{"total":183,"rows":[{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"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":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"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":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118,"area":null},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2211.12316","title":"Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions","created":"2022-11-22","cited_by_count":70,"area":null},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","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":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"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":"2308.12108","title":"The Local Learning Coefficient: A Singularity-Aware Complexity Measure","created":"2023-08-23","cited_by_count":51,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50,"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":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2106.02105","title":"A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2402.18377","title":"Out-of-Domain Generalization in Dynamical Systems Reconstruction","created":"2024-02-28","cited_by_count":33,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2401.14953","title":"Learning Universal Predictors","created":"2024-01-26","cited_by_count":31,"area":null},{"id":"2402.04362","title":"Neural Networks Learn Statistics of Increasing Complexity","created":"2024-02-06","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":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2304.06670","title":"Deep neural networks have an inbuilt Occam's razor","created":"2023-04-13","cited_by_count":28,"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":"2110.03922","title":"The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2106.03314","title":"Measuring Generalization with Optimal Transport","created":"2021-06-07","cited_by_count":25,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2404.16367","title":"Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers","created":"2024-04-25","cited_by_count":24,"area":null},{"id":"2410.19637","title":"A distributional simplicity bias in the learning dynamics of transformers","created":"2024-10-25","cited_by_count":24,"area":null},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","cited_by_count":23,"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":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2203.14661","title":"Random matrix analysis of deep neural network weight matrices","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2202.13473","title":"The Spectral Bias of Polynomial Neural Networks","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2110.11749","title":"Feature Learning and Signal Propagation in Deep Neural Networks","created":"2021-10-22","cited_by_count":18,"area":null},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2112.05611","title":"Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks","created":"2021-12-10","cited_by_count":17,"area":null},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"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":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"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":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","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":"2504.05461","title":"Intermediate Layer Classifiers for OOD generalization","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2103.06219","title":"Why flatness does and does not correlate with generalization for deep neural networks","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2311.04163","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","created":"2023-11-07","cited_by_count":13,"area":null},{"id":"2401.01869","title":"On the hardness of learning under symmetries","created":"2024-01-03","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":"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":"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":"2502.13870","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2204.05023","title":"Machine Learning and Deep Learning -- A review for Ecologists","created":"2022-04-11","cited_by_count":11,"area":null},{"id":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","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":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","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":"2302.07557","title":"On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2305.09779","title":"A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2603.00742","title":"To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters","created":"2026-02-28","cited_by_count":10,"area":null},{"id":"2206.07673","title":"Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2410.07501","title":"Inferring biological processes with intrinsic noise from cross-sectional data","created":"2024-10-10","cited_by_count":9,"area":null},{"id":"2309.17417","title":"Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2409.17691","title":"Efficient Bias Mitigation Without Privileged Information","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2410.06300","title":"SHAP values via sparse Fourier representation","created":"2024-10-08","cited_by_count":8,"area":null},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8,"area":"wm"},{"id":"2102.05110","title":"Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2310.06161","title":"Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2311.17094","title":"In Search of a Data Transformation That Accelerates Neural Field Training","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2406.09935","title":"Predicting the Susceptibility of Examples to Catastrophic Forgetting","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2510.12071","title":"Influence Dynamics and Stagewise Data Attribution","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2210.02419","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","created":"2022-10-05","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":"2402.03698","title":"Estimating the Local Learning Coefficient at Scale","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2102.07238","title":"Double-descent curves in neural networks: a new perspective using Gaussian processes","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2111.11542","title":"Depth Without the Magic: Inductive Bias of Natural Gradient Descent","created":"2021-11-22","cited_by_count":5,"area":null},{"id":"2205.03940","title":"Investigating Generalization by Controlling Normalized Margin","created":"2022-05-08","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":"2410.19092","title":"Provable Tempered Overfitting of Minimal Nets and Typical Nets","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2509.12527","title":"Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2111.11514","title":"On Data-centric Myths","created":"2021-11-22","cited_by_count":4,"area":null},{"id":"2205.01421","title":"A Falsificationist Account of Artificial Neural Networks","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2205.07427","title":"Exploring the Learning Difficulty of Data Theory and Measure","created":"2022-05-16","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":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2601.07524","title":"Stagewise Reinforcement Learning and the Geometry of the Regret Landscape","created":"2026-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2103.01045","title":"Computing the Information Content of Trained Neural Networks","created":"2021-03-01","cited_by_count":3,"area":null},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3,"area":null}],"next_cursor":"100"}