{"total":63,"rows":[{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"id":"2402.04379","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","created":"2024-02-06","cited_by_count":93,"area":null},{"id":"2306.04891","title":"In-Context Learning through the Bayesian Prism","created":"2023-06-08","cited_by_count":83,"area":null},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"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":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2412.09810","title":"The Complexity Dynamics of Grokking","created":"2024-12-13","cited_by_count":22,"area":null},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","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":"2506.12027","title":"Constant Bit-size Transformers Are Turing Complete","created":"2025-05-22","cited_by_count":19,"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":"2402.00491","title":"EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations","created":"2024-02-01","cited_by_count":14,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2410.14817","title":"A Complexity-Based Theory of Compositionality","created":"2024-10-18","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":"2405.01502","title":"Analyzing the Role of Semantic Representations in the Era of Large Language Models","created":"2024-05-02","cited_by_count":12,"area":null},{"id":"2403.14628","title":"Zero-Shot Multi-Object Scene Completion","created":"2024-03-21","cited_by_count":9,"area":null},{"id":"2410.14086","title":"In-context learning and Occam's razor","created":"2024-10-17","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":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2409.09626","title":"Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics","created":"2024-09-15","cited_by_count":5,"area":null},{"id":"2506.20057","title":"Universal pre-training by iterated random computation","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2312.09323","title":"Perspectives on the State and Future of Deep Learning - 2023","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2508.00545","title":"Foundations of Interpretable Models","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2409.13728","title":"Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2410.02735","title":"OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2602.14896","title":"Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.20274","title":"Solomonoff induction","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2607.10039","title":"Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough","created":"2026-07-10","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":"2405.07024","title":"Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning","created":"2024-05-11","cited_by_count":1,"area":null},{"id":"2407.03080","title":"Artificial Inductive Bias for Synthetic Tabular Data Generation in Data-Scarce Scenarios","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2505.09855","title":"An evolutionary perspective on modes of learning in Transformers","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.24060","title":"Characterising the Inductive Biases of Neural Networks on Boolean Data","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2602.10657","title":"Benchmarks Are Not That Out of Distribution: Word Overlap Predicts Performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.11749","title":"Truth as a Compression Artifact in Language Model Training","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2505.20235","title":"Variational Deep Learning via Implicit Regularization","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.00182","title":"Overfitting has a limitation: a model-independent generalization gap bound based on R\\'enyi entropy","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.07804","title":"Deep Survival Analysis in Multimodal Medical Data: A Parametric and Probabilistic Approach with Competing Risks","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2507.10678","title":"A Group Theoretic Analysis of the Symmetries Underlying Base Addition and Their Learnability by Neural Networks","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2511.13062","title":"Self-Adaptive Graph Mixture of Models","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2601.21618","title":"Semantic Content Determines Algorithmic Performance","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.03613","title":"Empirical Evaluation of No Free Lunch Violations in Permutation-Based Optimization","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.25839","title":"A Compression Perspective on Simplicity Bias","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.15551","title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.29823","title":"Quantifying and Optimizing Simplicity via Polynomial Representations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.02632","title":"Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.03386","title":"Benign interpolation and Occam's razor","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.26539","title":"A retrospective analysis on the use of LLMs to study infant syntax learning","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34458","title":"Understanding Generalization Requires Universal Induction","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}