{"total":69,"rows":[{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2310.02664","title":"On Memorization in Diffusion Models","created":"2023-10-04","cited_by_count":125,"area":"diffusion"},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2406.02366","title":"Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models","created":"2024-06-04","cited_by_count":37,"area":"diffusion"},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2404.03631","title":"Robust Concept Erasure Using Task Vectors","created":"2024-04-04","cited_by_count":27,"area":null},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2407.02943","title":"PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding","created":"2024-07-03","cited_by_count":24,"area":null},{"id":"2403.09562","title":"PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps","created":"2024-03-14","cited_by_count":23,"area":"safety"},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2501.00961","title":"Uncovering Memorization Effect in the Presence of Spurious Correlations","created":"2025-01-01","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2308.04466","title":"Backdoor Federated Learning by Poisoning Backdoor-Critical Layers","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2406.18566","title":"Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted","created":"2024-06-01","cited_by_count":13,"area":"diffusion"},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2408.04965","title":"Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2408.01228","title":"The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models","created":"2024-08-02","cited_by_count":8,"area":"mllm"},{"id":"2411.19479","title":"FLARE: Toward Universal Dataset Purification against Backdoor Attacks","created":"2024-11-29","cited_by_count":7,"area":null},{"id":"2505.17730","title":"Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data","created":"2025-05-23","cited_by_count":7,"area":"safety"},{"id":"2507.09937","title":"Memorization Sinks: Isolating Memorization during LLM Training","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2412.01528","title":"CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks","created":"2024-12-02","cited_by_count":6,"area":"diffusion"},{"id":"2412.02432","title":"Improved Localized Machine Unlearning Through the Lens of Memorization","created":"2024-12-03","cited_by_count":6,"area":"safety"},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2405.19458","title":"MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection","created":"2024-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2412.11302","title":"Sequence-Level Leakage Risk of Training Data in Large Language Models","created":"2024-12-15","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2410.08557","title":"MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes","created":"2024-10-11","cited_by_count":3,"area":"safety"},{"id":"2412.01014","title":"Detecting Memorization in Large Language Models","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2405.17377","title":"How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2410.08003","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","created":"2024-10-10","cited_by_count":2,"area":"moe"},{"id":"2412.07261","title":"MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2502.05159","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2508.12148","title":"Demystifying Foreground-Background Memorization in Diffusion Models","created":"2025-08-16","cited_by_count":2,"area":"diffusion"},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2603.03335","title":"Compressed Sensing for Capability Localization in Large Language Models","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2606.13873","title":"Natively Unlearnable Large Language Models","created":"2026-06-11","cited_by_count":2,"area":"safety"},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2409.06216","title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2502.06695","title":"FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2503.08633","title":"How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?","created":"2025-03-11","cited_by_count":1,"area":"safety"},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.20095","title":"Spurious Privacy Leakage in Neural Networks","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.15954","title":"One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2508.19352","title":"Memorization in Graph Neural Networks","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.00488","title":"Localizing and Mitigating Memorization in Image Autoregressive Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2510.11372","title":"Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.26560","title":"On Measuring Localization of Shortcuts in Deep Networks","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2605.24420","title":"Batch Normalization Amplifies Memorization and Privacy Risks","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2605.24545","title":"Rethinking Federated Unlearning via the Lens of Memorization","created":"2026-05-23","cited_by_count":1,"area":"safety"},{"id":"2505.17664","title":"What is the role of memorization in Continual Learning?","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.23041","title":"ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation","created":"2025-06-29","cited_by_count":0,"area":"distill"},{"id":"2511.18660","title":"Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2602.22611","title":"Mitigating Membership Inference in Intermediate Representations with Differentially Private Training","created":"2026-02-26","cited_by_count":0,"area":"safety"},{"id":"2605.04231","title":"Anatomy of a failure: When, how, and why deep vision fails in scientific domains","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.18767","title":"Output Vector Editing for Memorization Mitigation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.30081","title":"Discard the Dross and Select the Essential: Pre-query Sample Selection for Black-box Membership Inference Attacks","created":"2026-06-29","cited_by_count":0,"area":"safety"},{"id":"2607.11541","title":"Random Label Prediction Heads for Studying Memorization in Deep Neural Networks","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.04084","title":"SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization","created":"2026-08-04","cited_by_count":0,"area":"moe"},{"id":"2609.17571","title":"Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.34933","title":"Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.17686","title":"Encoding Context into LLM Weights: What Makes It Context?","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}