Research Mission

Build fundamental AI/ML methods for computer vision and language modeling to address societal challenges.

Research Interests

Our research is highly interdisciplinary and collaborative, and interests include vision-language models, large language models, computer vision, text/image/video classification, text recognition (OCR, Handwritten), human action analysis, multispectral imaging and NLP tasks.

Research Projects

  • Multimodal deep learning
  • Vision-language(-action) models
  • Multispectral handwritten text and palimpsests modelling
  • Large Language Models and applications in computer vision

News

  • March 2025: Ekta Vats is appointed to the WASP–Diversity and Inclusion Group.
  • March 2025: We welcome Tianru Zhang as a Postdoc in the group!
  • Jan. 2025: WASP Affiliation for PhD student project on Multimodal Deep Learning.
  • Oct. 2024: UU-MISHA is ready! We built a cost-effective Multispectral imaging (MSI) system to reveal hidden text from manuscripts, partially funded by Kjell och Märta Beijers Stiftelsen. We thank team MISHA at Rochester Institute of Technology for the collaboration.
  • Sept. 2024: We welcome Robin Hollifeldt as our PhD student!
  • May 28, 2024: Ekta Vats got promoted to a Docent in Computerised Image Processing. Docent Lecture: Introduction to Large Language Models in Image Analysis: Theory and Applications. Read more!
  • New funding from the UU Graduate School in Cybersecurity for project: Large language models-powered social robots in cybersecurity applications (CYBERBOT). PI: Ginevra Castellano, Co-PIs: Ekta Vats, Katie Winkle and Boel Nelson. 
  • Ekta Vats’ interview with Beijerstiftelsen: 3 frågor till nya Beijerforskaren Ekta Vats (3 questions for the new Beijer Researcher Ekta Vats)
  • Dec. 2023: Women in Data Science Sweden (WiDS) mentorship program wrap up! Ekta Vats served as a mentor
  • Oct. – Dec. 2023: Till Grutschus from Technical University of Munich joined us on an exchange semester. Project: Human fall detection on untrimmed videos using large foundational video-understanding model
  • Oct. 5, 2023: Beijerforskardagen
  • Oct. 4, 2023: Raphaela M. Heil defended her thesis titled Document Image Processing for Handwritten Text Recognition. Deep Learning-based Transliteration of Astrid Lindgren’s Stenographic Manuscripts.

Hiring!