{"total":138,"rows":[{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"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":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205,"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":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"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":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2202.06523","title":"MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts","created":"2022-02-14","cited_by_count":81,"area":null},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"area":null},{"id":"2204.00570","title":"Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-04-01","cited_by_count":67,"area":null},{"id":"2106.03917","title":"Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments","created":"2021-06-07","cited_by_count":66,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"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":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"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":"2102.11203","title":"A Theory of Label Propagation for Subpopulation Shift","created":"2021-02-22","cited_by_count":48,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2204.02683","title":"Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations","created":"2022-04-06","cited_by_count":44,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2405.02363","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","created":"2024-05-03","cited_by_count":44,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2207.09504","title":"Invariant Feature Learning for Generalized Long-Tailed Classification","created":"2022-07-19","cited_by_count":34,"area":null},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"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":"2103.10994","title":"Self-Supervised Classification Network","created":"2021-03-19","cited_by_count":28,"area":null},{"id":"2106.03783","title":"An Information-theoretic Approach to Distribution Shifts","created":"2021-06-07","cited_by_count":25,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2402.10099","title":"Any-Shift Prompting for Generalization over Distributions","created":"2024-02-15","cited_by_count":24,"area":null},{"id":"2211.09359","title":"How to Fine-Tune Vision Models with SGD","created":"2022-11-17","cited_by_count":23,"area":null},{"id":"2307.09520","title":"Adversarial Bayesian Augmentation for Single-Source Domain Generalization","created":"2023-07-18","cited_by_count":22,"area":null},{"id":"2106.08537","title":"Clustering Mixture Models in Almost-Linear Time via List-Decodable Mean Estimation","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2310.12964","title":"PAC Prediction Sets Under Label Shift","created":"2023-10-19","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":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","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":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2406.11608","title":"Visually Consistent Hierarchical Image Classification","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2412.01023","title":"Learning Structured Representations with Hyperbolic Embeddings","created":"2024-12-02","cited_by_count":16,"area":null},{"id":"2403.10175","title":"A Short Survey on Importance Weighting for Machine Learning","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2205.00504","title":"Domain Adaptation meets Individual Fairness. And they get along","created":"2022-05-01","cited_by_count":13,"area":null},{"id":"2306.11035","title":"Adversarial Training Should Be Cast as a Non-Zero-Sum Game","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2208.10967","title":"The Value of Out-of-Distribution Data","created":"2022-08-23","cited_by_count":12,"area":null},{"id":"2209.09120","title":"A Closer Look at Novel Class Discovery from the Labeled Set","created":"2022-09-19","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":"2205.12753","title":"An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation","created":"2022-05-25","cited_by_count":11,"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":"2403.12777","title":"Discover and Mitigate Multiple Biased Subgroups in Image Classifiers","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2404.10980","title":"Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty","created":"2024-04-17","cited_by_count":11,"area":null},{"id":"2405.10053","title":"SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2206.01986","title":"Delving into the Openness of CLIP","created":"2022-06-04","cited_by_count":10,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2302.05441","title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features","created":"2023-02-10","cited_by_count":10,"area":null},{"id":"2111.14806","title":"Coarse-To-Fine Incremental Few-Shot Learning","created":"2021-11-24","cited_by_count":9,"area":null},{"id":"2203.08644","title":"Context-Aware Drift Detection","created":"2022-03-16","cited_by_count":9,"area":null},{"id":"2211.15762","title":"Understanding the Impact of Adversarial Robustness on Accuracy Disparity","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2304.05727","title":"Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2310.00164","title":"PRIME: Prioritizing Interpretability in Failure Mode Extraction","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2503.09487","title":"Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2204.11122","title":"Can domain adaptation make object recognition work for everyone?","created":"2022-04-23","cited_by_count":8,"area":null},{"id":"2311.11019","title":"Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels","created":"2023-11-18","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":"2512.25034","title":"Generative Classifiers Avoid Shortcut Solutions","created":"2025-12-31","cited_by_count":8,"area":null},{"id":"2103.00259","title":"Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition","created":"2021-02-27","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":"2403.00194","title":"Ask Your Distribution Shift if Pre-Training is Right for You","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2107.06217","title":"What classifiers know what they don't?","created":"2021-07-13","cited_by_count":6,"area":null},{"id":"2307.13381","title":"Scaff-PD: Communication Efficient Fair and Robust Federated Learning","created":"2023-07-25","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":"2411.06966","title":"Robust Fine-tuning of Zero-shot Models via Variance Reduction","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2501.06669","title":"Challenging reaction prediction models to generalize to novel chemistry","created":"2025-01-11","cited_by_count":6,"area":null},{"id":"2202.01671","title":"Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2205.07315","title":"Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2205.11473","title":"Rethinking Streaming Machine Learning Evaluation","created":"2022-05-23","cited_by_count":5,"area":null},{"id":"2207.01059","title":"Identifying the Context Shift between Test Benchmarks and Production Data","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2211.08722","title":"Learning with Noisy Labels over Imbalanced Subpopulations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2304.11072","title":"An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph","created":"2023-04-17","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2307.06457","title":"Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective","created":"2023-07-12","cited_by_count":5,"area":null},{"id":"2307.14729","title":"Understanding Silent Failures in Medical Image Classification","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2407.01316","title":"Evaluating Model Performance Under Worst-case Subpopulations","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2306.03648","title":"Supervised Knowledge May Hurt Novel Class Discovery Performance","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2310.08677","title":"GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2402.02851","title":"Enhancing Compositional Generalization via Compositional Feature Alignment","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2409.04188","title":"Reassessing the Validity of Spurious Correlations Benchmarks","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2507.07780","title":"Where are we with calibration under dataset shift in image classification?","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2111.12922","title":"Clustering Effect of (Linearized) Adversarial Robust Models","created":"2021-11-25","cited_by_count":3,"area":null},{"id":"2112.10844","title":"Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift","created":"2021-12-20","cited_by_count":3,"area":null},{"id":"2205.09891","title":"Interpolating Compressed Parameter Subspaces","created":"2022-05-19","cited_by_count":3,"area":null}],"next_cursor":"100"}