{"total":94,"rows":[{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77,"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":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"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":"2411.13136","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","created":"2024-11-20","cited_by_count":23,"area":"mllm"},{"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":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21,"area":null},{"id":"2310.00116","title":"Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization","created":"2023-09-29","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":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"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":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17,"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":"2307.02460","title":"Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources","created":"2023-07-05","cited_by_count":16,"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":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2307.13136","title":"Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?","created":"2023-07-24","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","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":"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":"2502.13576","title":"Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation","created":"2025-02-19","cited_by_count":12,"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":"2411.17332","title":"On the Generalization of Handwritten Text Recognition Models","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2506.16416","title":"On Continuous Monitoring of Risk Violations under Unknown Shift","created":"2025-06-19","cited_by_count":10,"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":"2406.19049","title":"Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"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":"2302.10341","title":"DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models","created":"2023-02-20","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":"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":"2407.09475","title":"Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2303.08081","title":"Explanation Shift: How Did the Distribution Shift Impact the Model?","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2311.11096","title":"On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation","created":"2023-11-18","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":"2306.04793","title":"On the Joint Interaction of Models, Data, and Features","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2306.11120","title":"Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2412.06461","title":"Ranked from Within: Ranking Large Multimodal Models Without Labels","created":"2024-12-09","cited_by_count":5,"area":"mllm"},{"id":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2308.16274","title":"Learning Diverse Features in Vision Transformers for Improved Generalization","created":"2023-08-30","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":"2312.10083","title":"The Limits of Fair Medical Imaging AI In The Wild","created":"2023-12-11","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":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","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":"2211.08583","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2302.00775","title":"Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2401.10220","title":"AutoFT: Learning an Objective for Robust Fine-Tuning","created":"2024-01-18","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":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"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":"2410.23494","title":"Causality-Driven Audits of Model Robustness","created":"2024-10-30","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":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.12894","title":"LanePerf: a Performance Estimation Framework for Lane Detection","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2209.15618","title":"Beyond Bayes-optimality: meta-learning what you know you don't know","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2310.00873","title":"Deep Neural Networks Tend To Extrapolate Predictably","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2310.05754","title":"Unleashing the power of Neural Collapse for Transferability Estimation","created":"2023-10-09","cited_by_count":1,"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":"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":"2407.14306","title":"Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation","created":"2024-07-19","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":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2412.16739","title":"UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2412.20682","title":"Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks","created":"2024-12-30","cited_by_count":1,"area":"mllm"},{"id":"2506.14978","title":"ODD: Overlap-aware Estimation of Model Performance under Distribution Shift","created":"2025-06-17","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":"2605.08870","title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","created":"2026-05-09","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":"2309.10977","title":"PAGER: A Framework for Failure Analysis of Deep Regression Models","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2411.00328","title":"How many classifiers do we need?","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2503.00563","title":"A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2506.17989","title":"Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddings","created":"2025-06-22","cited_by_count":0,"area":"synth"},{"id":"2507.22776","title":"Label-free estimation of clinically relevant performance metrics under distribution shifts","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2507.23128","title":"Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shifts","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2508.12082","title":"Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2508.19613","title":"ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2606.22054","title":"Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2609.04388","title":"Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.20700","title":"Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.31996","title":"Can Circuit Alignment Predict OOD Generalization?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36569","title":"From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.12397","title":"Prospective Prediction of OOD Degradation from Source-Side Training Dynamics","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}