Haoran Li | Xu Labhttps://xushidang-lab.netlify.app/author/haoran-li/Haoran LiHugo Blox Builder (https://hugoblox.com)en-usThu, 01 Jan 2026 00:00:00 +0000https://xushidang-lab.netlify.app/media/icon_hu16174698449664387463.pngHaoran Lihttps://xushidang-lab.netlify.app/author/haoran-li/AnyAvatar: High-Fidelity Gaussian Head Avatars under Uncalibrated Camera Settingshttps://xushidang-lab.netlify.app/publication/2026-anyavatar/Thu, 01 Jan 2026 00:00:00 +0000https://xushidang-lab.netlify.app/publication/2026-anyavatar/<p>Accepted for ACM International Conference on Multimedia (ACM MM) 2026. Proceedings details will be added when available.</p> <p><a href="https://aishiweilai.github.io/AnyAvatar.github.io/" target="_blank" rel="noopener">Visit the authors’ project page</a>.</p>Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstructionhttps://xushidang-lab.netlify.app/publication/2025-cdsr-whole-slide-images/Sun, 03 Aug 2025 00:00:00 +0000https://xushidang-lab.netlify.app/publication/2025-cdsr-whole-slide-images/<p>A conference version has been accepted at PRCV 2026. The accepted title is “Learning Whole Slide Image Representations from Few High-Resolution Patches via Cascaded Dual-Scale Reconstruction”. The author list and downloadable citation on this page describe the 2025 preprint; the conference citation will be added after its final metadata is confirmed.</p> <p>Read the <a href="https://arxiv.org/abs/2508.01641" target="_blank" rel="noopener">preprint and its version history</a>.</p>