{"total":73,"rows":[{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714,"area":null},{"id":"2308.07707","title":"Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening","created":"2023-08-15","cited_by_count":181,"area":"safety"},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2310.02664","title":"On Memorization in Diffusion Models","created":"2023-10-04","cited_by_count":125,"area":"diffusion"},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108,"area":null},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69,"area":null},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60,"area":null},{"id":"2206.08009","title":"Balancing Discriminability and Transferability for Source-Free Domain Adaptation","created":"2022-06-16","cited_by_count":58,"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":"2307.05831","title":"Memorization Through the Lens of Curvature of Loss Function Around Samples","created":"2023-07-11","cited_by_count":27,"area":null},{"id":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2302.11346","title":"Task-Aware Information Routing from Common Representation Space in Lifelong Learning","created":"2023-02-14","cited_by_count":22,"area":null},{"id":"2108.12006","title":"When and how epochwise double descent happens","created":"2021-08-26","cited_by_count":21,"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":"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":"2502.08009","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2210.15909","title":"Subsidiary Prototype Alignment for Universal Domain Adaptation","created":"2022-10-28","cited_by_count":17,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2204.08624","title":"Topology and geometry of data manifold in deep learning","created":"2022-04-19","cited_by_count":12,"area":null},{"id":"2307.09048","title":"FedDefender: Client-Side Attack-Tolerant Federated Learning","created":"2023-07-18","cited_by_count":12,"area":null},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2510.02833","title":"Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs","created":"2025-10-03","cited_by_count":10,"area":"alignment"},{"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":"2503.18114","title":"Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry","created":"2025-03-23","cited_by_count":9,"area":null},{"id":"2106.11486","title":"Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification","created":"2021-06-22","cited_by_count":7,"area":null},{"id":"2202.04287","title":"Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation","created":"2022-02-09","cited_by_count":7,"area":null},{"id":"2210.05330","title":"Label Noise-Robust Learning using a Confidence-Based Sieving Strategy","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2310.05337","title":"What do larger image classifiers memorise?","created":"2023-10-09","cited_by_count":6,"area":null},{"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":"2305.14576","title":"Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2306.03406","title":"Deep neural networks architectures from the perspective of manifold learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2410.13792","title":"Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2505.20435","title":"The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology","created":"2025-05-26","cited_by_count":5,"area":"safety"},{"id":"2212.11680","title":"Smooth Sailing: Improving Active Learning for Pre-trained Language Models with Representation Smoothness Analysis","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2305.05208","title":"Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2312.14285","title":"Probing Biological and Artificial Neural Networks with Task-dependent Neural Manifolds","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2404.14265","title":"Deep Learning as Ricci Flow","created":"2024-04-22","cited_by_count":4,"area":null},{"id":"2502.17771","title":"Sample Selection via Contrastive Fragmentation for Noisy Label Regression","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2602.00084","title":"Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2210.06709","title":"Categorizing Semantic Representations for Neural Machine Translation","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2304.02223","title":"Local Intrinsic Dimensional Entropy","created":"2023-04-05","cited_by_count":2,"area":null},{"id":"2410.04144","title":"ConDa: Fast Federated Unlearning with Contribution Dampening","created":"2024-10-05","cited_by_count":2,"area":"safety"},{"id":"2603.01879","title":"Diagnosing Generalization Failures from Representational Geometry Markers","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2605.27078","title":"Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2201.06274","title":"Detecting danger in gridworlds using Gromov's Link Condition","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2210.01869","title":"Memory in humans and deep language models: Linking hypotheses for model augmentation","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2502.01360","title":"A Quotient Homology Theory of Representation in Neural Networks","created":"2025-02-03","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":"2602.02296","title":"Decoupling Generalizability and Membership Privacy Risks in Neural Networks","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.20338","title":"Emergent Manifold Separability during Reasoning in Large Language Models","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2603.19865","title":"On the Dynamics & Transferability of Latent Generalization during Memorization","created":"2026-03-20","cited_by_count":1,"area":"mechinterp"},{"id":"2605.24420","title":"Batch Normalization Amplifies Memorization and Privacy Risks","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2609.08561","title":"Certified Topological Interaction in Neural Representations: Exact Tests and the Statistic They Require","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2201.11939","title":"With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2308.00858","title":"Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2407.21159","title":"Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models","created":"2024-07-30","cited_by_count":0,"area":"diffusion"},{"id":"2408.16031","title":"EMP: Enhance Memory in Data Pruning","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2410.00772","title":"On the Generalization and Causal Explanation in Self-Supervised Learning","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2504.17449","title":"HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.06597","title":"Phase Transitions between Accuracy Regimes in L2 regularized Deep Neural Networks","created":"2025-05-10","cited_by_count":0,"area":null},{"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":"2601.10084","title":"Adaptive Label Error Detection: A Bayesian Approach to Mislabeled Data Detection","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.05748","title":"LeakBoost: Perceptual-Loss-Based Membership Inference Attack","created":"2026-02-05","cited_by_count":0,"area":"safety"},{"id":"2602.17088","title":"MeGU: Machine-Guided Unlearning with Target Feature Disentanglement","created":"2026-02-19","cited_by_count":0,"area":"safety"},{"id":"2605.13148","title":"Understanding Generalization through Decision Pattern Shift","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.18676","title":"InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.15632","title":"Sparse Prototype Code Underlies Classification and Prediction Across Modalities","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":null}