{"total":22,"rows":[{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57,"area":null},{"id":"2412.06590","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","created":"2024-12-09","cited_by_count":48,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","cited_by_count":17,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2207.12152","title":"Deep Laparoscopic Stereo Matching with Transformers","created":"2022-07-25","cited_by_count":9,"area":null},{"id":"2405.21022","title":"You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2308.04321","title":"All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2510.12660","title":"On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2606.14757","title":"Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.33325","title":"VisionHOPE: Visual Backbones as Self-Modifying Learning Systems","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}