Scholar
Can Qin
Google Scholar ID: QCik-YcAAAAJ
Salesforce
Citations & Impact
Citations
3,679
H-index
27
i10-index
41
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published multiple papers including 'UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG', 'CoDA: Coding LM via Diffusion Adaptation', 'Vlm2vec-v2 (MMEB-V2): Advancing multimodal embedding for videos, images, and visual documents', etc. Several projects have been accepted or released such as NeurIPS 25, ACL findings, CVPR 25, etc.
Research Experience
- Started working as a Research Scientist at Salesforce AI Research in 2023.
Education
- Earned a Ph.D. from Northeastern University in Boston, USA, in 2023, with research centered around Transfer Learning and Efficient AI. Obtained B.E. degree from Xidian University in Xi’an, China, in 2018.
Background
- Currently a Research Scientist at Salesforce AI Research, focusing on Generative AI and Multi-modal Learning, particularly Video/Image to Text (Understanding) and Text to Video/Image (Generation) techniques.