{"total":97,"rows":[{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2203.17260","title":"Generating High Fidelity Data from Low-density Regions using Diffusion Models","created":"2022-03-31","cited_by_count":78,"area":"diffusion"},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2207.10384","title":"Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing","created":"2022-07-21","cited_by_count":52,"area":null},{"id":"2111.12621","title":"Accelerating Deep Learning with Dynamic Data Pruning","created":"2021-11-24","cited_by_count":43,"area":null},{"id":"2311.13613","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","created":"2023-11-22","cited_by_count":38,"area":null},{"id":"2301.12334","title":"Don't Play Favorites: Minority Guidance for Diffusion Models","created":"2023-01-29","cited_by_count":37,"area":"diffusion"},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2301.00930","title":"Data Valuation Without Training of a Model","created":"2023-01-03","cited_by_count":35,"area":null},{"id":"2205.13323","title":"The Effect of Task Ordering in Continual Learning","created":"2022-05-26","cited_by_count":31,"area":null},{"id":"2407.15811","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","created":"2024-07-22","cited_by_count":30,"area":"diffusion"},{"id":"2603.11178","title":"PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence","created":"2026-03-11","cited_by_count":28,"area":"distill"},{"id":"2209.10015","title":"Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics","created":"2022-09-20","cited_by_count":26,"area":null},{"id":"2310.16981","title":"Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"id":"2205.10439","title":"How Useful are Gradients for OOD Detection Really?","created":"2022-05-20","cited_by_count":20,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","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":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"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":"2310.02832","title":"Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness","created":"2023-10-04","cited_by_count":15,"area":null},{"id":"2406.00060","title":"Cascade-Aware Training of Language Models","created":"2024-05-29","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":"2401.01867","title":"Dataset Difficulty and the Role of Inductive Bias","created":"2024-01-03","cited_by_count":12,"area":null},{"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":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2405.19462","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2212.09206","title":"Segmentation Ability Map: Interpret deep features for medical image segmentation","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2301.04850","title":"Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure","created":"2023-01-12","cited_by_count":9,"area":null},{"id":"2310.08866","title":"Adaptivity and Modularity for Efficient Generalization Over Task Complexity","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2404.03784","title":"A Layer Selection Approach to Test Time Adaptation","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2411.00999","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2501.16614","title":"FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning","created":"2025-01-28","cited_by_count":7,"area":"safety"},{"id":"2304.01401","title":"U-Netmer: U-Net meets Transformer for medical image segmentation","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2310.18970","title":"TRIAGE: Characterizing and auditing training data for improved regression","created":"2023-10-29","cited_by_count":6,"area":null},{"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":"2311.16298","title":"Influence Scores at Scale for Efficient Language Data Sampling","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2108.06217","title":"Beyond Fairness Metrics: Roadblocks and Challenges for Ethical AI in Practice","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2201.05610","title":"When less is more: Simplifying inputs aids neural network understanding","created":"2022-01-14","cited_by_count":4,"area":null},{"id":"2205.07427","title":"Exploring the Learning Difficulty of Data Theory and Measure","created":"2022-05-16","cited_by_count":4,"area":null},{"id":"2211.09113","title":"On Measuring the Intrinsic Few-Shot Hardness of Datasets","created":"2022-11-16","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2402.00853","title":"LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2410.00759","title":"Targeted synthetic data generation for tabular data via hardness characterization","created":"2024-10-01","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":"2504.20902","title":"Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2203.15100","title":"Understanding out-of-distribution accuracies through quantifying difficulty of test samples","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2305.02942","title":"Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2406.13733","title":"You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2407.05973","title":"Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2302.01440","title":"Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications","created":"2023-02-02","cited_by_count":2,"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":"2405.09600","title":"Aggregate Representation Measure for Predictive Model Reusability","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2406.04892","title":"Sexism Detection on a Data Diet","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2501.14551","title":"Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation","created":"2025-01-24","cited_by_count":2,"area":null},{"id":"2506.23881","title":"Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2508.07066","title":"Membership Inference Attacks with False Discovery Rate Control","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2605.28631","title":"Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2203.09829","title":"Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2304.04222","title":"CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement","created":"2023-04-09","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":"2409.09196","title":"Are Sparse Neural Networks Better Hard Sample Learners?","created":"2024-09-13","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":"2507.00038","title":"Quality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information","created":"2025-06-19","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":"2601.07224","title":"Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration","created":"2026-01-12","cited_by_count":1,"area":"agents"},{"id":"2301.06928","title":"Towards Estimating Transferability using Hard Subsets","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2302.01243","title":"Human not in the loop: objective sample difficulty measures for Curriculum Learning","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2305.16583","title":"Detecting Errors in a Numerical Response via any Regression Model","created":"2023-05-26","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":"2404.16917","title":"Grad Queue : A probabilistic framework to reinforce sparse gradients","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2412.15511","title":"RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2501.09101","title":"Relation U-Net","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2504.07031","title":"Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling","created":"2025-04-09","cited_by_count":0,"area":null},{"id":"2506.11615","title":"Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments","created":"2025-06-13","cited_by_count":0,"area":"safety"},{"id":"2506.14203","title":"Intended Target Identification for Anomia Patients with Gradient-based Selective Augmentation","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.06896","title":"Are Targeted Data Poisoning Attacks as Effective as We Think?","created":"2025-09-08","cited_by_count":0,"area":"safety"},{"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":"2509.26242","title":"Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.09190","title":"Gradient Residual Connections","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.11533","title":"AltTS: A Dual-Path Framework with Alternating Optimization for Multivariate Time Series Forecasting","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.19907","title":"Gradient based Severity Labeling for Biomarker Classification in OCT","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.20720","title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","created":"2026-04-22","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":"2605.24680","title":"Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.12251","title":"Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2608.04147","title":"LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}