{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:28:36Z","timestamp":1773804516060,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"34","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression---targeting ultra-low-bit quantization for both activations and weights---from a Fourier frequency domain perspective. We propose SpecQuant, a two-stage framework that tackles activation outliers and cross-channel variance. In the first stage, activation outliers are smoothed and transferred into the weight matrix to simplify downstream quantization. In the second stage, we apply channel-wise low-frequency Fourier truncation to suppress high-frequency components while preserving essential signal energy, improving quantization robustness. Our method builds on the principle that most of the weight energy is concentrated in low-frequency components, which can be retained with minimal impact on model accuracy. To enable runtime adaptability, we introduce a lightweight truncation module during inference that adjusts truncation thresholds based on channel characteristics. On LLaMA-3 8B, SpecQuant achieves 4-bit quantization for both weights and activations, narrowing the zero-shot accuracy gap to only 1.5% compared to full precision, while delivering 2\u00d7 faster inference and 3\u00d7 lower memory usage.<\/jats:p>","DOI":"10.1609\/aaai.v40i34.40112","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:25:03Z","timestamp":1773800703000},"page":"28786-28794","source":"Crossref","is-referenced-by-count":0,"title":["SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization"],"prefix":"10.1609","volume":"40","author":[{"given":"Zhixiong","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibing","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/40112\/44073","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40112\/44073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:25:03Z","timestamp":1773800703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i34.40112","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]]}}}