{"total":333,"rows":[{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218,"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":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"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":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2306.11074","title":"Simple and Fast Group Robustness by Automatic Feature Reweighting","created":"2023-06-19","cited_by_count":68,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62,"area":null},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"area":null},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2304.12566","title":"AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation","created":"2023-04-25","cited_by_count":48,"area":null},{"id":"2402.11137","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","created":"2024-02-17","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":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35,"area":null},{"id":"2403.04547","title":"CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2406.19380","title":"TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks","created":"2024-06-27","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":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","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":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2206.13378","title":"Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning","created":"2022-06-27","cited_by_count":26,"area":null},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"area":null},{"id":"2309.16748","title":"Discovering environments with XRM","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","cited_by_count":25,"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":"2206.08871","title":"How Robust is Unsupervised Representation Learning to Distribution Shift?","created":"2022-06-17","cited_by_count":24,"area":null},{"id":"2309.04344","title":"Zero-Shot Robustification of Zero-Shot Models","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2408.08041","title":"The Clever Hans Effect in Unsupervised Learning","created":"2024-08-15","cited_by_count":24,"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":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2405.16747","title":"Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective","created":"2024-05-27","cited_by_count":22,"area":null},{"id":"2305.19254","title":"What Can We Learn from Unlearnable Datasets?","created":"2023-05-30","cited_by_count":21,"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":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2403.11391","title":"Investigating the Benefits of Projection Head for Representation Learning","created":"2024-03-18","cited_by_count":20,"area":null},{"id":"2501.00961","title":"Uncovering Memorization Effect in the Presence of Spurious Correlations","created":"2025-01-01","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"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":"2308.04431","title":"When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2402.18919","title":"Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2406.06487","title":"When is Multicalibration Post-Processing Necessary?","created":"2024-06-10","cited_by_count":18,"area":null},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2211.15231","title":"Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers","created":"2022-11-28","cited_by_count":17,"area":null},{"id":"2212.06254","title":"You Only Need a Good Embeddings Extractor to Fix Spurious Correlations","created":"2022-12-12","cited_by_count":17,"area":null},{"id":"2304.03935","title":"Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks","created":"2023-04-08","cited_by_count":17,"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":"2309.08825","title":"Distributionally Robust Post-hoc Classifiers under Prior Shifts","created":"2023-09-16","cited_by_count":16,"area":null},{"id":"2404.13815","title":"Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference","created":"2024-04-22","cited_by_count":15,"area":null},{"id":"2212.07346","title":"Learning useful representations for shifting tasks and distributions","created":"2022-12-14","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":"2405.14839","title":"A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis","created":"2024-05-23","cited_by_count":14,"area":null},{"id":"2406.10050","title":"Comparison of fine-tuning strategies for transfer learning in medical image classification","created":"2024-06-14","cited_by_count":14,"area":null},{"id":"2407.11083","title":"Empowering Graph Invariance Learning with Deep Spurious Infomax","created":"2024-07-13","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":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2307.13136","title":"Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?","created":"2023-07-24","cited_by_count":13,"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":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2505.24022","title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2206.09868","title":"Understanding Robust Learning through the Lens of Representation Similarities","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2303.07527","title":"Domain Generalization via Nuclear Norm Regularization","created":"2023-03-13","cited_by_count":12,"area":null},{"id":"2308.04553","title":"From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition","created":"2023-08-08","cited_by_count":12,"area":null},{"id":"2402.00322","title":"Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2402.12789","title":"Fairness Without Harm: An Influence-Guided Active Sampling Approach","created":"2024-02-20","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":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","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":"2305.13654","title":"Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis","created":"2023-05-23","cited_by_count":11,"area":null},{"id":"2307.10404","title":"Interpreting and Correcting Medical Image Classification with PIP-Net","created":"2023-07-19","cited_by_count":11,"area":null},{"id":"2402.13368","title":"Unsupervised Concept Discovery Mitigates Spurious Correlations","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2410.20380","title":"FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion","created":"2024-10-27","cited_by_count":11,"area":null},{"id":"2502.07778","title":"Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2211.10370","title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","created":"2022-11-18","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":"2403.02695","title":"Controllable Prompt Tuning For Balancing Group Distributional Robustness","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2406.00661","title":"Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift","created":"2024-06-02","cited_by_count":10,"area":null},{"id":"2206.00944","title":"Feature Space Particle Inference for Neural Network Ensembles","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2302.02931","title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","created":"2023-02-06","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":"2308.00473","title":"Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?","created":"2023-08-01","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":"2406.17433","title":"Mind the Graph When Balancing Data for Fairness or Robustness","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2407.14974","title":"Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations","created":"2024-07-20","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":"2502.06343","title":"Prediction-Powered Causal Inferences","created":"2025-02-10","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}],"next_cursor":"100"}