{"total":136,"rows":[{"id":"2312.10794","title":"A mathematical perspective on Transformers","created":"2023-12-17","cited_by_count":164,"area":null},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76,"area":null},{"id":"2306.13465","title":"3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation","created":"2023-06-23","cited_by_count":70,"area":null},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2406.09009","title":"Fredformer: Frequency Debiased Transformer for Time Series Forecasting","created":"2024-06-13","cited_by_count":45,"area":null},{"id":"2303.06562","title":"ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond","created":"2023-03-12","cited_by_count":39,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2306.04990","title":"Multi-Architecture Multi-Expert Diffusion Models","created":"2023-06-08","cited_by_count":35,"area":"diffusion"},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32,"area":null},{"id":"2503.13695","title":"Mitigating Spectral Bias in Neural Operators via High-Frequency Scaling for Physical Systems","created":"2025-03-17","cited_by_count":31,"area":"diffusion"},{"id":"2309.00121","title":"Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation","created":"2023-08-31","cited_by_count":30,"area":null},{"id":"2407.09618","title":"The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges","created":"2024-07-12","cited_by_count":29,"area":null},{"id":"2312.10325","title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","created":"2023-12-16","cited_by_count":28,"area":null},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27,"area":"inference"},{"id":"2308.09281","title":"Diverse Cotraining Makes Strong Semi-Supervised Segmentor","created":"2023-08-18","cited_by_count":26,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2303.09735","title":"SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2501.00658","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","created":"2024-12-31","cited_by_count":18,"area":"ssm"},{"id":"2309.06922","title":"Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning","created":"2023-09-13","cited_by_count":17,"area":null},{"id":"2203.06578","title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","created":"2022-03-13","cited_by_count":16,"area":null},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2211.15362","title":"Exploring the Coordination of Frequency and Attention in Masked Image Modeling","created":"2022-11-28","cited_by_count":12,"area":null},{"id":"2307.09763","title":"Towards Building More Robust Models with Frequency Bias","created":"2023-07-19","cited_by_count":12,"area":null},{"id":"2404.04531","title":"Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation","created":"2024-04-06","cited_by_count":12,"area":null},{"id":"2210.08122","title":"Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again","created":"2022-10-14","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":"2402.15989","title":"PIDformer: Transformer Meets Control Theory","created":"2024-02-25","cited_by_count":11,"area":null},{"id":"2309.00108","title":"Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection","created":"2023-08-31","cited_by_count":10,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2505.19105","title":"Latent Mamba Operator for Partial Differential Equations","created":"2025-05-25","cited_by_count":10,"area":"ssm"},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2410.24200","title":"Length-Induced Embedding Collapse in PLM-based Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2412.11076","title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","created":"2024-12-15","cited_by_count":9,"area":null},{"id":"2209.07026","title":"Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2305.15033","title":"SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models","created":"2023-05-24","cited_by_count":7,"area":"mllm"},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2406.13762","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2409.02866","title":"Hybrid-Segmentor: A Hybrid Approach to Automated Fine-Grained Crack Segmentation in Civil Infrastructure","created":"2024-09-04","cited_by_count":7,"area":null},{"id":"2407.08567","title":"Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2412.10776","title":"Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification","created":"2024-12-14","cited_by_count":6,"area":null},{"id":"2412.16233","title":"WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2507.01945","title":"LongAnimation: Long Animation Generation with Dynamic Global-Local Memory","created":"2025-07-02","cited_by_count":6,"area":null},{"id":"2512.03870","title":"Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers","created":"2025-12-03","cited_by_count":6,"area":"inference"},{"id":"2310.05654","title":"No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2403.00012","title":"PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2406.01189","title":"MultiMax: Sparse and Multi-Modal Attention Learning","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2407.21640","title":"MSA$^2$Net: Multi-scale Adaptive Attention-guided Network for Medical Image Segmentation","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2412.10448","title":"Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction","created":"2024-12-11","cited_by_count":5,"area":"diffusion"},{"id":"2507.21244","title":"Bubbleformer: Forecasting Boiling with Transformers","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2205.10505","title":"A Study on Transformer Configuration and Training Objective","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2505.08516","title":"Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain","created":"2025-05-13","cited_by_count":4,"area":null},{"id":"2505.15325","title":"SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2510.16807","title":"Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads","created":"2025-10-19","cited_by_count":4,"area":"inference"},{"id":"2603.05117","title":"SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation","created":"2026-03-05","cited_by_count":4,"area":"diffusion"},{"id":"2203.08739","title":"What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study","created":"2022-03-16","cited_by_count":3,"area":null},{"id":"2304.14919","title":"ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges","created":"2023-04-26","cited_by_count":3,"area":null},{"id":"2308.06548","title":"Revisiting Vision Transformer from the View of Path Ensemble","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2308.13442","title":"Unlocking Fine-Grained Details with Wavelet-based High-Frequency Enhancement in Transformers","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2403.07942","title":"Attacking Transformers with Feature Diversity Adversarial Perturbation","created":"2024-03-10","cited_by_count":3,"area":null},{"id":"2403.18535","title":"Theoretical Bound-Guided Hierarchical VAE for Neural Image Codecs","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2407.14296","title":"Foundation Models for Autonomous Robots in Unstructured Environments","created":"2024-07-19","cited_by_count":3,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.00687","title":"Transformer Meets Twicing: Harnessing Unattended Residual Information","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2506.10813","title":"Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2510.08389","title":"Revisiting Hallucination Detection with Effective Rank-based Uncertainty","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2511.21477","title":"Frequency-Aware Token Reduction for Efficient Vision Transformer","created":"2025-11-26","cited_by_count":3,"area":"inference"},{"id":"2407.15516","title":"Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2503.18337","title":"Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2503.23764","title":"WaveFormer: A 3D Transformer with Wavelet-Driven Feature Representation for Efficient Medical Image Segmentation","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2506.13678","title":"A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2511.06285","title":"Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2602.00217","title":"Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2212.10197","title":"EIT: Enhanced Interactive Transformer","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2310.14921","title":"PartialFormer: Modeling Part Instead of Whole for Machine Translation","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2312.07753","title":"Polynomial-based Self-Attention for Table Representation learning","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2409.11051","title":"Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2411.17296","title":"GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2411.19297","title":"Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2504.02016","title":"Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.16455","title":"Cross Paradigm Representation and Alignment Transformer for Image Deraining","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2506.15929","title":"Moir\\'eXNet: Adaptive Multi-Scale Demoir\\'eing with Linear Attention Test-Time Training and Truncated Flow Matching Prior","created":"2025-06-19","cited_by_count":1,"area":"diffusion"},{"id":"2508.12787","title":"Wavy Transformer","created":"2025-08-18","cited_by_count":1,"area":null},{"id":"2509.00102","title":"ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Models","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2510.15101","title":"Operator Flow Matching for Timeseries Forecasting","created":"2025-10-16","cited_by_count":1,"area":"diffusion"},{"id":"2510.16446","title":"VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2510.27547","title":"MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.05745","title":"Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder","created":"2025-11-07","cited_by_count":1,"area":"moe"},{"id":"2511.11700","title":"EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2511.20698","title":"On the Role of Hidden States of Modern Hopfield Network in Transformer","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.09010","title":"Towards Lossless Ultimate Vision Token Compression for VLMs","created":"2025-12-09","cited_by_count":1,"area":"mllm"},{"id":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null}],"next_cursor":"100"}