{"total":66,"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":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78,"area":"distill"},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61,"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":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44,"area":null},{"id":"2207.14087","title":"CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation","created":"2022-07-28","cited_by_count":40,"area":null},{"id":"2406.00123","title":"Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration","created":"2024-05-31","cited_by_count":38,"area":null},{"id":"2109.04454","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","created":"2021-09-09","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"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":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32,"area":null},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2111.12527","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","created":"2021-11-24","cited_by_count":21,"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":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13,"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":"2401.17992","title":"Multilinear Operator Networks","created":"2024-01-31","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":"2306.14525","title":"ParameterNet: Parameters Are All You Need","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"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":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2311.16707","title":"Full-resolution MLPs Empower Medical Dense Prediction","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2208.11718","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","created":"2022-08-24","cited_by_count":5,"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":"2502.09928","title":"Deep Tree Tensor Networks","created":"2025-02-14","cited_by_count":5,"area":null},{"id":"2111.13156","title":"Global Interaction Modelling in Vision Transformer via Super Tokens","created":"2021-11-25","cited_by_count":4,"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":"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":"2305.19492","title":"CVSNet: A Computer Implementation for Central Visual System of The Brain","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2407.09790","title":"Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs","created":"2024-07-13","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":"2409.09244","title":"Investigation of Hierarchical Spectral Vision Transformer Architecture for Classification of Hyperspectral Imagery","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2410.10914","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2507.12135","title":"Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2207.07284","title":"Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP","created":"2022-07-15","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":"2412.18545","title":"Advancing Deformable Medical Image Registration with Multi-axis Cross-covariance Attention","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2208.08191","title":"Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems","created":"2022-08-17","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":"2211.14434","title":"Multi-Step Short-Term Wind Speed Prediction with Rank Pooling and Fast Fourier Transformation","created":"2022-11-23","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":"2308.13363","title":"CS-Mixer: A Cross-Scale Vision MLP Model with Spatial-Channel Mixing","created":"2023-08-25","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":"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":"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":"2509.11328","title":"Toward Next-generation Medical Vision Backbones: Modeling Finer-grained Long-range Visual Dependency","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.18431","title":"ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2601.14799","title":"UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Tracking","created":"2026-01-21","cited_by_count":0,"area":"ssm"},{"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":"2603.23122","title":"PiCo: Active Manifold Canonicalization for Robust Robotic Visual Anomaly Detection","created":"2026-03-24","cited_by_count":0,"area":null}],"next_cursor":null}