{"total":56,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2202.02794","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","created":"2022-02-06","cited_by_count":133,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2208.14933","title":"Membership Inference Attacks by Exploiting Loss Trajectory","created":"2022-08-31","cited_by_count":101,"area":"safety"},{"id":"2311.11908","title":"Continual Learning: Applications and the Road Forward","created":"2023-11-20","cited_by_count":59,"area":null},{"id":"2202.05656","title":"Evaluation of post-hoc interpretability methods in time-series classification","created":"2022-02-11","cited_by_count":53,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36,"area":null},{"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":"2302.00457","title":"Simplicity Bias in 1-Hidden Layer Neural Networks","created":"2023-02-01","cited_by_count":26,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2305.01604","title":"The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold","created":"2023-05-02","cited_by_count":21,"area":null},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2402.07891","title":"Label-Efficient Model Selection for Text Generation","created":"2024-02-12","cited_by_count":19,"area":null},{"id":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2306.03543","title":"How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget","created":"2023-06-06","cited_by_count":17,"area":null},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"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":"2105.08997","title":"When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics","created":"2021-05-19","cited_by_count":11,"area":null},{"id":"2205.12528","title":"LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2306.08590","title":"Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2212.00261","title":"Task Discovery: Finding the Tasks that Neural Networks Generalize on","created":"2022-12-01","cited_by_count":9,"area":null},{"id":"2212.09321","title":"Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","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":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","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":"2312.16313","title":"Unraveling the Key Components of OOD Generalization via Diversification","created":"2023-12-26","cited_by_count":4,"area":null},{"id":"2409.02228","title":"Unforgettable Generalization in Language Models","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2106.11424","title":"HODA: Hardness-Oriented Detection of Model Extraction Attacks","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2204.08601","title":"A Tour of Visualization Techniques for Computer Vision Datasets","created":"2022-04-19","cited_by_count":3,"area":null},{"id":"2210.00583","title":"The Dynamic of Consensus in Deep Networks and the Identification of Noisy Labels","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","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":"2310.11077","title":"United We Stand: Using Epoch-wise Agreement of Ensembles to Combat Overfit","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2511.19536","title":"AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents","created":"2025-11-24","cited_by_count":2,"area":"agents"},{"id":"2602.03344","title":"Robustness as an Emergent Property of Task Performance","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2103.00147","title":"Statistical Measures For Defining Curriculum Scoring Function","created":"2021-02-27","cited_by_count":1,"area":null},{"id":"2211.07959","title":"The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2505.08915","title":"An Analytical Characterization of Sloppiness in Neural Networks: Insights from Linear Models","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2111.02732","title":"When Neural Networks Using Different Sensors Create Similar Features","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2311.12337","title":"Do Smaller Language Models Answer Contextualised Questions Through Memorisation Or Generalisation?","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2604.11508","title":"Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.16332","title":"Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning","created":"2026-03-12","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":"2609.17846","title":"PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"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},{"id":"2610.02491","title":"What Does a Token Cost? A Mixture-of-Agents Measurement of Sufficient Per-Token Compute","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}