Jianing Zhu

Decoupling the Class Label and the Target Concept in Machine Unlearning

Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models

Towards Understanding Valuable Preference Data for Large Language Model Alignment

On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model

Bilateral Information-aware Test-time Adaptation for Vision-Language Models

Sequence Length Matters in Data Scheduling for Accelerating Language Model Pretraining

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Fine-tuning and Prompt-based Attacks

Decoupling the Class Label and the Target Concept in Machine Unlearning

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Nested Gloss Makes Large Language Models Lost