{"total":171,"rows":[{"id":"2305.18455","title":"Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models","created":"2023-05-29","cited_by_count":236,"area":"diffusion"},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205,"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":"2403.07366","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","created":"2024-03-12","cited_by_count":106,"area":null},{"id":"2304.09218","title":"Generative models improve fairness of medical classifiers under distribution shifts","created":"2023-04-18","cited_by_count":90,"area":null},{"id":"2206.04046","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","created":"2022-06-08","cited_by_count":85,"area":"moe"},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2306.03536","title":"On Pitfalls of Test-Time Adaptation","created":"2023-06-06","cited_by_count":64,"area":null},{"id":"2311.17055","title":"No Representation Rules Them All in Category Discovery","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58,"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":"2209.08590","title":"RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection","created":"2022-09-18","cited_by_count":52,"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":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"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":"2211.12870","title":"ActMAD: Activation Matching to Align Distributions for Test-Time-Training","created":"2022-11-23","cited_by_count":41,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2211.02843","title":"Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift","created":"2022-11-05","cited_by_count":38,"area":null},{"id":"2212.04196","title":"Learning Domain Invariant Prompt for Vision-Language Models","created":"2022-12-08","cited_by_count":36,"area":"mllm"},{"id":"2206.07837","title":"Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":34,"area":null},{"id":"2207.00012","title":"Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN","created":"2022-06-30","cited_by_count":34,"area":null},{"id":"2201.12919","title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","created":"2022-01-30","cited_by_count":32,"area":null},{"id":"2304.07939","title":"Leveraging sparse and shared feature activations for disentangled representation learning","created":"2023-04-17","cited_by_count":32,"area":null},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2201.12293","title":"Understanding Why Generalized Reweighting Does Not Improve Over ERM","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2402.12971","title":"Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamics","created":"2024-02-20","cited_by_count":27,"area":null},{"id":"2209.09125","title":"Operationalizing Machine Learning: An Interview Study","created":"2022-09-16","cited_by_count":25,"area":null},{"id":"2302.11861","title":"Out-of-Domain Robustness via Targeted Augmentations","created":"2023-02-23","cited_by_count":24,"area":null},{"id":"2301.08834","title":"ManyDG: Many-domain Generalization for Healthcare Applications","created":"2023-01-21","cited_by_count":23,"area":null},{"id":"2405.02797","title":"Adapting to Distribution Shift by Visual Domain Prompt Generation","created":"2024-05-05","cited_by_count":23,"area":null},{"id":"2206.12796","title":"Transferring Fairness under Distribution Shifts via Fair Consistency Regularization","created":"2022-06-26","cited_by_count":21,"area":null},{"id":"2308.16460","title":"Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery","created":"2023-08-31","cited_by_count":21,"area":null},{"id":"2210.07571","title":"Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2210.15212","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","created":"2022-10-27","cited_by_count":20,"area":null},{"id":"2305.15253","title":"Rethinking the Evaluation Protocol of Domain Generalization","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2206.14534","title":"When Does Group Invariant Learning Survive Spurious Correlations?","created":"2022-06-29","cited_by_count":18,"area":null},{"id":"2210.10769","title":"\"Why did the Model Fail?\": Attributing Model Performance Changes to Distribution Shifts","created":"2022-10-19","cited_by_count":18,"area":null},{"id":"2310.13852","title":"Gradual Domain Adaptation: Theory and Algorithms","created":"2023-10-20","cited_by_count":18,"area":null},{"id":"2205.13647","title":"Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"id":"2209.11233","title":"Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts","created":"2022-09-22","cited_by_count":16,"area":null},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16,"area":"moe"},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2302.03679","title":"How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2306.02595","title":"Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","cited_by_count":14,"area":"mllm"},{"id":"2208.03409","title":"DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2304.06813","title":"Unified Out-Of-Distribution Detection: A Model-Specific Perspective","created":"2023-04-13","cited_by_count":13,"area":null},{"id":"2308.07832","title":"REFORMS: Reporting Standards for Machine Learning Based