{"total":334,"rows":[{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2303.02190","title":"MixVPR: Feature Mixing for Visual Place Recognition","created":"2023-03-03","cited_by_count":161,"area":null},{"id":"2207.01186","title":"Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures","created":"2022-07-04","cited_by_count":160,"area":null},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152,"area":null},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"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":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2308.03364","title":"Dual Aggregation Transformer for Image Super-Resolution","created":"2023-08-07","cited_by_count":124,"area":null},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2202.13556","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93,"area":null},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91,"area":null},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66,"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":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"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":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2303.12071","title":"ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals","created":"2023-03-21","cited_by_count":48,"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":"2302.14502","title":"A Survey on Long Text Modeling with Transformers","created":"2023-02-28","cited_by_count":47,"area":null},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2410.08565","title":"Baichuan-Omni Technical Report","created":"2024-10-11","cited_by_count":42,"area":null},{"id":"2202.12165","title":"Transformers in Medical Image Analysis: A Review","created":"2022-02-24","cited_by_count":41,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38,"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":"2207.13159","title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","created":"2022-07-26","cited_by_count":36,"area":null},{"id":"2301.01146","title":"Rethinking Mobile Block for Efficient Attention-based Models","created":"2023-01-03","cited_by_count":36,"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":"2405.15124","title":"Scaling Law for Time Series Forecasting","created":"2024-05-24","cited_by_count":33,"area":null},{"id":"2108.13002","title":"A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP","created":"2021-08-30","cited_by_count":32,"area":null},{"id":"2112.11081","title":"RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality","created":"2021-12-21","cited_by_count":32,"area":null},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31,"area":null},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30,"area":null},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"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":"2203.16248","title":"InstaFormer: Instance-Aware Image-to-Image Translation with Transformer","created":"2022-03-30","cited_by_count":28,"area":null},{"id":"2303.11674","title":"ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization","created":"2023-03-21","cited_by_count":28,"area":null},{"id":"2205.13891","title":"Transformers from an Optimization Perspective","created":"2022-05-27","cited_by_count":27,"area":null},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27,"area":null},{"id":"2303.06337","title":"AutoMLP: Automated MLP for Sequential Recommendations","created":"2023-03-11","cited_by_count":25,"area":null},{"id":"2108.01072","title":"S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23,"area":null},{"id":"2208.00306","title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","created":"2022-07-30","cited_by_count":23,"area":null},{"id":"2110.01775","title":"Deep Instance Segmentation with Automotive Radar Detection Points","created":"2021-10-05","cited_by_count":22,"area":null},{"id":"2203.07057","title":"Self-Promoted Supervision for Few-Shot Transformer","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"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":"2206.06420","title":"GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation","created":"2022-06-13","cited_by_count":21,"area":null},{"id":"2206.09132","title":"Pre-training Vision Transformers with Formula-driven Supervised Learning","created":"2022-06-18","cited_by_count":21,"area":null},{"id":"2211.03495","title":"How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers","created":"2022-11-07","cited_by_count":21,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2202.04350","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","created":"2022-02-09","cited_by_count":19,"area":null},{"id":"2310.17653","title":"Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2403.16899","title":"State Space Models as Foundation Models: A Control Theoretic Overview","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2201.12961","title":"Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations","created":"2022-01-31","cited_by_count":18,"area":null},{"id":"2408.07307","title":"Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery","created":"2024-08-14","cited_by_count":18,"area":null},{"id":"2507.00191","title":"Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions","created":"2025-06-30","cited_by_count":18,"area":null},{"id":"2109.03777","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","created":"2021-09-08","cited_by_count":17,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","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":"2112.07605","title":"The King is Naked: on the Notion of Robustness for Natural Language Processing","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2203.14679","title":"Brain-inspired Multilayer Perceptron with Spiking Neurons","created":"2022-03-28","cited_by_count":16,"area":null},{"id":"2106.14882","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","created":"2021-06-28","cited_by_count":15,"area":null}],"next_cursor":"100"}