Peiqiang Wang | LLAM | Lab of Large Audio Modelhttps://largeaudiomodel.com/author/peiqiang-wang/Peiqiang WangWowchemy (https://wowchemy.com)en-usLab of Large Audio ModelSun, 06 Sep 2026 00:00:00 +0000https://largeaudiomodel.com/media/logo_hu6d226c372fb6e14ffc932dabb016ec70_112597_300x300_fit_lanczos_3.pngPeiqiang Wanghttps://largeaudiomodel.com/author/peiqiang-wang/WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimizationhttps://largeaudiomodel.com/publication/2026/tao2026windowquant/Sun, 06 Sep 2026 00:00:00 +0000https://largeaudiomodel.com/publication/2026/tao2026windowquant/<div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div>