{"total":38,"rows":[{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"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":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216,"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":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2106.04051","title":"Graph-MLP: Node Classification without Message Passing in Graph","created":"2021-06-08","cited_by_count":73,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2112.13715","title":"SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos","created":"2021-12-27","cited_by_count":64,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"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":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2409.00953","title":"PNVC: Towards Practical INR-based Video Compression","created":"2024-09-02","cited_by_count":19,"area":null},{"id":"2211.03885","title":"Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2109.03508","title":"RepNAS: Searching for Efficient Re-parameterizing Blocks","created":"2021-09-08","cited_by_count":11,"area":null},{"id":"2311.08759","title":"4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2206.13231","title":"QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2412.08341","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2110.13587","title":"Arbitrary Distribution Modeling with Censorship in Real-Time Bidding Advertising","created":"2021-10-26","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":"2304.06345","title":"ASR: Attention-alike Structural Re-parameterization","created":"2023-04-13","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":"2110.10939","title":"A channel attention based MLP-Mixer network for motor imagery decoding with EEG","created":"2021-10-21","cited_by_count":1,"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":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2503.03104","title":"RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2506.11305","title":"Don't Pay Attention","created":"2025-06-12","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":"2207.14545","title":"A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs","created":"2022-07-29","cited_by_count":0,"area":null},{"id":"2308.07110","title":"SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2311.05707","title":"FMViT: A multiple-frequency mixing Vision Transformer","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2402.16121","title":"Towards Accurate Post-training Quantization for Reparameterized Models","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2403.17607","title":"Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2405.13088","title":"Combining Relevance and Magnitude for Resource-Aware DNN Pruning","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2410.07987","title":"A transition towards virtual representations of visual scenes","created":"2024-10-10","cited_by_count":0,"area":null}],"next_cursor":null}