{"total":17,"rows":[{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2511.06294","title":"Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention","created":"2025-11-09","cited_by_count":13,"area":null},{"id":"2603.06199","title":"FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2603.16063","title":"ViT-AdaLA: Adapting Vision Transformers with Linear Attention","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2602.02195","title":"State Rank Dynamics in Linear Attention LLMs","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2506.21137","title":"Norm$\\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2510.10631","title":"GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2602.12128","title":"HLA: Hadamard Linear Attention","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2608.30129","title":"Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2509.15436","title":"Region-Aware Deformable Convolutions","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.20092","title":"Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.00175","title":"Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2608.29609","title":"nnMNet: Baseline for Martian Terrain Semantic Segmentation","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}