{"total":14,"rows":[{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2406.15079","title":"GOAL: A Generalist Combinatorial Optimization Agent Learner","created":"2024-06-21","cited_by_count":42,"area":null},{"id":"2107.00782","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","created":"2021-07-02","cited_by_count":39,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2108.11833","title":"DeepGene Transformer: Transformer for the gene expression-based classification of cancer subtypes","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2404.01139","title":"Structured Initialization for Attention in Vision Transformers","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2309.10713","title":"Interpret Vision Transformers as ConvNets with Dynamic Convolutions","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2510.22673","title":"Alias-Free ViT: Fractional Shift Invariance via Linear Attention","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2202.03539","title":"Structured Time Series Prediction without Structural Prior","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2302.10692","title":"On Inductive Biases for Machine Learning in Data Constrained Settings","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2405.01216","title":"DMON: A Simple yet Effective Approach for Argument Structure Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2410.17628","title":"Is Smoothness the Key to Robustness? A Comparison of Attention and Convolution Models Using a Novel Metric","created":"2024-10-23","cited_by_count":0,"area":null}],"next_cursor":null}