{"total":12,"rows":[{"id":"2412.05496","title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels","created":"2024-12-07","cited_by_count":185,"area":null},{"id":"2504.16922","title":"Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2505.11157","title":"Attention on the Sphere","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2503.22235","title":"WeatherMesh-3: Fast and accurate operational global weather forecasting","created":"2025-03-28","cited_by_count":4,"area":null},{"id":"2512.18363","title":"Enhancing 3D Semantic Scene Completion with a Refinement Module","created":"2025-12-20","cited_by_count":3,"area":null},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2505.16993","title":"Native Segmentation Vision Transformers","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2605.31577","title":"SurGe: Improved Surface Geometry in Point Maps","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2507.13546","title":"NABLA: Neighborhood Adaptive Block-Level Attention","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2511.05832","title":"Hilbert-Guided Sparse Local Attention","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2602.21010","title":"Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design","created":"2026-02-24","cited_by_count":1,"area":null}],"next_cursor":null}