Ming Jin

STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning ACL 2026 A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety ICLR 2025 A Dynamic Penalization Framework for Online Rank-1 Semidefinite Programming Relaxations L4DC 2025 DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking NAACL 2025 From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing EMNLP 2025 Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 LLMs Can Plan Only If We Tell Them ICLR 2025 LLMs Can Reason Faster Only If We Let Them ICML 2025 Position: AI Safety Must Embrace an Antifragile Perspective ICML 2025 Retracing the Past: LLMs Emit Training Data When They Get Lost EMNLP 2025 Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning ICLR 2025 Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories EMNLP 2025 T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models IJCAI 2025 TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis ICLR 2025 Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts ICLR 2025 Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement ACL 2025 Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting ICML 2025 Towards Neural Scaling Laws for Time Series Foundation Models ICLR 2025 Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models ICML 2024 Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective NeurIPS 2024 Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation AAAI 2024 Boosting Alignment for Post-Unlearning Text-to-Image Generative Models NeurIPS 2024 Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? EMNLP 2024 Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation NeurIPS 2024 Fairness-Aware Meta-Learning via Nash Bargaining NeurIPS 2024 InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States EMNLP 2024 Pausing Policy Learning in Non-stationary Reinforcement Learning ICML 2024 Position: What Can Large Language Models Tell Us about Time Series Analysis ICML 2024 Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs ACL 2024 The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes CVPR 2024 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models ICLR 2024 A CMDP-within-online framework for Meta-Safe Reinforcement Learning ICLR 2023 LAVA: Data Valuation without Pre-Specified Learning Algorithms ICLR 2023 Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold L4DC 2023 Non-stationary Risk-Sensitive Reinforcement Learning: Near-Optimal Dynamic Regret, Adaptive Detection, and Separation Design AAAI 2023 On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds AAAI 2023 Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study ICCV 2023 Tempo Adaptation in Non-stationary Reinforcement Learning NeurIPS 2023 Towards Robustness Certification Against Universal Perturbations ICLR 2023 Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-Based Guidance AAAI 2023 Adversarial Unlearning of Backdoors via Implicit Hypergradient ICLR 2022 Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs NeurIPS 2022 Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems AAAI 2022 Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning IJCAI 2021 Power up! Robust Graph Convolutional Network via Graph Powering AAAI 2021