{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:01:59Z","timestamp":1780639319525,"version":"3.54.1"},"reference-count":27,"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\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]},{"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\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","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\/date69613.2026.11539329","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":["AO-BFP: An Adaptive Mixed-Precision and Outlier-Aware Block Floating-Point Accelerator for Large Language Model Inference"],"prefix":"10.23919","author":[{"given":"Yifan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zetao","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendi","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyan","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"ref3","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992912"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993129"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref7","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","author":"Zhao","year":"2024","journal-title":"MLSys"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/78.492531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.617"},{"key":"ref10","article-title":"Meta llama"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3547732"},{"key":"ref13","article-title":"Bie: Bi-exponent block floating-point for large language models quantization","volume-title":"Forty-first International Conference on Machine Learning","author":"Zou"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10248013"},{"key":"ref15","article-title":"Bitq: Tailoring block floating point precision for improved dnn efficiency on resource-constrained devices","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref16","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref18","first-page":"4954","article-title":"Hessian-based analysis of large batch training and robustness to adversaries","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Yao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3253050"},{"key":"ref20","article-title":"Smoothquant: accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Xiao"},{"key":"ref21","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shao"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00084"},{"key":"ref24","article-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2024","journal-title":"MLSys"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"}],"event":{"name":"2026 Design, Automation & 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 & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539329.pdf?arnumber=11539329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:14:52Z","timestamp":1780636492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539329","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}