Kevin Lin
Scholar

Kevin Lin

Google Scholar ID: LKSy1kwAAAAJ
Microsoft
Computer VisionVision and LanguageMultimodal
Citations & Impact
All-time
Citations
8,867
 
H-index
32
 
i10-index
48
 
Publications
20
 
Co-authors
76
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Published multiple papers in top international conferences such as EMNLP 2025, WACV 2026, ICCV 2025, CVPR 2025, ICLR 2025, NeurIPS 2024, including 'Exploring ALLMs as a judge for speaking style' and 'AVED for zero-shot audio-visual editing'. Also involved in various research projects like 'VisVM for guiding VLM inference-time search' and 'ImageGen-CoT for reasoning in visual generation'.
Research Experience
  • Working on post-training of OpenAI models at Microsoft GenAI team.
Education
  • Ph.D. in Electrical Engineering from the University of Washington in 2020; M.S. degree from National Taiwan University in 2014.
Background
  • Member of Technical Staff at Microsoft GenAI team, with research interests in multimodal understanding and generation.
Miscellany
  • Links to Google Scholar, GitHub, and Microsoft profile.