Scholar
Tejas Gokhale
Google Scholar ID: _ILTlEwAAAAJ
Assistant Professor, University of Maryland Baltimore County
Citations & Impact
Citations
991
H-index
18
i10-index
20
Publications
20
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Spotlight talk at ICCV 2025; serving as Tutorial Chair and participating in Area Chair Workshop.
- Best Paper Award at VDU Workshop @ CVPR 2024 (led by Yiran Luo).
- Tutorials at ECCV 2024 ('Responsibly Building Generative Models') and WACV 2024 ('Reliability of Generative Models in Vision').
- Invited Talk at AAAI 2024.
- Serving as Area Chair for NeurIPS, ACL, and NAACL.
- Published a new book on Multimodal Retrieval and Generation in July 2024.
- Featured in an AI Magazine article summarizing team’s work (September 2024).
- Paper 'Side Effects of Erasing Concepts from Diffusion Models' accepted at EMNLP Findings 2025.
- Paper 'Latent Diffusion Unlearning: Protecting against Unauthorized Personalization through Trajectory Shifted Perturbations' accepted at ACM Multimedia 2025.
Research Experience
- Host of the Perception, Prediction, and Reasoning (PPR) Seminar at UMBC.
- Participated in SCALE 2024 (Video-Based Event Retrieval) at JHU HLTCOE.
- Co-Principal Investigator (Co-PI) for a grant from the DARPA SciFy program.
- Received research funding from UMBC’s Cybersecurity Institute, CIDER (with GESTAR-II), START, and SURFF.
- Received in-kind support from Microsoft Research under the Accelerate Foundation Models Academic Research Initiative.
Background
- Philosopher, scientist, and professor of computing, grappling with questions in computational perception, learning, reasoning, and communication.
- Assistant Professor in the Department of Computer Science & Electrical Engineering at the University of Maryland, Baltimore County (UMBC).
- Director of the Cognitive Vision Group (CVG) at UMBC.
- Affiliate Faculty at the UMBC Center for AI.
- Research themes include: concept-level characterization of the visual world; interpretation of visual data under incomplete information; recognizing and adapting to novelty and variations; leveraging external knowledge and reasoning modules for generalization across contexts, domains, environments, and tasks; acquiring visual knowledge and communicating it to machines and humans.
