{"total":91,"rows":[{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2102.10249","title":"Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction","created":"2021-02-20","cited_by_count":68,"area":null},{"id":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60,"area":null},{"id":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"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":"2208.10099","title":"Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect","created":"2022-08-22","cited_by_count":47,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","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":"2312.05976","title":"A Representative Study on Human Detection of Artificially Generated Media Across Countries","created":"2023-12-10","cited_by_count":22,"area":null},{"id":"2203.10726","title":"TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers","created":"2022-03-21","cited_by_count":21,"area":null},{"id":"2104.07838","title":"Investigating Failures of Automatic Translation in the Case of Unambiguous Gender","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2304.07235","title":"Mapping of attention mechanisms to a generalized Potts model","created":"2023-04-14","cited_by_count":19,"area":null},{"id":"2109.15144","title":"A Review of Text Style Transfer using Deep Learning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17,"area":null},{"id":"2310.01749","title":"Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns","created":"2023-10-03","cited_by_count":17,"area":null},{"id":"2104.13100","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2209.13271","title":"The Curse of Unrolling: Rate of Differentiating Through Optimization","created":"2022-09-27","cited_by_count":16,"area":null},{"id":"2303.01542","title":"Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention","created":"2023-03-02","cited_by_count":16,"area":null},{"id":"2106.06038","title":"Modeling Hierarchical Structures with Continuous Recursive Neural Networks","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2110.06865","title":"Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments","created":"2021-10-13","cited_by_count":14,"area":null},{"id":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2404.03936","title":"Deep Learning for Satellite Image Time Series Analysis: A Review","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2112.13310","title":"Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence","created":"2021-12-26","cited_by_count":12,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2308.03312","title":"Exploiting Code Symmetries for Learning Program Semantics","created":"2023-08-07","cited_by_count":10,"area":null},{"id":"2403.08293","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2112.04075","title":"Active Sensing for Communications by Learning","created":"2021-12-08","cited_by_count":9,"area":null},{"id":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2109.09587","title":"Recommender systems based on graph embedding techniques: A comprehensive review","created":"2021-09-20","cited_by_count":8,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2407.17406","title":"Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models","created":"2024-07-24","cited_by_count":8,"area":null},{"id":"2108.04879","title":"Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2205.09956","title":"Structured Attention Composition for Temporal Action Localization","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2209.11223","title":"UniColor: A Unified Framework for Multi-Modal Colorization with Transformer","created":"2022-09-22","cited_by_count":7,"area":null},{"id":"2210.03183","title":"Compositional Generalisation with Structured Reordering and Fertility Layers","created":"2022-10-06","cited_by_count":6,"area":null},{"id":"2109.08382","title":"To be Closer: Learning to Link up Aspects with Opinions","created":"2021-09-17","cited_by_count":5,"area":null},{"id":"2112.11789","title":"DRF Codes: Deep SNR-Robust Feedback Codes","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2301.05864","title":"Recent advances in artificial intelligence for retrosynthesis","created":"2023-01-14","cited_by_count":5,"area":null},{"id":"2303.15761","title":"Learning Second-Order Attentive Context for Efficient Correspondence Pruning","created":"2023-03-28","cited_by_count":5,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2404.08263","title":"Relational Prompt-based Pre-trained Language Models for Social Event Detection","created":"2024-04-12","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":"2406.11085","title":"Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2208.00579","title":"Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization","created":"2022-08-01","cited_by_count":4,"area":null},{"id":"2304.04556","title":"Attention: Marginal Probability is All You Need?","created":"2023-04-07","cited_by_count":4,"area":null},{"id":"2306.15103","title":"Structured Dialogue Discourse Parsing","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2406.13781","title":"A Primal-Dual Framework for Transformers and Neural Networks","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2402.09947","title":"Explaining Probabilistic Models with Distributional Values","created":"2024-02-15","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":"2509.07324","title":"Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2511.01202","title":"Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2103.03510","title":"Variational Structured Attention Networks for Deep Visual Representation Learning","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2108.03578","title":"Language Model Evaluation in Open-ended Text Generation","created":"2021-08-08","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2206.00206","title":"Transformer with Fourier Integral Attentions","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","cited_by_count":2,"area":null},{"id":"2308.03291","title":"SynJax: Structured Probability Distributions for JAX","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2406.07812","title":"To be Continuous, or to be Discrete, Those are Bits of Questions","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2509.11390","title":"Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning","created":"2025-09-14","cited_by_count":2,"area":null},{"id":"2607.07678","title":"How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2109.05182","title":"Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2109.06966","title":"Searching for More Efficient Dynamic Programs","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2205.06801","title":"Twitter-Based Gender Recognition Using Transformers","created":"2022-04-24","cited_by_count":1,"area":null},{"id":"2209.01914","title":"Scene Text Recognition with Single-Point Decoding Network","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2209.11628","title":"A Neural Model for Regular Grammar Induction","created":"2022-09-23","cited_by_count":1,"area":null},{"id":"2308.05115","title":"PTransIPs: Identification of phosphorylation sites enhanced by protein PLM embeddings","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2312.02748","title":"Compositional Generalization for Data-to-Text Generation","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2506.22978","title":"A Systematic Study of Compositional Syntactic Transformer Language Models","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2507.20871","title":"FedABC: Attention-Based Client Selection for Federated Learning with Long-Term View","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2511.09766","title":"Ksurf-Drone: Attention Kalman Filter for Contextual Bandit Optimization in Cloud Resource Allocation","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2603.20316","title":"Bypassing Document Ingestion: An MCP Approach to Financial Q&A","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.22476","title":"Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2108.03989","title":"Spatial-Temporal Deep Intention Destination Networks for Online Travel Planning","created":"2021-08-09","cited_by_count":0,"area":null},{"id":"2110.02057","title":"Structured Prediction in NLP -- A survey","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2202.03755","title":"Can We Generate Shellcodes via Natural Language? An Empirical Study","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2210.17497","title":"Leveraging Pre-trained Models for Failure Analysis Triplets Generation","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2305.07988","title":"Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2308.03429","title":"RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modelling","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2404.02583","title":"Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2406.02632","title":"Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2408.02685","title":"Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2501.09451","title":"Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2503.10655","title":"Language modelling techniques for analysing the impact of human genetic variation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2604.09674","title":"How LLMs Might Think","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.19138","title":"INDEQS: Informed Neural controlled Differential EQuationS","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.07673","title":"From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}