{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:06:56Z","timestamp":1790269616801,"version":"4.1.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["23KJ1594"],"award-info":[{"award-number":["23KJ1594"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3695094","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:52:22Z","timestamp":1779306742000},"page":"11952-11963","source":"Crossref","is-referenced-by-count":3,"title":["SeqPE: Transformer With Sequential Position Encoding"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-8648","authenticated-orcid":false,"given":"Huayang","family":"Li","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)","place":["Nara, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4398-8867","authenticated-orcid":false,"given":"Yahui","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7172-3411","authenticated-orcid":false,"given":"Hongyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)","place":["Nara, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3444-8383","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Independent Researchers"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leyang","family":"Cui","sequence":"additional","affiliation":[{"name":"Independent Researchers"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Bi","sequence":"additional","affiliation":[{"name":"Independent Researchers"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8543-3953","authenticated-orcid":false,"given":"Peilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8349-3522","authenticated-orcid":false,"given":"Taro","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)","place":["Nara, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The Falcon series of open language models","author":"Almazrouei","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.323"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref4","first-page":"14352","article-title":"CLEX: Continuous length extrapolation for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref5","first-page":"6572","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2018"},{"key":"ref6","article-title":"Extending context window of large language models via positional interpolation","author":"Chen","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref8","article-title":"Emu3.5: Native multimodal models are world learners","author":"Cui","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","article-title":"An image is worth 16 x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref11","article-title":"ViTAR: Vision transformer with any resolution","author":"Fan","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref13","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.99"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_17"},{"key":"ref21","article-title":"RULER: What\u2019s the real context size of your long-context language models","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Hsieh","year":"2024"},{"key":"ref22","first-page":"24932","article-title":"Fourier position embedding: Enhancing attention\u2019s periodic extension for length generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hua","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1082"},{"key":"ref26","article-title":"Rethinking positional encoding in language pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ke","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgmcn.5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","first-page":"6327","article-title":"Learning to encode position for transformer with continuous dynamical model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","first-page":"87386","article-title":"Base of rope bounds context length","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Men","year":"2024"},{"key":"ref34","first-page":"47339","article-title":"LieRE: Generalizing rotary position encodings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostmeier","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0970"},{"key":"ref36","first-page":"31932","article-title":"YaRN: Efficient context window extension of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2024"},{"key":"ref37","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Press","year":"2021"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"issue":"8","key":"ref39","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref40","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01952"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.161"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref48","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref49","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref50","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Den","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","article-title":"Encoding word order in complex embeddings","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-industry.6"},{"key":"ref54","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2150"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.582"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"},{"key":"ref58","first-page":"6446","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2025"},{"key":"ref59","first-page":"18940","article-title":"PoSE: Efficient context window extension of LLMS via positional skip-wise training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11526967.pdf?arnumber=11526967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:40:05Z","timestamp":1790268005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11526967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3695094","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}