{"total":117,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"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":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2112.10327","title":"Classifier Calibration: A survey on how to assess and improve predicted class probabilities","created":"2021-12-20","cited_by_count":73,"area":null},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71,"area":null},{"id":"2106.15728","title":"Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles","created":"2021-06-29","cited_by_count":54,"area":null},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","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":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","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":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2304.01910","title":"On the Variance of Neural Network Training with respect to Test Sets and Distributions","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","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":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"area":null},{"id":"2310.14586","title":"GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels","created":"2023-10-23","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":"2109.11126","title":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels","created":"2021-09-23","cited_by_count":16,"area":null},{"id":"2202.01851","title":"A Note on \"Assessing Generalization of SGD via Disagreement\"","created":"2022-02-03","cited_by_count":16,"area":null},{"id":"2205.12702","title":"Detecting Label Errors by using Pre-Trained Language Models","created":"2022-05-25","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":"2404.00498","title":"94% on CIFAR-10 in 3.29 Seconds on a Single GPU","created":"2024-03-30","cited_by_count":16,"area":null},{"id":"2303.15488","title":"On the Importance of Feature Separability in Predicting Out-Of-Distribution Error","created":"2023-03-27","cited_by_count":15,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"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":"2306.08893","title":"LOVM: Language-Only Vision Model Selection","created":"2023-06-15","cited_by_count":12,"area":"mllm"},{"id":"2407.16067","title":"LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2205.13577","title":"Understanding new tasks through the lens of training data via exponential tilting","created":"2022-05-26","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":"2507.08721","title":"Monitoring Risks in Test-Time Adaptation","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2205.15947","title":"Evaluating Robustness to Dataset Shift via Parametric Robustness Sets","created":"2022-05-31","cited_by_count":10,"area":null},{"id":"2201.11676","title":"Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap","created":"2022-01-27","cited_by_count":9,"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":"2401.08348","title":"Estimating Model Performance Under Covariate Shift Without Labels","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2404.01351","title":"AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2310.05833","title":"A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2407.08649","title":"Confidence-based Estimators for Predictive Performance in Model Monitoring","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2206.01515","title":"Understanding Deep Learning via Decision Boundary","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2310.14814","title":"Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","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":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2111.14212","title":"On Predicting Generalization using GANs","created":"2021-11-28","cited_by_count":6,"area":null},{"id":"2306.00169","title":"Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2311.02940","title":"The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning","created":"2023-11-06","cited_by_count":6,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"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":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2207.04185","title":"Domain Alignment Meets Fully Test-Time Adaptation","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2207.09408","title":"Bounding generalization error with input compression: An empirical study with infinite-width networks","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2304.08288","title":"Toward Auto-evaluation with Confidence-based Category Relation-aware Regression","created":"2023-04-17","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":"2312.16313","title":"Unraveling the Key Components of OOD Generalization via Diversification","created":"2023-12-26","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2501.19032","title":"Error Slice Discovery via Manifold Compactness","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","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":"2210.04166","title":"Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2307.10062","title":"Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2310.17044","title":"Learning to Rank for Active Learning via Multi-Task Bilevel Optimization","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2407.12996","title":"Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2410.02384","title":"Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors","created":"2024-10-03","cited_by_count":3,"area":null},{"id":"2505.13900","title":"New Evidence of the Two-Phase Learning Dynamics of Neural Networks","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2205.09809","title":"Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2210.12061","title":"Validation of Composite Systems by Discrepancy Propagation","created":"2022-10-21","cited_by_count":2,"area":null},{"id":"2308.07223","title":"Distance Matters For Improving Performance Estimation Under Covariate Shift","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2309.05619","title":"Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2410.05980","title":"Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2505.05295","title":"Performance Estimation in Binary Classification Using Calibrated Confidence","created":"2025-05-08","cited_by_count":2,"area":null},{"id":"2505.11380","title":"On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.17968","title":"h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2605.12803","title":"Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2310.09250","title":"It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2311.09422","title":"Predicting generalization performance with correctness discriminators","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2312.08033","title":"Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2408.02209","title":"Source-Free Domain-Invariant Performance Prediction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2408.09015","title":"AdaRank: Disagreement Based Module Rank Prediction for Low-rank Adaptation","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2505.07023","title":"Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2506.04690","title":"Towards Better Generalization via Distributional Input Projection Network","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2507.19408","title":"On Arbitrary Predictions from Equally Valid Models","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2510.02956","title":"Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2602.23360","title":"Model Agreement via Anchoring","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.06335","title":"Bridging Domain Expertise and Generalization for Performance Estimation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2211.12016","title":"Variation-based Cause Effect Identification","created":"2022-11-22","cited_by_count":0,"area":null}],"next_cursor":"100"}