Ming Jin

Venues

Frequent coauthors

Papers

1. A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
   ICLR 2025 ·

   Hyunin Lee

   DBLP profile ↗ORCID search ↗
2. DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking
   NAACL 2025 ·

   Hoang Anh Just

   DBLP profile ↗ORCID search ↗
3. Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL
   NeurIPS 2025 ·

   Junyu Guo

   DBLP profile ↗ORCID search ↗
4. From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing
   EMNLP 2025 ·

   Lanxiao Huang

   DBLP profile ↗ORCID search ↗
5. Improving Novel Anomaly Detection with Domain-Invariant Latent Representations
   ECML-PKDD 2025 ·

   Padmaksha Roy

   DBLP profile ↗ORCID search ↗
6. Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
   ICML 2025 ·

   Mahavir Dabas

   DBLP profile ↗ORCID search ↗
7. LLMs Can Plan Only If We Tell Them
   ICLR 2025 ·

   Bilgehan Sel

   DBLP profile ↗ORCID search ↗
8. LLMs Can Reason Faster Only If We Let Them
   ICML 2025 ·

   Bilgehan Sel

   DBLP profile ↗ORCID search ↗
9. Position: AI Safety Must Embrace an Antifragile Perspective
   ICML 2025 · Ming Jin
10. Probing Hidden Knowledge Holes in Unlearned LLMs
    NeurIPS 2025 ·

    Myeongseob Ko

    DBLP profile ↗ORCID search ↗
11. Reinforcement Learning with Backtracking Feedback
    NeurIPS 2025 ·

    Bilgehan Sel

    DBLP profile ↗ORCID search ↗
12. Retracing the Past: LLMs Emit Training Data When They Get Lost
    EMNLP 2025 ·

    Myeongseob Ko

    DBLP profile ↗ORCID search ↗
13. Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
    ICLR 2025 ·

    Shangding Gu

    DBLP profile ↗ORCID search ↗
14. Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
    EMNLP 2025 ·

    Mohammad Beigi

    DBLP profile ↗ORCID search ↗
15. Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
    ICML 2024 ·

    Bilgehan Sel

    DBLP profile ↗ORCID search ↗
16. Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
    AAAI 2024 ·

    Shangding Gu

    DBLP profile ↗ORCID search ↗
17. Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
    NeurIPS 2024 ·

    Myeongseob Ko

    DBLP profile ↗ORCID search ↗
18. Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?
    EMNLP 2024 ·

    Jianfeng He

    DBLP profile ↗ORCID search ↗
19. Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
    NeurIPS 2024 ·

    Shangding Gu

    DBLP profile ↗ORCID search ↗
20. Fairness-Aware Meta-Learning via Nash Bargaining
    NeurIPS 2024 ·

    Yi Zeng

    DBLP profile ↗ORCID search ↗
21. InternalInspector I²: Robust Confidence Estimation in LLMs through Internal States
    EMNLP 2024 ·

    Mohammad Beigi

    DBLP profile ↗ORCID search ↗
22. Pausing Policy Learning in Non-stationary Reinforcement Learning
    ICML 2024 ·

    Hyunin Lee

    DBLP profile ↗ORCID search ↗
23. Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
    ACL 2024 ·

    Bilgehan Sel

    DBLP profile ↗ORCID search ↗
24. The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
    CVPR 2024 ·

    Myeongseob Ko

    DBLP profile ↗ORCID search ↗