{"total":61,"rows":[{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186,"area":null},{"id":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139,"area":null},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2211.12905","title":"GhostNetV2: Enhance Cheap Operation with Long-Range Attention","created":"2022-11-23","cited_by_count":44,"area":null},{"id":"2211.14731","title":"BALF: Simple and Efficient Blur Aware Local Feature Detector","created":"2022-11-27","cited_by_count":34,"area":null},{"id":"2306.00396","title":"Lightweight Vision Transformer with Bidirectional Interaction","created":"2023-06-01","cited_by_count":25,"area":null},{"id":"2205.10528","title":"PointVector: A Vector Representation In Point Cloud Analysis","created":"2022-05-21","cited_by_count":21,"area":null},{"id":"2306.16678","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","created":"2023-06-29","cited_by_count":17,"area":null},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2203.14679","title":"Brain-inspired Multilayer Perceptron with Spiking Neurons","created":"2022-03-28","cited_by_count":16,"area":null},{"id":"2308.11568","title":"SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation","created":"2023-08-22","cited_by_count":14,"area":null},{"id":"2307.11458","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","created":"2023-07-21","cited_by_count":12,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2407.19811","title":"Synthetic Thermal and RGB Videos for Automatic Pain Assessment utilizing a Vision-MLP Architecture","created":"2024-07-29","cited_by_count":12,"area":null},{"id":"2406.00843","title":"Diffusion-Inspired Quantum Noise Mitigation in Parameterized Quantum Circuits","created":"2024-06-02","cited_by_count":10,"area":null},{"id":"2505.01571","title":"PainFormer: a Vision Foundation Model for Automatic Pain Assessment","created":"2025-05-02","cited_by_count":10,"area":null},{"id":"2303.00941","title":"ParaFormer: Parallel Attention Transformer for Efficient Feature Matching","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2412.13231","title":"C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Prediction","created":"2024-12-17","cited_by_count":9,"area":null},{"id":"2407.13108","title":"UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2306.14525","title":"ParameterNet: Parameters Are All You Need","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2411.13378","title":"Quantum-Brain: Quantum-Inspired Neural Network Approach to Vision-Brain Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2202.06510","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","created":"2022-02-14","cited_by_count":6,"area":null},{"id":"2203.06108","title":"Active Token Mixer","created":"2022-03-11","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2403.18063","title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","created":"2024-03-26","cited_by_count":5,"area":"ssm"},{"id":"2305.17644","title":"Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation","created":"2023-05-28","cited_by_count":4,"area":null},{"id":"2201.00978","title":"PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2212.14158","title":"BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2303.13111","title":"Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2402.11303","title":"FViT: A Focal Vision Transformer with Gabor Filter","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2,"area":null},{"id":"2604.13941","title":"SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2211.15672","title":"ExpNet: A unified network for Expert-Level Classification","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2304.03532","title":"Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction","created":"2023-04-07","cited_by_count":1,"area":null},{"id":"2305.14675","title":"TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.21040","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2512.07078","title":"DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2206.02220","title":"U(1) Symmetry-breaking Observed in Generic CNN Bottleneck Layers","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2206.02997","title":"TadML: A fast temporal action detection with Mechanics-MLP","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2208.09183","title":"Improved Image Classification with Token Fusion","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2304.03917","title":"MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2309.06721","title":"Dynamic Spectrum Mixer for Visual Recognition","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2310.03911","title":"Coloring Deep CNN Layers with Activation Hue Loss","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2311.18735","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2403.05703","title":"Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.05886","title":"Generalizing to Out-of-Sample Degradations via Model Reprogramming","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2407.03033","title":"ISWSST: Index-space-wave State Superposition Transformers for Multispectral Remotely Sensed Imagery Semantic Segmentation","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2408.13661","title":"Hierarchical Network Fusion for Multi-Modal Electron Micrograph Representation Learning with Foundational Large Language Models","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2503.23947","title":"Spectral-Adaptive Modulation Networks for Visual Perception","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2504.09076","title":"Exploring Synergistic Ensemble Learning: Uniting CNNs, MLP-Mixers, and Vision Transformers to Enhance Image Classification","created":"2025-04-12","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":"2509.03973","title":"SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2603.01706","title":"Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2607.06949","title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}