Scholar
Hareesh Ravi
Google Scholar ID: Lo7VgJ0AAAAJ
Adobe
Citations & Impact
Citations
232
H-index
10
i10-index
10
Publications
20
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Published papers include 'Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods' (ECCV 2024), 'PREDITOR: Text Guided Image Editing with Diffusion Prior' (Preprint 2023), 'Controlled and Conditional Text to Image Generation with Diffusion Prior' (Preprint 2023), 'Cross-Modal Coherence Model for Text to Image Retrieval' (AAAI 2022).
Research Experience
- Senior Applied Research Scientist at Adobe's Applied Research team, working on language-vision research and Generative AI. Led several projects including Adobe's FireFly Image Model 3, zero-shot stylized image generation, and Structure Match.
Education
- PhD from the Computer Science department at Rutgers University's Intelligent Visual Interfaces lab, supervised by Dr. Mubbasir Kapadia and Dr. Gerard De Melo.
Background
- Research interests include vision-language understanding, particularly multimodal story comprehension, story illustration, visual storytelling, image captioning, and text-to-image retrieval/generation. Current work focuses on text to image generation with diffusion/flow based models, interactive editing, and large multimodal models.
Miscellany
- Looking for summer PhD research interns to work on text to image generation, interactive and multi-turn editing, and multimodal models.
