{"total":19,"rows":[{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2402.03902","title":"A phase transition between positional and semantic learning in a solvable model of dot-product attention","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2202.00565","title":"Data-driven emergence of convolutional structure in neural networks","created":"2022-02-01","cited_by_count":29,"area":null},{"id":"2210.02157","title":"The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2106.13031","title":"Towards Biologically Plausible Convolutional Networks","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2105.03906","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","created":"2021-05-09","cited_by_count":11,"area":null},{"id":"2206.05317","title":"Intrinsic dimensionality and generalization properties of the $\\mathcal{R}$-norm inductive bias","created":"2022-06-10","cited_by_count":5,"area":null},{"id":"2106.05795","title":"Transformed CNNs: recasting pre-trained convolutional layers with self-attention","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2106.10704","title":"Better Training using Weight-Constrained Stochastic Dynamics","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2311.06224","title":"Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization","created":"2023-11-10","cited_by_count":4,"area":null},{"id":"2104.13343","title":"Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?","created":"2021-04-27","cited_by_count":3,"area":null},{"id":"2306.01470","title":"Understanding MLP-Mixer as a Wide and Sparse MLP","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2202.12119","title":"Optimal Convergence Rates of Deep Convolutional Neural Networks: Additive Ridge Functions","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2401.03797","title":"Anatomy of Neural Language Models","created":"2024-01-08","cited_by_count":1,"area":null},{"id":"2210.17141","title":"Studying inductive biases in image classification task","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2408.00923","title":"Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization","created":"2024-08-01","cited_by_count":0,"area":null}],"next_cursor":null}