{"total":93,"rows":[{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105,"area":null},{"id":"2406.01257","title":"What makes unlearning hard and what to do about it","created":"2024-06-03","cited_by_count":89,"area":"safety"},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69,"area":null},{"id":"2310.07931","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","created":"2023-10-11","cited_by_count":69,"area":null},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2301.00930","title":"Data Valuation Without Training of a Model","created":"2023-01-03","cited_by_count":35,"area":null},{"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":"2205.12693","title":"Contrastive Learning with Boosted Memorization","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2209.10015","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","created":"2022-09-20","cited_by_count":26,"area":null},{"id":"2409.13745","title":"Context-Aware Membership Inference Attacks against Pre-trained Large Language Models","created":"2024-09-11","cited_by_count":22,"area":"safety"},{"id":"2502.06905","title":"Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty","created":"2025-02-10","cited_by_count":22,"area":null},{"id":"2203.02485","title":"Better Supervisory Signals by Observing Learning Paths","created":"2022-03-04","cited_by_count":21,"area":"distill"},{"id":"2405.03676","title":"Why is SAM Robust to Label Noise?","created":"2024-05-06","cited_by_count":21,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2206.02617","title":"Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent","created":"2022-06-06","cited_by_count":20,"area":null},{"id":"2107.13098","title":"A Tale Of Two Long Tails","created":"2021-07-27","cited_by_count":19,"area":null},{"id":"2308.13862","title":"Late Stopping: Avoiding Confidently Learning from Mislabeled Examples","created":"2023-08-26","cited_by_count":17,"area":null},{"id":"2308.10888","title":"Unlocking Accuracy and Fairness in Differentially Private Image Classification","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2304.10127","title":"Learning Sample Difficulty from Pre-trained Models for Reliable Prediction","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2103.01338","title":"Acceleration via Fractal Learning Rate Schedules","created":"2021-03-01","cited_by_count":13,"area":null},{"id":"2401.01867","title":"Dataset Difficulty and the Role of Inductive Bias","created":"2024-01-03","cited_by_count":12,"area":null},{"id":"2505.22310","title":"From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization","created":"2025-05-28","cited_by_count":12,"area":"safety"},{"id":"2302.09344","title":"Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2402.18726","title":"Unveiling Privacy, Memorization, and Input Curvature Links","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2207.01145","title":"Memory Population in Continual Learning via Outlier Elimination","created":"2022-07-04","cited_by_count":9,"area":"moe"},{"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":"2303.11114","title":"SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage","created":"2023-03-20","cited_by_count":8,"area":null},{"id":"2406.09935","title":"Predicting the Susceptibility of Examples to Catastrophic Forgetting","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2410.23495","title":"DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity","created":"2024-10-30","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":"2102.09808","title":"Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss","created":"2021-02-19","cited_by_count":6,"area":null},{"id":"2202.07652","title":"Predicting on the Edge: Identifying Where a Larger Model Does Better","created":"2022-02-15","cited_by_count":6,"area":null},{"id":"2207.08525","title":"Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration","created":"2022-07-18","cited_by_count":6,"area":null},{"id":"2307.11525","title":"Model Reporting for Certifiable AI: A Proposal from Merging EU Regulation into AI Development","created":"2023-07-21","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","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":"2401.08808","title":"lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning","created":"2024-01-16","cited_by_count":6,"area":null},{"id":"2412.21197","title":"A Large-Scale Study on Video Action Dataset Condensation","created":"2024-12-30","cited_by_count":6,"area":null},{"id":"2202.08099","title":"Measuring Unintended Memorisation of Unique Private Features in Neural Networks","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2209.09658","title":"Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2306.04793","title":"On the Joint Interaction of Models, Data, and Features","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5,"area":null},{"id":"2410.16516","title":"Scalability of memorization-based machine unlearning","created":"2024-10-21","cited_by_count":5,"area":"safety"},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2406.01757","title":"Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2502.08227","title":"Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2505.18786","title":"Leveraging Per-Instance Privacy for Machine Unlearning","created":"2025-05-24","cited_by_count":4,"area":"safety"},{"id":"2507.03648","title":"Disentangling the Roles of Representation and Selection in Data Pruning","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2604.07962","title":"Is your algorithm unlearning or untraining?","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2106.11424","title":"HODA: Hardness-Oriented Detection of Model Extraction Attacks","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2411.00973","title":"Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2308.01189","title":"Data-Centric Diet: Effective Multi-center Dataset Pruning for Medical Image Segmentation","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2311.02891","title":"AdaFlood: Adaptive Flood Regularization","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2411.01099","title":"Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2412.09765","title":"L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2506.05281","title":"Fast-DataShapley: Neural Modeling for Training Data Valuation","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2508.15475","title":"Influence-driven Curriculum Learning for Pre-training on Limited Data","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.24262","title":"UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2205.10079","title":"Unintended memorisation of unique features in neural networks","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2312.10105","title":"SeiT++: Masked Token Modeling Improves Storage-efficient Training","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2410.15772","title":"Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmark","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2505.15303","title":"Laplace Sample Information: Data Informativeness Through a Bayesian Lens","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2512.24991","title":"Efficiently Estimating Data Efficiency for Language Model Fine-tuning","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2602.03586","title":"APEX: Probing Neural Networks via Activation Perturbation","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2108.03913","title":"Unified Regularity Measures for Sample-wise Learning and Generalization","created":"2021-08-09","cited_by_count":0,"area":null},{"id":"2203.08174","title":"Towards understanding deep learning with the natural clustering prior","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2207.03571","title":"A Study on the Predictability of Sample Learning Consistency","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2311.07864","title":"Probing clustering in neural network representations","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2408.07243","title":"Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2409.00284","title":"Reframing Data Value for Large Language Models Through the Lens of Plausibility","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2503.13058","title":"Do Vision Models Develop Human-Like Progressive Difficulty Understanding?","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2503.15060","title":"Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2506.04047","title":"On Support Samples of Next Word Prediction","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.20463","title":"Efficiently Attacking Memorization Scores","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2509.20786","title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.24477","title":"Performance-Efficiency Trade-off for Fashion Image Retrieval","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.02738","title":"Calibration improves detection of mislabeled examples","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.15276","title":"SNAP: Low-Latency Test-Time Adaptation with Sparse Updates","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2602.20114","title":"Benchmarking Unlearning for Vision Transformers","created":"2026-02-23","cited_by_count":0,"area":"safety"},{"id":"2603.13761","title":"Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning","created":"2026-03-14","cited_by_count":0,"area":null},{"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":"2606.21916","title":"Data Pruning: Redundant, Problematic, and Interdependent Samples","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2610.00221","title":"Useful to Whom? The Easy-versus-Coverage Boundary Moves with the Learner","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}