About Ali Vosoughi

Multimodal AI Researcher • University of Rochester • Dissertation complete
Advisors: Axel Wismueller (Imaging Sciences) and Chenliang Xu (Computer Science)
Research focus: vision-language models and multimodal LLMs (video understanding, multimodal reasoning and evaluation, RL post-training), plus audio-language models; applications in medical imaging and chip design.


Ali Vosoughi multimodal AI researcher University of Rochester

Portfolio: Industry Experience | Datasets | Demos | Awards | Presentations | Research showcase

Professional Gallery

Ali Vosoughi computer science multimodal AI spatial audio researcher
Ali Vosoughi – Multimodal AI Research
Ali Vosoughi researcher Microsoft Research Bosch AI Smule AI internships
Ali Vosoughi – Research Scientist, Industry Collaborations
Mohammad Ali Vosoughi University of Rochester computer science audio-visual AI
Mohammad Ali Vosoughi – Audiovisual AI Researcher
Mohammad Ali Vosoughi multimodal machine learning researcher IEEE TMM ICASSP publications
Mohammad Ali Vosoughi – Publications in IEEE TMM, ICASSP, ACM MM
Visit my complete galleries for more professional photos.

Contact: ali.vosoughi@rochester.edu
Earlier publications may appear under M. Ali Vosoughi. ORCID: 0000-0003-1014-2937