{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:04:39Z","timestamp":1773803079310,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"26","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Traditional post-training quantization (PTQ) is considered an effective approach to reduce model size and accelerate inference of large-scale language models (LLMs). However, existing low-rank PTQ methods require costly fine-tuning to determine a compromise rank for diverse data and layers in large models, failing to exploit their full potential. Additionally, the current SVD-based low-rank approximation compounds the computational overhead. In this work, we thoroughly analyze the varying effectiveness of low-rank approximation across different layers in representative models. Accordingly, we introduce Flexible Low-Rank Quantization (FLRQ), a novel solution designed to quickly identify the accuracy-optimal ranks and aggregate them to achieve minimal storage combinations. FLRQ comprises two powerful components, Rank1-Sketch-based Flexible Rank Selection (R1-FLR) and Best Low-rank Approximation under Clipping (BLC). R1-FLR applies the R1-Sketch with Gaussian projection for the fast low-rank approximation, enabling outlier-aware rank extraction for each layer. Meanwhile, BLC aims at minimizing the low-rank quantization error under the scaling and clipping strategy through an iterative method. FLRQ demonstrates strong effectiveness and robustness in comprehensive experiments, achieving state-of-the-art performance in both quantization quality and algorithm efficiency.<\/jats:p>","DOI":"10.1609\/aaai.v40i26.39283","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:29:46Z","timestamp":1773797386000},"page":"21369-21377","source":"Crossref","is-referenced-by-count":0,"title":["FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching"],"prefix":"10.1609","volume":"40","author":[{"given":"Hongyaoxing","family":"Gu","sequence":"first","affiliation":[]},{"given":"Lijuan","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Shuzi","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Fangfang","family":"Liu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39283\/43244","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39283\/43244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:29:46Z","timestamp":1773797386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"26","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i26.39283","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}