Shaoguang Wang

MPhil Student in Artificial Intelligence
The Hong Kong University of Science and Technology (HKUST), Guangzhou
Advised by Prof. Hui Xiong and Prof. Xuming Hu

I research efficient long video understanding with Multimodal Large Language Models (MLLMs) — query-aware keyframe selection, token-efficient prompting, and multimodal reasoning for Video-QA. My recent work has been published at CVPR and NeurIPS.

Selected Publications

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding — arXiv 2026. PDF
Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration — CVPR Findings 2026. PDF · Code
Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification — NeurIPS 2025. PDF · Code

Contact

Email: shaoguangwang9@gmail.com
Google Scholar: profile
GitHub: @shaoguangwang

This page renders its main content with JavaScript. For the full interactive experience, please enable JavaScript in your browser.

MPhil Student

HKUST (Guangzhou)

Guangzhou, China

Email Google Scholar GitHub

Publications

Awards

Projects