{"total":120,"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":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2106.11230","title":"Can contrastive learning avoid shortcut solutions?","created":"2021-06-21","cited_by_count":114,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"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":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2111.00898","title":"Availability Attacks Create Shortcuts","created":"2021-11-01","cited_by_count":62,"area":null},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59,"area":null},{"id":"2110.03095","title":"Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"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":"2110.14189","title":"Robust Contrastive Learning Using Negative Samples with Diminished Semantics","created":"2021-10-27","cited_by_count":43,"area":null},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"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":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"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":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2212.13881","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","created":"2022-12-28","cited_by_count":25,"area":null},{"id":"2206.08871","title":"How Robust is Unsupervised Representation Learning to Distribution Shift?","created":"2022-06-17","cited_by_count":24,"area":null},{"id":"2405.05847","title":"Learned feature representations are biased by complexity, learning order, position, and more","created":"2024-05-09","cited_by_count":23,"area":null},{"id":"2303.13988","title":"Machine Psychology","created":"2023-03-24","cited_by_count":22,"area":null},{"id":"2109.01396","title":"Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT","created":"2021-09-03","cited_by_count":21,"area":null},{"id":"2307.14039","title":"Controllable Guide-Space for Generalizable Face Forgery Detection","created":"2023-07-26","cited_by_count":21,"area":null},{"id":"2407.03993","title":"A Survey on Natural Language Counterfactual Generation","created":"2024-07-04","cited_by_count":21,"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":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2310.06982","title":"Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality","created":"2023-10-10","cited_by_count":17,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2512.20607","title":"Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures","created":"2025-12-23","cited_by_count":15,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2309.12821","title":"A Spectral Theory of Neural Prediction and Alignment","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2504.05461","title":"Intermediate Layer Classifiers for OOD generalization","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2308.00994","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","created":"2023-08-02","cited_by_count":13,"area":null},{"id":"2503.10065","title":"Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild","created":"2025-03-13","cited_by_count":13,"area":null},{"id":"2509.20234","title":"ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2305.06568","title":"Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation","created":"2023-05-11","cited_by_count":12,"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":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2305.14668","title":"NOVUM: Neural Object Volumes for Robust Object Classification","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2405.17299","title":"Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2108.05779","title":"DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities","created":"2021-08-12","cited_by_count":10,"area":null},{"id":"2202.07184","title":"On the Origins of the Block Structure Phenomenon in Neural Network Representations","created":"2022-02-15","cited_by_count":10,"area":null},{"id":"2412.04619","title":"Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization","created":"2024-12-05","cited_by_count":10,"area":null},{"id":"2212.08378","title":"Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning","created":"2022-12-16","cited_by_count":9,"area":null},{"id":"2402.11816","title":"Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2405.20439","title":"Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2107.06304","title":"Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks","created":"2021-07-13","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":"2401.03002","title":"Prompt-driven Latent Domain Generalization for Medical Image Classification","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2102.06406","title":"A Too-Good-to-be-True Prior to Reduce Shortcut Reliance","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2207.10002","title":"Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain","created":"2022-07-20","cited_by_count":7,"area":null},{"id":"2310.18590","title":"Using Early Readouts to Mediate Featural Bias in Distillation","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2509.25270","title":"InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions","created":"2025-09-28","cited_by_count":7,"area":null},{"id":"2112.07806","title":"Representation Alignment in Neural Networks","created":"2021-12-15","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","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":"2403.19863","title":"DeNetDM: Debiasing by Network Depth Modulation","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2406.00685","title":"Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2507.22216","title":"Representation biases: will we achieve complete understanding by analyzing representations?","created":"2025-07-29","cited_by_count":6,"area":null},{"id":"2207.04104","title":"Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models","created":"2022-07-08","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":"2312.00694","title":"Object Detector Differences when using Synthetic and Real Training Data","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2412.04243","title":"Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects","created":"2024-12-05","cited_by_count":5,"area":null},{"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":"2111.11514","title":"On Data-centric Myths","created":"2021-11-22","cited_by_count":4,"area":null},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2204.13382","title":"Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2210.09834","title":"Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2301.03844","title":"Look Beyond Bias with Entropic Adversarial Data Augmentation","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2306.12673","title":"Identifying and Disentangling Spurious Features in Pretrained Image Representations","created":"2023-06-22","cited_by_count":3,"area":null},{"id":"2403.11792","title":"SETA: Semantic-Aware Token Augmentation for Domain Generalization","created":"2024-03-18","cited_by_count":3,"area":null},{"id":"2404.17768","title":"Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization","created":"2024-04-27","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2507.00493","title":"Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2508.11017","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2208.06809","title":"Multi-Attribute Open Set Recognition","created":"2022-08-14","cited_by_count":2,"area":null},{"id":"2304.01333","title":"Classification of integers based on residue classes via modern deep learning algorithms","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2308.15704","title":"Towards a Rigorous Analysis of Mutual Information in Contrastive Learning","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2401.11713","title":"Medical Image Debiasing by Learning Adaptive Agreement from a Biased Council","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2405.17377","title":"How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2405.21042","title":"Comparing the information content of probabilistic representation spaces","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2510.13307","title":"Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2511.04401","title":"Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2607.04926","title":"Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2607.17624","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2201.08893","title":"Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers","created":"2022-01-19","cited_by_count":1,"area":null},{"id":"2211.10880","title":"PartCom: Part Composition Learning for 3D Open-Set Recognition","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2212.13439","title":"Robust Cross-vendor Mammographic Texture Models Using Augmentation-based Domain Adaptation for Long-term Breast Cancer Risk","created":"2022-12-27","cited_by_count":1,"area":null}],"next_cursor":"100"}