{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:01:17Z","timestamp":1780639277078,"version":"3.54.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013105","name":"Shanghai Rising-Star Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013105","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539383","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Endor: Exploit Nearly-Decode-Only Opportunities of LLM Reasoning on Near-Memory Architecture"],"prefix":"10.23919","author":[{"given":"Jun","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiancai","family":"Ye","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Ning","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llm reasoners: New evaluation, library, and analysis of step-by-step reasoning with large language models","author":"Hao","year":"2024"},{"key":"ref2","article-title":"Openr: An open source framework for advanced reasoning with large language models","author":"Wang","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2066"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref5","article-title":"Skeleton-of-thought: Prompting LLMs for efficient parallel generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ning"},{"key":"ref6","article-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024"},{"key":"ref7","volume-title":"Learning to reason with llms"},{"key":"ref8","article-title":"Training verifiers to solve math word problems, 2021","author":"Cobbe","year":"2021"},{"key":"ref9","article-title":"Can llms learn by teaching for better reasoning? a preliminary study","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Ning"},{"key":"ref10","volume-title":"Openai o1-mini advancing cost-efficient reasoning"},{"key":"ref11","article-title":"Moa: Mixture of sparse attention for automatic large language model compression","author":"Fu","year":"2024"},{"key":"ref12","article-title":"Evaluating quantized large language models","author":"Li","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527388"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247946"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"ref17","first-page":"28935","article-title":"Eagle: speculative sampling requires rethinking feature uncertainty","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Li"},{"key":"ref18","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00071"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00126"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716267"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00129"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00128"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3333759"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref31","volume-title":"Design compiler","author":"Synopsys"},{"key":"ref32","article-title":"L3: Dimm-pim integrated architecture and coordination for scalable long-context llm inference","author":"Liu","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref36","article-title":"Measuring mathematical problem solving with the math dataset","author":"Hendrycks","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"}],"event":{"name":"2026 Design, Automation &amp; Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539383.pdf?arnumber=11539383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:11:07Z","timestamp":1780636267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":37,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539383","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}