Shiyu Huang

机构：Open Society, Hi-Z Technology (United States) · ORCID：0009-0008-9541-0622

发表论文 11 篇 · 总被引 20 次 · h-index 3

代表论文

• MotionBench: Benchmarking and Improving Fine-Grained Video Motion Understanding for Vision Language Models (2025 · 被引 9)
• CogVLM2: Visual Language Models for Image and Video Understanding (2024 · arXiv (Cornell University) · 被引 7)
• VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation (2026 · Proceedings of the AAAI Conference on Artificial Intelligence · 被引 4)
• DAF‐Retinex: Preserve the image detailed features and restore the reflected image (2024 · IET Image Processing · 被引 1)
• OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments (2026 · arXiv (Cornell University))
• OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments (2026 · arXiv (Cornell University))