{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T06:04:31Z","timestamp":1781762671982,"version":"3.54.5"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvlsi.2025.3650684","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:05:23Z","timestamp":1769115923000},"page":"1097-1109","source":"Crossref","is-referenced-by-count":2,"title":["TABv2: A Faster Ternary and Binary Neural Network Inference Library on the Edge"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9615-8456","authenticated-orcid":false,"given":"Guanshujie","family":"Fu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Systems Group, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5074-6940","authenticated-orcid":false,"given":"Olivier","family":"Fischer","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Systems Group, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-7643","authenticated-orcid":false,"given":"Shien","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Systems Group, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4396-6695","authenticated-orcid":false,"given":"Gustavo","family":"Alonso","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Systems Group, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"issue":"10","key":"ref2","first-page":"1613","article-title":"A survey of quantization methods for deep neural networks","volume":"45","author":"Yang","year":"2023","journal-title":"Chin. J. Eng."},{"key":"ref3","article-title":"A study of BFLOAT16 for deep learning training","author":"Kalamkar","year":"2019","journal-title":"arXiv:1905.12322"},{"key":"ref4","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00204"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16462"},{"key":"ref7","first-page":"14651","article-title":"FP8 quantization: The power of the exponent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kuzmin"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_24"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2137"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JCC62314.2024.00017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.39"},{"key":"ref12","first-page":"4107","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Hubara"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00517"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5912"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS51040.2020.00026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_20"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00357"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00034"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129393"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414539"},{"key":"ref24","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3508390"},{"key":"ref26","first-page":"110","article-title":"Instruction tables: Lists of instruction latencies, throughputs and micro-operation breakdowns for intel, amd and via cpus","volume":"93","author":"Fog","year":"2011","journal-title":"Copenhagen Univ. College Eng."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxx046"},{"key":"ref28","article-title":"DoReFa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"ref30","volume-title":"Pytorch Documentation","year":"2024"},{"key":"ref31","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref32","volume-title":"GPT-OSS: Open Source Release of GPT Components","year":"2024"},{"key":"ref33","volume-title":"Ocp Microscaling Formats MX V1.0 Spec","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref35","article-title":"TerViT: An efficient ternary vision transformer","author":"Xu","year":"2022","journal-title":"arXiv:2201.08050"},{"key":"ref36","article-title":"ViT-1.58b: Mobile vision transformers in the 1-bit era","author":"Yuan","year":"2024","journal-title":"arXiv:2406.18051"},{"key":"ref37","article-title":"TerDiT: Ternary diffusion models with transformers","author":"Lu","year":"2024","journal-title":"arXiv:2405.14854"},{"key":"ref38","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.11453"},{"key":"ref39","article-title":"1-bit AI infra: Part 1.1, fast and lossless BitNet b1.58 inference on CPUs","author":"Wang","year":"2024","journal-title":"arXiv:2410.16144"},{"key":"ref40","volume-title":"Intel Intrinsics Guide","year":"2024"},{"key":"ref41","volume-title":"Libpopcnt: Fast C\/C++ Bit Population Count Library","author":"Walisch","year":"2024"},{"key":"ref42","volume-title":"Using CUDA Warp-Level Primitives","author":"Lin","year":"2018"},{"key":"ref43","volume-title":"PTX ISA 9.0 Documentation","year":"2024"},{"key":"ref44","volume-title":"Cutlass","year":"2024"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11514136\/11360778.pdf?arnumber=11360778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:40:53Z","timestamp":1778564453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11360778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":44,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2025.3650684","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}