Yikang Zhou

发表论文 22 篇 · 总被引 191 次 · h-index 8

代表论文

• DVIS++: Improved Decoupled Framework for Universal Video Segmentation (2023 · arXiv.org · 被引 58)
• World Action Models: The Next Frontier in Embodied AI (2026 · arXiv.org · 被引 38)
• An Empirical Study of GPT-4o Image Generation Capabilities (2025 · arXiv.org · 被引 29)
• DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries (2024 · European Conference on Computer Vision · 被引 28)
• DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World (2025 · arXiv.org · 被引 17)
• Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs (2025 · IEEE International Conference on Computer Vision · 被引 17)