{"total":146,"rows":[{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"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":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172,"area":null},{"id":"2202.02466","title":"Handling Distribution Shifts on Graphs: An Invariance Perspective","created":"2022-02-05","cited_by_count":164,"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":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2101.01134","title":"Does Invariant Risk Minimization Capture Invariance?","created":"2021-01-04","cited_by_count":116,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2106.04496","title":"Towards a Theoretical Framework of Out-of-Distribution Generalization","created":"2021-06-08","cited_by_count":94,"area":null},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92,"area":null},{"id":"2106.06333","title":"Invariant Information Bottleneck for Domain Generalization","created":"2021-06-11","cited_by_count":86,"area":null},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86,"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":"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":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55,"area":null},{"id":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44,"area":null},{"id":"2102.12353","title":"Nonlinear Invariant Risk Minimization: A Causal Approach","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","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":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"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":"2204.08491","title":"Active Learning Helps Pretrained Models Learn the Intended Task","created":"2022-04-18","cited_by_count":33,"area":null},{"id":"2212.01433","title":"Avoiding spurious correlations via logit correction","created":"2022-12-02","cited_by_count":32,"area":null},{"id":"2106.11905","title":"Dangers of Bayesian Model Averaging under Covariate Shift","created":"2021-06-22","cited_by_count":31,"area":null},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2301.13293","title":"Overcoming Simplicity Bias in Deep Networks using a Feature Sieve","created":"2023-01-30","cited_by_count":29,"area":null},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28,"area":null},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27,"area":null},{"id":"2412.05152","title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","created":"2024-12-06","cited_by_count":25,"area":null},{"id":"2208.09083","title":"Out-of-distribution Detection via Frequency-regularized Generative Models","created":"2022-08-18","cited_by_count":23,"area":null},{"id":"2205.11672","title":"Why does Throwing Away Data Improve Worst-Group Error?","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2307.09933","title":"Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features","created":"2023-07-19","cited_by_count":21,"area":null},{"id":"2504.06969","title":"Towards LLMs Robustness to Changes in Prompt Format Styles","created":"2025-04-09","cited_by_count":21,"area":null},{"id":"2203.07798","title":"Igeood: An Information Geometry Approach to Out-of-Distribution Detection","created":"2022-03-15","cited_by_count":20,"area":null},{"id":"2206.03198","title":"Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow","created":"2022-06-07","cited_by_count":20,"area":null},{"id":"2405.16391","title":"When does compositional structure yield compositional generalization? A kernel theory","created":"2024-05-26","cited_by_count":20,"area":null},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19,"area":null},{"id":"2210.01302","title":"Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation","created":"2022-10-04","cited_by_count":18,"area":null},{"id":"2210.06807","title":"Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors","created":"2022-10-13","cited_by_count":17,"area":null},{"id":"2210.08813","title":"Test-Time Training for Graph Neural Networks","created":"2022-10-17","cited_by_count":17,"area":null},{"id":"2205.15458","title":"Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2210.05247","title":"Training Debiased Subnetworks with Contrastive Weight Pruning","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2105.06791","title":"Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations","created":"2021-05-14","cited_by_count":15,"area":null},{"id":"2211.00184","title":"FL Games: A Federated Learning Framework for Distribution Shifts","created":"2022-10-31","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":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2403.03375","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","created":"2024-03-05","cited_by_count":12,"area":null},{"id":"2404.11341","title":"The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology","created":"2024-04-17","cited_by_count":12,"area":null},{"id":"2406.13371","title":"Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2206.14917","title":"Towards out of distribution generalization for problems in mechanics","created":"2022-06-29","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":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2312.02207","title":"TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation","created":"2023-12-03","cited_by_count":10,"area":null},{"id":"2211.01914","title":"FedGen: Generalizable Federated Learning for Sequential Data","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2305.11615","title":"SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2307.12502","title":"Cross Contrasting Feature Perturbation for Domain Generalization","created":"2023-07-24","cited_by_count":9,"area":null},{"id":"2111.13733","title":"Failure Modes of Domain Generalization Algorithms","created":"2021-11-26","cited_by_count":8,"area":null},{"id":"2209.12172","title":"Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition","created":"2022-09-25","cited_by_count":8,"area":null},{"id":"2210.05248","title":"Self-supervised debiasing using low rank regularization","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2401.14846","title":"Understanding Domain Generalization: A Noise Robustness Perspective","created":"2024-01-26","cited_by_count":8,"area":null},{"id":"2405.18296","title":"Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","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":"2407.04911","title":"Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation","created":"2024-07-06","cited_by_count":7,"area":null},{"id":"2503.18258","title":"Severing Spurious Correlations with Data Pruning","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2103.05137","title":"Contemplating real-world object classification","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2209.08745","title":"Importance Tempering: Group Robustness for Overparameterized Models","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2211.15724","title":"Malign Overfitting: Interpolation Can Provably Preclude Invariance","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2308.11043","title":"Spurious Correlations and Where to Find Them","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2503.07315","title":"Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2111.09190","title":"Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data","created":"2021-11-17","cited_by_count":5,"area":null},{"id":"2307.08187","title":"An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2308.10103","title":"ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2312.03318","title":"Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2403.19950","title":"Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2410.08309","title":"Swing-by Dynamics in Concept Learning and Compositional Generalization","created":"2024-10-10","cited_by_count":5,"area":"diffusion"},{"id":"2605.11134","title":"Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training","created":"2026-05-11","cited_by_count":5,"area":"alignment"},{"id":"2106.07916","title":"Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization","created":"2021-06-15","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":"2303.04635","title":"Diffusing Gaussian Mixtures for Generating Categorical Data","created":"2023-03-08","cited_by_count":4,"area":"diffusion"},{"id":"2307.00667","title":"Morse Neural Networks for Uncertainty Quantification","created":"2023-07-02","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":"2409.04188","title":"Reassessing the Validity of Spurious Correlations Benchmarks","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2201.10460","title":"Conditional entropy minimization principle for learning domain invariant representation features","created":"2022-01-25","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":"2211.08583","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2309.06122","title":"A robust synthetic data generation framework for machine learning in High-Resolution Transmission Electron Microscopy (HRTEM)","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2406.09745","title":"How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2408.14584","title":"DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning","created":"2024-08-26","cited_by_count":3,"area":"diffusion"},{"id":"2409.14637","title":"Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting","created":"2024-09-23","cited_by_count":3,"area":null}],"next_cursor":"100"}