{"total":71,"rows":[{"id":"2402.16991","title":"A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data","created":"2024-02-26","cited_by_count":93,"area":"diffusion"},{"id":"2501.17047","title":"How Linguistics Learned to Stop Worrying and Love the Language Models","created":"2025-01-28","cited_by_count":51,"area":null},{"id":"2403.01633","title":"Critical windows: non-asymptotic theory for feature emergence in diffusion models","created":"2024-03-03","cited_by_count":47,"area":"diffusion"},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2406.00048","title":"Towards a theory of how the structure of language is acquired by deep neural networks","created":"2024-05-28","cited_by_count":39,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2410.13770","title":"Probing the Latent Hierarchical Structure of Data via Diffusion Models","created":"2024-10-17","cited_by_count":26,"area":"diffusion"},{"id":"2502.12089","title":"How Compositional Generalization and Creativity Improve as Diffusion Models are Trained","created":"2025-02-17","cited_by_count":25,"area":"diffusion"},{"id":"2505.16959","title":"Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models","created":"2025-05-22","cited_by_count":25,"area":"diffusion"},{"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":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2408.15138","title":"How transformers learn structured data: insights from hierarchical filtering","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2404.18444","title":"U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models","created":"2024-04-29","cited_by_count":17,"area":"diffusion"},{"id":"2410.11767","title":"Analyzing (In)Abilities of SAEs via Formal Languages","created":"2024-10-15","cited_by_count":17,"area":"mechinterp"},{"id":"2505.07067","title":"Learning curves theory for hierarchically compositional data with power-law distributed features","created":"2025-05-11","cited_by_count":17,"area":null},{"id":"2507.02550","title":"Position: A Theory of Deep Learning Must Include Compositional Sparsity","created":"2025-07-03","cited_by_count":14,"area":null},{"id":"2601.10684","title":"On the origin of neural scaling laws: from random graphs to natural language","created":"2026-01-15","cited_by_count":14,"area":null},{"id":"2505.18651","title":"On the Emergence of Linear Analogies in Word Embeddings","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2508.18226","title":"Disentangling the Factors of Convergence between Brains and Computer Vision Models","created":"2025-08-25","cited_by_count":13,"area":null},{"id":"2406.03260","title":"Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2410.09005","title":"Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2505.24769","title":"Generalization Dynamics of Linear Diffusion Models","created":"2025-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2602.05970","title":"Inverse Depth Scaling From Most Layers Being Similar","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2404.10727","title":"How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2507.07207","title":"Scaling can lead to compositional generalization","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2402.10164","title":"Random features and polynomial rules","created":"2024-02-15","cited_by_count":6,"area":null},{"id":"2407.05664","title":"How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2601.19756","title":"Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2505.07070","title":"Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures","created":"2025-05-11","cited_by_count":5,"area":null},{"id":"2511.20888","title":"Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2602.06065","title":"Deep networks learn to parse uniform-depth context-free languages from local statistics","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2602.10867","title":"Deep Learning of Compositional Targets with Hierarchical Spectral Methods","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2604.02028","title":"Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?","created":"2026-04-02","cited_by_count":5,"area":"diffusion"},{"id":"2603.03469","title":"Biased Generalization in Diffusion Models","created":"2026-03-03","cited_by_count":4,"area":"diffusion"},{"id":"2603.06603","title":"Scale Dependent Data Duplication","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2603.11331","title":"Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover","created":"2026-03-11","cited_by_count":4,"area":"alignment"},{"id":"2604.06107","title":"Artificial Intelligence and the Structure of Mathematics","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.08907","title":"Positive Distribution Shift as a Framework for Understanding Tractable Learning","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2605.25608","title":"Learning Sparse Compositional Functions with Norm-Constrained Neural Networks","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2411.01375","title":"Learning with Hidden Factorial Structure","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2605.27006","title":"Sampling Data with Chains of Forward-Backward Diffusion Steps","created":"2026-05-26","cited_by_count":2,"area":"diffusion"},{"id":"2605.27734","title":"Learn from your own latents and not from tokens: A sample-complexity theory","created":"2026-05-26","cited_by_count":2,"area":"diffusion"},{"id":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2509.05130","title":"The Advantage of Fine-Grained Training","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2511.06232","title":"Scaling Laws and In-Context Learning: A Unified Theoretical Framework","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2605.14927","title":"Learning with Shallow Neural Networks on Cluster-Structured Features","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.30642","title":"Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?","created":"2026-05-28","cited_by_count":1,"area":"diffusion"},{"id":"2605.31244","title":"Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.06382","title":"A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2407.01656","title":"Absolute abstraction: a renormalisation group approach","created":"2024-07-01","cited_by_count":0,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.19143","title":"Game-Theoretic Gradient Control for Robust Neural Network Training","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2511.20312","title":"Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.09394","title":"Language models as tools for investigating the distinction between possible and impossible natural languages","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.12447","title":"Large language models have learned to use language","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.13441","title":"Large language models are not about natural language","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.14506","title":"Linguists should learn to love speech-based deep learning models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.10421","title":"Are Language Models Models?","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2604.02415","title":"Generative models on phase space","created":"2026-04-02","cited_by_count":0,"area":"diffusion"},{"id":"2604.09466","title":"Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.09501","title":"You Can't Fight in Here! This is BBS!","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.15306","title":"Generalization in LLM Problem Solving: The Case of the Shortest Path","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.15593","title":"DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.10061","title":"Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.13687","title":"A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.20347","title":"Critical Percolation as a Synthetic Data Model for Interpretability","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.10330","title":"Hierarchical Compositionality for An Assistive AI Agent","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.20255","title":"Transfer Learning in Nonparametric Regression with Deep ReLU Networks","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.32288","title":"A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2609.32487","title":"Neural Dynamics as the Composition of Quantized Units","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}