{"total":49,"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":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220,"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":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2103.03571","title":"Cycle Self-Training for Domain Adaptation","created":"2021-03-05","cited_by_count":120,"area":null},{"id":"2207.09640","title":"Test-Time Adaptation via Conjugate Pseudo-labels","created":"2022-07-20","cited_by_count":98,"area":null},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2106.06600","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","created":"2021-06-11","cited_by_count":71,"area":null},{"id":"2203.05818","title":"ZIN: When and How to Learn Invariance Without Environment Partition?","created":"2022-03-11","cited_by_count":58,"area":null},{"id":"2306.09158","title":"Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection","created":"2023-06-15","cited_by_count":57,"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":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2303.10720","title":"Trainable Projected Gradient Method for Robust Fine-tuning","created":"2023-03-19","cited_by_count":37,"area":null},{"id":"2104.12928","title":"If your data distribution shifts, use self-learning","created":"2021-04-27","cited_by_count":36,"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":"2208.14153","title":"Identifying Weight-Variant Latent Causal Models","created":"2022-08-30","cited_by_count":34,"area":null},{"id":"2401.13544","title":"Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2310.17594","title":"SPA: A Graph Spectral Alignment Perspective for Domain Adaptation","created":"2023-10-26","cited_by_count":22,"area":null},{"id":"2106.13805","title":"Self-training Converts Weak Learners to Strong Learners in Mixture Models","created":"2021-06-25","cited_by_count":19,"area":null},{"id":"2503.13868","title":"Out-of-Distribution Generalization in Time Series: A Survey","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2110.08713","title":"Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set","created":"2021-10-17","cited_by_count":12,"area":null},{"id":"2310.10191","title":"VIBE: Topic-Driven Temporal Adaptation for Twitter Classification","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2309.15762","title":"Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2412.13394","title":"Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2105.14210","title":"Exploiting Position Bias for Robust Aspect Sentiment Classification","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2210.10019","title":"Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2207.06687","title":"Breaking Correlation Shift via Conditional Invariant Regularizer","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2311.01420","title":"Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data","created":"2023-11-02","cited_by_count":7,"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":"2111.15513","title":"RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising","created":"2021-11-30","cited_by_count":5,"area":null},{"id":"2405.01389","title":"Invariant Risk Minimization Is A Total Variation Model","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2303.09350","title":"Unsupervised domain adaptation by learning using privileged information","created":"2023-03-16","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":"2402.04644","title":"LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views","created":"2024-02-07","cited_by_count":4,"area":null},{"id":"2502.19665","title":"Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2110.13223","title":"Identifying and Benchmarking Natural Out-of-Context Prediction Problems","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2210.02857","title":"Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2302.05807","title":"Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2403.06424","title":"Bridging Domains with Approximately Shared Features","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2508.05182","title":"SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2208.13433","title":"Towards In-distribution Compatibility in Out-of-distribution Detection","created":"2022-08-29","cited_by_count":0,"area":null},{"id":"2401.03170","title":"Preserving Silent Features for Domain Generalization","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2403.15905","title":"Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2601.22944","title":"Environment-Conditioned Tail Reweighting for Invariant Learning under Mixed Shifts","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00002","title":"Disentangled Interest Network for Out-of-Distribution CTR Prediction","created":"2025-11-14","cited_by_count":0,"area":null}],"next_cursor":null}