{"total":19,"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":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2309.05455","title":"Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation","created":"2023-09-11","cited_by_count":28,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2403.10805","title":"Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference","created":"2024-03-16","cited_by_count":6,"area":null},{"id":"2405.18874","title":"Are queries and keys always relevant? A case study on Transformer wave functions","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"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":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2108.13032","title":"Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning","created":"2021-08-30","cited_by_count":1,"area":null},{"id":"2603.04805","title":"Attention's Gravitational Field:A Power-Law Interpretation of Positional Correlation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2310.14633","title":"Extending Input Contexts of Language Models through Training on Segmented Sequences","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2404.16574","title":"Exploring Internal Numeracy in Language Models: A Case Study on ALBERT","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2608.03994","title":"When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.08032","title":"Flexible Motion Generation from Language and Style References","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}