Jinghan Jia

CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling

Label Smoothing Improves Machine Unlearning

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation

The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Robust Multi-bit Text Watermark with LLM-based Paraphrasers

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

UOE: Unlearning One Expert is Enough for Mixture-of-Experts LLMs

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification