unlearning

A Certified Unlearning Approach without Access to Source Data ICML 2025 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning ICML 2025 Certified Unlearning for Neural Networks ICML 2025 Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization ICML 2025 Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning ICML 2025 Fast Exact Unlearning for In-Context Learning Data for LLMs ICML 2025 GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs ICML 2025 Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning ICML 2025 Large-Scale Training Data Attribution for Music Generative Models via Unlearning NeurIPS 2025 Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025 Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization ICML 2025 NegMerge: Sign-Consensual Weight Merging for Machine Unlearning ICML 2025 Not All Wrong is Bad: Using Adversarial Examples for Unlearning ICML 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 System-Aware Unlearning Algorithms: Use Lesser, Forget Faster ICML 2025 Targeted Unlearning with Single Layer Unlearning Gradient ICML 2025 Textual Unlearning Gives a False Sense of Unlearning ICML 2025 The Space Complexity of Learning-Unlearning Algorithms (extended abstract) COLT 2025 The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning ICLR 2025 Towards flexible perception with visual memory ICML 2025 Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning ICML 2025 Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction MIDL 2024 In-Context Unlearning: Language Models as Few-Shot Unlearners ICML 2024 The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning ICML 2024 To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models ICML 2024