{"total":94,"rows":[{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"area":null},{"id":"2404.14197","title":"SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion","created":"2024-04-22","cited_by_count":76,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71,"area":null},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60,"area":null},{"id":"2103.04350","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","created":"2021-03-07","cited_by_count":51,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46,"area":null},{"id":"2109.12218","title":"Long-Range Transformers for Dynamic Spatiotemporal Forecasting","created":"2021-09-24","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2111.15127","title":"A Unified Pruning Framework for Vision Transformers","created":"2021-11-30","cited_by_count":40,"area":null},{"id":"2106.01040","title":"Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling","created":"2021-06-02","cited_by_count":35,"area":null},{"id":"2205.01643","title":"MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer","created":"2022-05-03","cited_by_count":35,"area":null},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2104.09340","title":"Code Structure Guided Transformer for Source Code Summarization","created":"2021-04-19","cited_by_count":30,"area":null},{"id":"2205.13891","title":"Transformers from an Optimization Perspective","created":"2022-05-27","cited_by_count":27,"area":null},{"id":"2304.12959","title":"Escaping the sentence-level paradigm in machine translation","created":"2023-04-25","cited_by_count":27,"area":null},{"id":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2110.15763","title":"How to Leverage Multimodal EHR Data for Better Medical Predictions?","created":"2021-10-29","cited_by_count":26,"area":null},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24,"area":null},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24,"area":null},{"id":"2412.00346","title":"CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention","created":"2024-11-30","cited_by_count":24,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2309.10808","title":"AI Foundation Models for Weather and Climate: Applications, Design, and Implementation","created":"2023-09-19","cited_by_count":21,"area":null},{"id":"2102.07349","title":"MATCH: Metadata-Aware Text Classification in A Large Hierarchy","created":"2021-02-15","cited_by_count":20,"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":"2211.13785","title":"PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving","created":"2022-11-24","cited_by_count":17,"area":"diffusion"},{"id":"2210.15497","title":"LSG Attention: Extrapolation of pretrained Transformers to long sequences","created":"2022-10-13","cited_by_count":16,"area":null},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2403.05822","title":"TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generation","created":"2024-03-09","cited_by_count":15,"area":null},{"id":"2308.13494","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2401.09261","title":"MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting","created":"2024-01-17","cited_by_count":12,"area":null},{"id":"2506.03880","title":"RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2206.14550","title":"SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences","created":"2022-06-29","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":"2111.04022","title":"MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information","created":"2021-11-07","cited_by_count":9,"area":null},{"id":"2208.12527","title":"Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer","created":"2022-08-26","cited_by_count":8,"area":"distill"},{"id":"2106.14742","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2503.01256","title":"Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners","created":"2025-03-03","cited_by_count":7,"area":null},{"id":"2106.08823","title":"Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2109.14396","title":"StoryDB: Broad Multi-language Narrative Dataset","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2112.05364","title":"Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2408.08258","title":"Snuffy: Efficient Whole Slide Image Classifier","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2101.06423","title":"Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching","created":"2021-01-16","cited_by_count":5,"area":null},{"id":"2209.13139","title":"Searching a High-Performance Feature Extractor for Text Recognition Network","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2301.01772","title":"Infomaxformer: Maximum Entropy Transformer for Long Time-Series Forecasting Problem","created":"2023-01-04","cited_by_count":5,"area":null},{"id":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2305.01883","title":"A Lightweight CNN-Transformer Model for Learning Traveling Salesman Problems","created":"2023-05-03","cited_by_count":4,"area":null},{"id":"2405.18706","title":"FocSAM: Delving Deeply into Focused Objects in Segmenting Anything","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2107.13054","title":"Exceeding the Limits of Visual-Linguistic Multi-Task Learning","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2205.14014","title":"What Dense Graph Do You Need for Self-Attention?","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2210.08431","title":"Modeling Context With Linear Attention for Scalable Document-Level Translation","created":"2022-10-16","cited_by_count":3,"area":null},{"id":"2307.01115","title":"MeT: A Graph Transformer for Semantic Segmentation of 3D Meshes","created":"2023-07-03","cited_by_count":3,"area":null},{"id":"2401.11252","title":"Automated Fusion of Multimodal Electronic Health Records for Better Medical Predictions","created":"2024-01-20","cited_by_count":3,"area":null},{"id":"2406.19391","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2407.02423","title":"On the Anatomy of Attention","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2108.04962","title":"Adaptive Multi-Resolution Attention with Linear Complexity","created":"2021-08-10","cited_by_count":2,"area":null},{"id":"2311.15335","title":"TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2312.14609","title":"BLSTM-Based Confidence Estimation for End-to-End Speech Recognition","created":"2023-12-22","cited_by_count":2,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2506.23551","title":"A unified framework for establishing the universal approximation of transformer-type architectures","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2203.10482","title":"DEIM: An effective deep encoding and interaction model for sentence matching","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2302.00894","title":"How to choose \"Good\" Samples for Text Data Augmentation","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2302.14346","title":"Sampled Transformer for Point Sets","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2311.13502","title":"Bitformer: An efficient Transformer with bitwise operation-based attention for Big Data Analytics at low-cost low-precision devices","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2409.05022","title":"Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2411.04013","title":"$k$NN Attention Demystified: A Theoretical Exploration for Scalable Transformers","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2412.02602","title":"CEGI: Measuring the trade-off between efficiency and carbon emissions for SLMs and VLMs","created":"2024-12-03","cited_by_count":1,"area":"mllm"},{"id":"2503.07968","title":"LabelCoRank: Revolutionizing Long Tail Multi-Label Classification with Co-Occurrence Reranking","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2602.01763","title":"A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2101.06397","title":"To Understand Representation of Layer-aware Sequence Encoders as Multi-order-graph","created":"2021-01-16","cited_by_count":0,"area":null},{"id":"2106.05221","title":"Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2111.15436","title":"KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers","created":"2021-11-30","cited_by_count":0,"area":null},{"id":"2210.03841","title":"Breaking BERT: Evaluating and Optimizing Sparsified Attention","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2210.10240","title":"Type-supervised sequence labeling based on the heterogeneous star graph for named entity recognition","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2308.10839","title":"Vision Transformer Pruning Via Matrix Decomposition","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2403.02411","title":"NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2404.04922","title":"Efficient Learnable Collaborative Attention for Single Image Super-Resolution","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2405.15953","title":"Activator: GLU Activation Function as the Core Component of a Vision Transformer","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2505.24531","title":"Transformers Are Universally Consistent","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.09612","title":"Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}