{"total":121,"rows":[{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118,"area":null},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111,"area":null},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2206.08720","title":"Fast Finite Width Neural Tangent Kernel","created":"2022-06-17","cited_by_count":62,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57,"area":null},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2309.08586","title":"Replacing softmax with ReLU in Vision Transformers","created":"2023-09-15","cited_by_count":44,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2106.04110","title":"A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs","created":"2021-06-08","cited_by_count":33,"area":null},{"id":"2106.07880","title":"Scaling Neural Tangent Kernels via Sketching and Random Features","created":"2021-06-15","cited_by_count":32,"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":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2405.04669","title":"Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics","created":"2024-05-07","cited_by_count":27,"area":"lr"},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23,"area":null},{"id":"2210.00688","title":"On the infinite-depth limit of finite-width neural networks","created":"2022-10-03","cited_by_count":22,"area":null},{"id":"2307.03223","title":"Neural Network Field Theories: Non-Gaussianity, Actions, and Locality","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2106.05566","title":"A Neural Tangent Kernel Perspective of GANs","created":"2021-06-10","cited_by_count":21,"area":null},{"id":"2106.06529","title":"The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","cited_by_count":21,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2207.13676","title":"Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization","created":"2022-07-27","cited_by_count":18,"area":null},{"id":"2209.04121","title":"Fast Neural Kernel Embeddings for General Activations","created":"2022-09-09","cited_by_count":18,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2103.03113","title":"Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective","created":"2021-03-03","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":"2311.01575","title":"On the Convergence of Encoder-only Shallow Transformers","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2402.05173","title":"Towards Understanding Inductive Bias in Transformers: A View From Infinity","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2106.03186","title":"Reverse Engineering the Neural Tangent Kernel","created":"2021-06-06","cited_by_count":12,"area":null},{"id":"2202.06438","title":"Learning from Randomly Initialized Neural Network Features","created":"2022-02-13","cited_by_count":12,"area":null},{"id":"2305.09957","title":"Quantum neural networks form Gaussian processes","created":"2023-05-17","cited_by_count":12,"area":null},{"id":"2102.05628","title":"On the Regularity of Attention","created":"2021-02-10","cited_by_count":11,"area":null},{"id":"2203.03443","title":"Generalization Through The Lens Of Leave-One-Out Error","created":"2022-03-07","cited_by_count":10,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","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":"2303.05420","title":"Kernel Regression with Infinite-Width Neural Networks on Millions of Examples","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2310.06112","title":"Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2111.12143","title":"Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications","created":"2021-11-23","cited_by_count":8,"area":null},{"id":"2405.06008","title":"Wilsonian Renormalization of Neural Network Gaussian Processes","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2410.21273","title":"On Inductive Biases That Enable Generalization of Diffusion Transformers","created":"2024-10-28","cited_by_count":7,"area":"diffusion"},{"id":"2602.22617","title":"Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA","created":"2026-02-26","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2207.04612","title":"Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2409.06142","title":"Variational Search Distributions","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2511.16741","title":"Fermions and Supersymmetry in Neural Network Field Theories","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2107.01408","title":"Scale Mixtures of Neural Network Gaussian Processes","created":"2021-07-03","cited_by_count":5,"area":null},{"id":"2506.00846","title":"Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2108.12862","title":"Neural Network Gaussian Processes by Increasing Depth","created":"2021-08-29","cited_by_count":4,"area":null},{"id":"2205.11786","title":"Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2305.00995","title":"Towards a Phenomenological Understanding of Neural Networks: Data","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2503.09565","title":"Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $\\mu$P Parametrization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2601.03329","title":"Attention mechanisms in neural networks","created":"2026-01-06","cited_by_count":4,"area":null},{"id":"2202.12637","title":"Do autoencoders need a bottleneck for anomaly detection?","created":"2022-02-25","cited_by_count":3,"area":null},{"id":"2206.13568","title":"AutoInit: Automatic Initialization via Jacobian Tuning","created":"2022-06-27","cited_by_count":3,"area":null},{"id":"2409.05349","title":"On the Convergence Analysis of Over-Parameterized Variational Autoencoders: A Neural Tangent Kernel Perspective","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2504.11130","title":"Divergence of Empirical Neural Tangent Kernel in Classification Problems","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2506.01582","title":"Bayes optimal learning of attention-indexed models","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2204.04090","title":"Single-level Adversarial Data Synthesis based on Neural Tangent Kernels","created":"2022-04-08","cited_by_count":2,"area":null},{"id":"2209.12737","title":"A connection between probability, physics and neural networks","created":"2022-09-26","cited_by_count":2,"area":null},{"id":"2406.11016","title":"Optimized Speculative Sampling for GPU Hardware Accelerators","created":"2024-06-16","cited_by_count":2,"area":"inference"},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2603.10351","title":"Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.17569","title":"Gaussian Process Limit Reveals Structural Benefits of Graph Transformers","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2604.02313","title":"Topological Effects in Neural Network Field Theory","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2202.01958","title":"Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2202.12297","title":"Embedded Ensembles: Infinite Width Limit and Operating Regimes","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2309.01592","title":"Les Houches Lectures on Deep Learning at Large & Infinite Width","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2310.01683","title":"Commutative Width and Depth Scaling in Deep Neural Networks","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2403.17467","title":"A Unified Kernel for Neural Network Learning","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2407.04844","title":"Neural varifolds: an aggregate representation for quantifying the geometry of point clouds","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2501.10929","title":"Issues with Neural Tangent Kernel Approach to Neural Networks","created":"2025-01-19","cited_by_count":1,"area":null},{"id":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2510.06685","title":"Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2601.16514","title":"Finite-Time Analysis of Gradient Descent for Shallow Transformers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.20461","title":"Nonparametric Teaching of Attention Learners","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.11161","title":"Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.07959","title":"Convergent Stochastic Training of Multi-Headed Attention and Understanding LoRA","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.09905","title":"Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging","created":"2026-05-11","cited_by_count":1,"area":null}],"next_cursor":"100"}