Showing 21–34 of 34 results
/ Date/ Name
Dec 4, 2024Robust Multi-bit Text Watermark with LLM-based ParaphrasersNov 27, 2024SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?Feb 7, 2025Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and BeyondJun 2, 2025Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-TuningOct 1, 2025Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM UnlearningDec 19, 2022TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven OptimizationOct 13, 2023Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer LearningJun 9, 2025BLUR: A Bi-Level Optimization Approach for LLM UnlearningDec 12, 2023Robust MRI Reconstruction by Smoothed Unrolling (SMUG)Jun 4, 2025CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token SchedulingMar 14, 2023SMUG: Towards robust MRI reconstruction by smoothed unrollingJun 25, 2024Leveraging LLMs for Dialogue Quality MeasurementOct 3, 2023DeepZero: Scaling up Zeroth-Order Optimization for Deep Model TrainingMay 24, 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models