Ming Jin

7 papers Griffith University

• Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
• Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL
• DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
• Probing Hidden Knowledge Holes in Unlearned LLMs
• Reinforcement Learning with Backtracking Feedback
• ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models