{"total":23,"rows":[{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2109.05644","title":"SHAPE: Shifted Absolute Position Embedding for Transformers","created":"2021-09-13","cited_by_count":37,"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":"2210.11151","title":"Transformer-based Entity Typing in Knowledge Graphs","created":"2022-10-20","cited_by_count":13,"area":null},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","cited_by_count":13,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"area":null},{"id":"2209.01676","title":"Time-distance vision transformers in lung cancer diagnosis from longitudinal computed tomography","created":"2022-09-04","cited_by_count":9,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2304.02836","title":"Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification","created":"2023-04-06","cited_by_count":8,"area":null},{"id":"2102.09206","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder","created":"2021-02-18","cited_by_count":7,"area":null},{"id":"2404.00424","title":"Quantformer: from attention to profit with a quantitative transformer trading strategy","created":"2024-03-30","cited_by_count":6,"area":null},{"id":"2405.17509","title":"Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2111.15159","title":"CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer","created":"2021-11-30","cited_by_count":4,"area":null},{"id":"2307.02912","title":"LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2204.08688","title":"DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2302.06683","title":"Enhancing Multivariate Time Series Classifiers through Self-Attention and Relative Positioning Infusion","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2506.14786","title":"PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2209.06131","title":"User recommendation system based on MIND dataset","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2503.10733","title":"TAU: Modeling Temporal Consistency Through Temporal Attentive U-Net for PPG Peak Detection","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2512.17696","title":"Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting","created":"2025-12-19","cited_by_count":0,"area":null}],"next_cursor":null}