Scholar
Yifan Xu
Google Scholar ID: 1SmeNt0AAAAJ
Nanjing University
Citations & Impact
Citations
8
H-index
2
i10-index
0
Publications
2
Co-authors
4
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published 'VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking', arXiv, 2025
- Published 'CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval', arXiv, 2025
- Released VideoCap-R1: the first systematic study on GRPO-based RL post-training to improve video MLLMs’ action description capability
- Released CaReBench: a fine-grained benchmark with 1,000 high-quality videos and human-annotated captions, along with unified model CaRe
- Reviewer for Pattern Recognition (2025) and International Journal of Computer Vision (2025)
- Developed and open-sourced the academic homepage template 'Zero Academic Page' (built with Hugo)
