{"total":59,"rows":[{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"id":"2406.05688","title":"Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions","created":"2024-06-09","cited_by_count":46,"area":null},{"id":"2411.07635","title":"Breaking the Low-Rank Dilemma of Linear Attention","created":"2024-11-12","cited_by_count":31,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2312.11954","title":"Adversarial AutoMixup","created":"2023-12-19","cited_by_count":16,"area":null},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2405.20834","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","created":"2024-05-31","cited_by_count":14,"area":"lr"},{"id":"2503.07499","title":"AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2503.01136","title":"Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2504.00999","title":"MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization","created":"2025-04-01","cited_by_count":12,"area":"inference"},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2401.04942","title":"Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics","created":"2024-01-10","cited_by_count":8,"area":null},{"id":"2510.00059","title":"FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2406.00446","title":"Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2504.09588","title":"TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting","created":"2025-04-13","cited_by_count":6,"area":null},{"id":"2507.12905","title":"AthleticsPose: Authentic Sports Motion Dataset on Athletic Field and Evaluation of Monocular 3D Pose Estimation Ability","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2405.12721","title":"StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2405.13337","title":"Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2406.19253","title":"Advection Augmented Convolutional Neural Networks","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2411.04967","title":"AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2305.17644","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2311.03217","title":"Leveraging Transformers to Improve Breast Cancer Classification and Risk Assessment with Multi-modal and Longitudinal Data","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2506.06042","title":"SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detection","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2405.03192","title":"QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2507.11893","title":"Spatial Frequency Modulation for Semantic Segmentation","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","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":"2312.00412","title":"SCHEME: Scalable Channel Mixer for Vision Transformers","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2502.07299","title":"Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2503.17193","title":"MSCA-Net:Multi-Scale Context Aggregation Network for Infrared Small Target Detection","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"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":"2511.09942","title":"AdaptViG: Adaptive Vision GNN with Exponential Decay Gating","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2512.23938","title":"Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation","created":"2025-12-30","cited_by_count":2,"area":"moe"},{"id":"2305.10110","title":"Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2505.05936","title":"CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2507.04397","title":"Multi-Expert Learning Framework with the State Space Model for Optical and SAR Image Registration","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2605.17470","title":"EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2307.08559","title":"Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2407.20843","title":"DFE-IANet: A Method for Polyp Image Classification Based on Dual-domain Feature Extraction and Interaction Attention","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2412.17401","title":"Learning Dynamic Local Context Representations for Infrared Small Target Detection","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2412.19628","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2505.22226","title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2507.10999","title":"SpaRTAN: Spatial Reinforcement Token-based Aggregation Network for Visual Recognition","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2602.04346","title":"MirrorLA: Reflecting Feature Map for Vision Linear Attention","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.20537","title":"PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.02727","title":"Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.19074","title":"CAMO: A Conditional Neural Solver for the Multi-objective Multiple Traveling Salesman Problem","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.23284","title":"WaveSFNet: A Wavelet-Based Codec and Spatial--Frequency Dual-Domain Gating Network for Spatiotemporal Prediction","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27288","title":"StretchCast: Global-Regional AI Weather Forecasting on Stretched Cubed-Sphere Mesh","created":"2026-03-28","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}