{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:13:15Z","timestamp":1758089595065,"version":"3.44.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133343","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["DIAS: Distance-based Attention Sparsity for Ultra-Long-Sequence Transformer with Tree-like Processing-in-Memory Architecture"],"prefix":"10.1109","author":[{"given":"Zekai","family":"Chen","sequence":"first","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Wan","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Yu","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqing","family":"Li","sequence":"additional","affiliation":[{"name":"LEFT\/BNRist\/SKLSNC, Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref3","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"ref5","first-page":"27268","article-title":"Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Zhou"},{"key":"ref6","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref8","article-title":"Kvquant: Towards 10 million context length LLM inference with KV cache quantization","author":"Hooper","year":"2024","journal-title":"arXiv preprint arXiv:2401.18079"},{"key":"ref9","article-title":"Kivi: A tuning-free asymmetric 2bit quantization for KV cache","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2402.02750"},{"key":"ref10","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Leviathan"},{"key":"ref11","article-title":"Online speculative decoding","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2310.07177"},{"key":"ref12","article-title":"PADRe: A unifying polynomial attention drop-in replacement for efficient vision transformer","author":"Letourneau","year":"2024","journal-title":"arXiv preprint arXiv:2407.11306"},{"key":"ref13","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv preprint arXiv:2001.04451"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655953"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint arXiv:2309.17453"},{"key":"ref17","first-page":"34661","article-title":"H2O: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"InfLLM: Training-free long-context extrapolation for LLMs with an efficient context memory","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Xiao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref20","article-title":"You only cache once: Decoder-decoder architectures for language models","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2405.05254"},{"key":"ref21","article-title":"RazorAttention: Efficient KV cache compression through retrieval heads","author":"Tang","year":"2024","journal-title":"arXiv preprint arXiv:2407.15891"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2909204"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/98524.98564"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1132956.1132959"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00323"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247946"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref33","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref34","article-title":"Learning to (learn at test time): RNNs with expressive hidden states","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2407.04620"},{"key":"ref35","article-title":"LM-Infinite: Simple on-the-fly length generalization for large language models","volume":"abs\/2308.16137","author":"Han","year":"2023","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133343.pdf?arnumber=11133343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:32:15Z","timestamp":1758000735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133343","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}