{"total":185,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415,"area":null},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377,"area":null},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104,"area":null},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97,"area":null},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91,"area":null},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90,"area":null},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86,"area":null},{"id":"2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine learning models","created":"2024-03-11","cited_by_count":85,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2306.03536","title":"On Pitfalls of Test-Time Adaptation","created":"2023-06-06","cited_by_count":64,"area":null},{"id":"2106.05961","title":"What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?","created":"2021-06-10","cited_by_count":63,"area":null},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62,"area":null},{"id":"2411.03687","title":"Beyond Model Adaptation at Test Time: A Survey","created":"2024-11-06","cited_by_count":59,"area":null},{"id":"2203.00112","title":"GraphWorld: Fake Graphs Bring Real Insights for GNNs","created":"2022-02-28","cited_by_count":56,"area":null},{"id":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48,"area":null},{"id":"2310.20199","title":"In Search of Lost Online Test-time Adaptation: A Survey","created":"2023-10-31","cited_by_count":44,"area":null},{"id":"2205.10279","title":"Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors","created":"2022-05-20","cited_by_count":43,"area":null},{"id":"2106.12108","title":"Near-Optimal Linear Regression under Distribution Shift","created":"2021-06-23","cited_by_count":42,"area":null},{"id":"2205.10920","title":"Test-Time Robust Personalization for Federated Learning","created":"2022-05-22","cited_by_count":39,"area":null},{"id":"2308.09942","title":"On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion","created":"2023-08-19","cited_by_count":34,"area":null},{"id":"2210.11389","title":"TTTFlow: Unsupervised Test-Time Training with Normalizing Flow","created":"2022-10-20","cited_by_count":33,"area":null},{"id":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2311.08819","title":"Frequency Domain-based Dataset Distillation","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2202.00395","title":"Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2104.08381","title":"Robust Object Detection via Instance-Level Temporal Cycle Confusion","created":"2021-04-16","cited_by_count":24,"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":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22,"area":null},{"id":"2310.12345","title":"ClusT3: Information Invariant Test-Time Training","created":"2023-10-18","cited_by_count":21,"area":null},{"id":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"area":null},{"id":"2312.17162","title":"Function-Space Regularization in Neural Networks: A Probabilistic Perspective","created":"2023-12-28","cited_by_count":20,"area":null},{"id":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","cited_by_count":19,"area":null},{"id":"2309.14531","title":"Pixel-Grounded Prototypical Part Networks","created":"2023-09-25","cited_by_count":18,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2211.15231","title":"Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers","created":"2022-11-28","cited_by_count":17,"area":null},{"id":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2303.08485","title":"Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2408.11839","title":"Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function","created":"2024-08-07","cited_by_count":16,"area":null},{"id":"2302.06637","title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","created":"2023-02-13","cited_by_count":15,"area":null},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2303.01475","title":"Over-training with Mixup May Hurt Generalization","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2311.18807","title":"Pre-registration for Predictive Modeling","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2211.01407","title":"On the Informativeness of Supervision Signals","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2302.06495","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2304.06537","title":"Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2310.04414","title":"CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2311.15990","title":"Should We Learn Most Likely Functions or Parameters?","created":"2023-11-27","cited_by_count":12,"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":"2305.01481","title":"Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2310.04941","title":"Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line","created":"2023-10-07","cited_by_count":11,"area":null},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2103.09947","title":"Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition","created":"2021-03-17","cited_by_count":10,"area":null},{"id":"2306.03962","title":"PILLAR: How to make semi-private learning more effective","created":"2023-06-06","cited_by_count":10,"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":"2102.13189","title":"Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data","created":"2021-02-25","cited_by_count":8,"area":null},{"id":"2204.04372","title":"A Siren Song of Open Source Reproducibility","created":"2022-04-09","cited_by_count":8,"area":null},{"id":"2309.10109","title":"AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation","created":"2023-09-18","cited_by_count":8,"area":null},{"id":"2505.04950","title":"Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2507.23771","title":"Consensus-Driven Active Model Selection","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2104.12231","title":"Model-based metrics: Sample-efficient estimates of predictive model subpopulation performance","created":"2021-04-25","cited_by_count":7,"area":null},{"id":"2108.11801","title":"Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2108.11926","title":"Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2202.12412","title":"Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2211.00527","title":"Self-Supervised Learning with Limited Labeled Data for Prostate Cancer Detection in High Frequency Ultrasound","created":"2022-11-01","cited_by_count":7,"area":null},{"id":"2212.08649","title":"Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2305.02995","title":"Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2409.04707","title":"Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training","created":"2024-09-07","cited_by_count":7,"area":null},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2312.01792","title":"Wild-Tab: A Benchmark For Out-Of-Distribution Generalization In Tabular Regression","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2406.09908","title":"What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2410.04201","title":"IT$^3$: Idempotent Test-Time Training","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2505.20761","title":"Practical estimation of the optimal classification error with soft labels and calibration","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2202.04052","title":"Decision boundaries and convex hulls in the feature space that deep learning functions learn from images","created":"2022-02-05","cited_by_count":5,"area":null},{"id":"2210.17274","title":"Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network","created":"2022-10-28","cited_by_count":5,"area":null},{"id":"2411.06613","title":"Are Neuromorphic Architectures Inherently Privacy-preserving? An Exploratory Study","created":"2024-11-10","cited_by_count":5,"area":null},{"id":"2502.10828","title":"The Vendiscope: An Algorithmic Microscope For Data Collections","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2210.12231","title":"Reducing Training Sample Memorization in GANs by Training with Memorization Rejection","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2304.09758","title":"K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2310.12793","title":"OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2310.13675","title":"On Synthetic Data for Back Translation","created":"2023-10-20","cited_by_count":4,"area":null}],"next_cursor":"100"}