{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:53:11Z","timestamp":1773193991554,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T00:00:00Z","timestamp":1739664000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T00:00:00Z","timestamp":1739664000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62125403,92164301,62304121"],"award-info":[{"award-number":["62125403,92164301,62304121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0115201"],"award-info":[{"award-number":["2022ZD0115201"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,16]]},"DOI":"10.1109\/isscc49661.2025.10904774","type":"proceedings-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T18:33:12Z","timestamp":1741285992000},"page":"420-422","source":"Crossref","is-referenced-by-count":11,"title":["23.8 An 88.36TOPS\/W Bit-Level-Weight-Compressed Large-Language-Model Accelerator with Cluster-Aligned INT-FP-GEMM and Bi-Dimensional Workflow Reformulation"],"prefix":"10.1109","author":[{"given":"Yubin","family":"Qin","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Jiachen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Zhiwei","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Yushu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]},{"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume":"abs\/2303.08774","year":"2023","journal-title":"CoRR"},{"key":"ref2","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","volume":"abs\/2307.09288","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref3","article-title":"OPT: Open Pre-Trained Transformer Language Models","volume":"abs\/2205.01068","author":"Zhang","year":"2022","journal-title":"CoRR"},{"key":"ref4","article-title":"Gemini 1.5: Unlocking Multimodal Understanding Across Millions of Tokens of Context","volume":"abs\/2403.05530","author":"Reid","year":"2024","journal-title":"CoRR"},{"key":"ref5","article-title":"Scaling Laws for Neural Language Models","volume":"abs\/2001.08361","author":"Kaplan","year":"2020","journal-title":"CoRR"},{"key":"ref6","first-page":"22964","article-title":"What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?","author":"Wang","year":"2022","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref8","article-title":"Roberta: A Robustly Optimized BERT Pretraining Approach","volume":"abs\/1907.11692","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref10","article-title":"SpQR: A Sparse-Quantized Representation For Near-Lossless LLM Weight Compression","author":"Dettmers","year":"2024","journal-title":"ICLR"},{"key":"ref11","article-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-Trained Transformers","author":"Frantar","year":"2023","journal-title":"ICLR"},{"key":"ref12","volume-title":"NVIDIA A100 Tensor Core GPU","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731686"},{"key":"ref14","first-page":"248","article-title":"MulTCIM: A 28nm 2.24\u03bcJ\/Token Attention-Token-Bit Hybrid Sparse Digital CIM-Based Accelerator for Multimodal Transformers","volume-title":"ISSCC","author":"Tu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067360"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631311"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3397189"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185403"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067817"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00079"},{"key":"ref25","article-title":"LLMZip: Lossless Text Compression using Large Language Models","volume":"abs\/2306.04050","author":"Valmeekam","year":"2023","journal-title":"CoRR"}],"event":{"name":"2025 IEEE International Solid-State Circuits Conference (ISSCC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,2,16]]},"end":{"date-parts":[[2025,2,20]]}},"container-title":["2025 IEEE International Solid-State Circuits Conference (ISSCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10904417\/10904496\/10904774.pdf?arnumber=10904774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:34:50Z","timestamp":1744997690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10904774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,16]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/isscc49661.2025.10904774","relation":{},"subject":[],"published":{"date-parts":[[2025,2,16]]}}}