{"total":316,"rows":[{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210,"area":null},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302,"area":null},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260,"area":null},{"id":"2111.13802","title":"Factorized Fourier Neural Operators","created":"2021-11-27","cited_by_count":249,"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":"2307.03756","title":"FITS: Modeling Time Series with $10k$ Parameters","created":"2023-07-06","cited_by_count":195,"area":null},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148,"area":null},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"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":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2302.04501","title":"MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing","created":"2023-02-09","cited_by_count":53,"area":null},{"id":"2303.16513","title":"Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution","created":"2023-03-29","cited_by_count":52,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"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":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2412.17739","title":"Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization","created":"2024-12-23","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37,"area":null},{"id":"2301.11509","title":"Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation","created":"2023-01-27","cited_by_count":32,"area":null},{"id":"2109.15142","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","created":"2021-09-30","cited_by_count":31,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31,"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":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30,"area":null},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2410.09836","title":"Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift","created":"2024-10-13","cited_by_count":24,"area":null},{"id":"2203.13639","title":"Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness","created":"2022-03-25","cited_by_count":23,"area":null},{"id":"2303.03932","title":"FFT-based Dynamic Token Mixer for Vision","created":"2023-03-07","cited_by_count":22,"area":null},{"id":"2403.13335","title":"Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection","created":"2024-03-20","cited_by_count":22,"area":null},{"id":"2110.13572","title":"Periodic Activation Functions Induce Stationarity","created":"2021-10-26","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":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2205.14375","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","created":"2022-05-28","cited_by_count":19,"area":null},{"id":"2212.06385","title":"TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2212.08151","title":"First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting","created":"2022-12-15","cited_by_count":19,"area":null},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2401.00955","title":"Learning Long Sequences in Spiking Neural Networks","created":"2023-12-14","cited_by_count":19,"area":null},{"id":"2406.16531","title":"GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2208.06551","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","created":"2022-08-13","cited_by_count":18,"area":null},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","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":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","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":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16,"area":null},{"id":"2403.19928","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2203.05142","title":"IAE-Net: Integral Autoencoders for Discretization-Invariant Learning","created":"2022-03-10","cited_by_count":15,"area":null},{"id":"2312.01758","title":"CILF-CIAE: CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation","created":"2023-12-04","cited_by_count":15,"area":null},{"id":"2305.19534","title":"Recasting Self-Attention with Holographic Reduced Representations","created":"2023-05-31","cited_by_count":14,"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":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2201.02711","title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","created":"2022-01-07","cited_by_count":13,"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":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2410.02675","title":"FAN: Fourier Analysis Networks","created":"2024-10-03","cited_by_count":13,"area":null},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2205.02100","title":"MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series","created":"2022-05-04","cited_by_count":12,"area":null},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2207.10284","title":"Multi Resolution Analysis (MRA) for Approximate Self-Attention","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2209.13017","title":"Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2309.10371","title":"Generative AI vs. AGI: The Cognitive Strengths and Weaknesses of Modern LLMs","created":"2023-09-19","cited_by_count":11,"area":null},{"id":"2312.04234","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","created":"2023-12-07","cited_by_count":11,"area":null},{"id":"2401.16923","title":"Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation","created":"2024-01-30","cited_by_count":11,"area":null},{"id":"2403.02619","title":"Training Machine Learning models at the Edge: A Survey","created":"2024-03-05","cited_by_count":11,"area":null},{"id":"2110.09823","title":"An Empirical Study: Extensive Deep Temporal Point Process","created":"2021-10-19","cited_by_count":10,"area":null},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2206.09418","title":"LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2210.07661","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2307.00430","title":"WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution","created":"2023-07-01","cited_by_count":10,"area":null},{"id":"2307.16418","title":"DRAW: Defending Camera-shooted RAW against Image Manipulation","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2410.11382","title":"Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space","created":"2024-10-15","cited_by_count":10,"area":null},{"id":"2504.07099","title":"Time Series Analysis in Frequency Domain: A Survey of Open Challenges, Opportunities and Benchmarks","created":"2025-02-12","cited_by_count":10,"area":null},{"id":"2109.02418","title":"Multitask Balanced and Recalibrated Network for Medical Code Prediction","created":"2021-09-06","cited_by_count":9,"area":null},{"id":"2203.03689","title":"WaveMix: Resource-efficient Token Mixing for Images","created":"2022-03-07","cited_by_count":9,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2312.11023","title":"Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector","created":"2023-12-18","cited_by_count":9,"area":null}],"next_cursor":"100"}