3. Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
   ACL 2025 ·

   Wenyue Hua

   DBLP profile ↗ORCID search ↗
4. Disentangling Memory and Reasoning Ability in Large Language Models
   ACL 2025 · Mingyu Jin
5. EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
   NAACL 2025 ·

   Sam Lin

   DBLP profile ↗ORCID search ↗
6. From Commands to Prompts: LLM-based Semantic File System for AIOS
   ICLR 2025 ·

   Zeru Shi

   DBLP profile ↗ORCID search ↗
7. Invisible Backdoor Attack against Self-supervised Learning
   CVPR 2025 ·

   Hanrong Zhang

   DBLP profile ↗ORCID search ↗
8. Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
   ICML 2025 · Mingyu Jin
9. SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
   EMNLP 2025 ·

   Zirui He

   DBLP profile ↗ORCID search ↗
10. Uncertainty Quantification for Multiple-Choice Questions is Just One-Token Deep
    CIKM 2025 ·

    Qingcheng Zeng

    DBLP profile ↗ORCID search ↗
11. Visual Agents as Fast and Slow Thinkers
    ICLR 2025 ·

    Guangyan Sun

    DBLP profile ↗ORCID search ↗
12. Adaptive Axes: A Pipeline for In-domain Social Stereotype Analysis
    EMNLP 2024 ·

    Qingcheng Zeng

    DBLP profile ↗ORCID search ↗
13. BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis
    EMNLP 2024 ·

    Shuhang Lin

    DBLP profile ↗ORCID search ↗
14. Goal-Guided Generative Prompt Injection Attack on Large Language Models
    ICDM 2024 ·

    Chong Zhang

    DBLP profile ↗ORCID search ↗
15. MathAttack: Attacking Large Language Models towards Math Solving Ability
    AAAI 2024 ·

    Zihao Zhou

    DBLP profile ↗ORCID search ↗
16. Target-driven Attack for Large Language Models
    ECAI 2024 ·

    Chong Zhang

    DBLP profile ↗ORCID search ↗
17. The Impact of Reasoning Step Length on Large Language Models
    ACL 2024 · Mingyu Jin
18. TrustAgent: Towards Safe and Trustworthy LLM-based Agents
    EMNLP 2024 ·

    Wenyue Hua

    DBLP profile ↗ORCID search ↗