Science","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2407.00502","title":"Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting","created":"2024-06-29","cited_by_count":13,"area":null},{"id":"2408.16757","title":"Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2303.03300","title":"Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach","created":"2023-03-06","cited_by_count":12,"area":null},{"id":"2304.10266","title":"OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2023-04-17","cited_by_count":12,"area":null},{"id":"2310.10696","title":"Robust Collaborative Filtering to Popularity Distribution Shift","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","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":"2302.09344","title":"Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2307.02791","title":"The Role of Subgroup Separability in Group-Fair Medical Image Classification","created":"2023-07-06","cited_by_count":11,"area":null},{"id":"2309.13258","title":"Order-preserving Consistency Regularization for Domain Adaptation and Generalization","created":"2023-09-23","cited_by_count":11,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2301.12351","title":"Emerging Synergies in Causality and Deep Generative Models: A Survey","created":"2023-01-29","cited_by_count":10,"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":"2307.07840","title":"RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks","created":"2023-07-15","cited_by_count":9,"area":null},{"id":"2207.01919","title":"Vector Quantisation for Robust Segmentation","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2301.12993","title":"Benchmarking Robustness to Adversarial Image Obfuscations","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2312.03878","title":"Domain constraints improve risk prediction when outcome data is missing","created":"2023-12-06","cited_by_count":8,"area":null},{"id":"2401.03350","title":"Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks","created":"2024-01-07","cited_by_count":8,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2211.15646","title":"Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with \"Spurious\" Correlations","created":"2022-11-28","cited_by_count":7,"area":null},{"id":"2311.02236","title":"Robust Fine-Tuning of Vision-Language Models for Domain Generalization","created":"2023-11-03","cited_by_count":7,"area":"mllm"},{"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":"2405.08586","title":"Cross-Domain Feature Augmentation for Domain Generalization","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2206.13034","title":"Monitoring Shortcut Learning using Mutual Information","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2211.11513","title":"DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2306.02623","title":"Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2310.17159","title":"MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2503.18695","title":"OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2208.06987","title":"The Causal Structure of Domain Invariant Supervised Representation Learning","created":"2022-08-15","cited_by_count":5,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2211.02400","title":"Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data","created":"2022-11-04","cited_by_count":5,"area":null},{"id":"2307.01166","title":"Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2308.06889","title":"Robustness Stress Testing in Medical Image Classification","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2310.06670","title":"Domain Generalization by Rejecting Extreme Augmentations","created":"2023-10-10","cited_by_count":5,"area":null},{"id":"2312.13842","title":"Statistical learning theory and Occam's razor: The core argument","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2406.09588","title":"Learning Color Equivariant Representations","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2505.04038","title":"Identities are not Interchangeable: The Problem of Overgeneralization in Fair Machine Learning","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2510.22127","title":"Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions","created":"2025-10-25","cited_by_count":5,"area":"mllm"},{"id":"2212.02384","title":"Addressing Distribution Shift at Test Time in Pre-trained Language Models","created":"2022-12-05","cited_by_count":4,"area":null},{"id":"2212.07026","title":"Improving group robustness under noisy labels using predictive uncertainty","created":"2022-12-14","cited_by_count":4,"area":null},{"id":"2308.06668","title":"Large Language Models and Foundation Models in Smart Agriculture: Basics, Opportunities, and Challenges","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2309.00480","title":"Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network","created":"2023-09-01","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":"2312.10083","title":"The Limits of Fair Medical Imaging AI In The Wild","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2405.12217","title":"Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning","created":"2024-05-20","cited_by_count":4,"area":"mllm"},{"id":"2406.11685","title":"Edge Classification on Graphs: New Directions in Topological Imbalance","created":"2024-06-17","cited_by_count":4,"area":null}],"next_cursor":"100"}