Scholar
Vivek Ramanujan
Google Scholar ID: yXFPyNMAAAAJ
University of Washington
Citations & Impact
Citations
2,346
H-index
12
i10-index
14
Publications
17
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - When Worse is Better: Navigating the Compression-Generation Tradeoff in Visual Tokenization
- - From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
- - The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
- - On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
- - DataComp: In Search of the Next Generation of Multimodal Datasets
Research Experience
- Worked as a predoctoral researcher at the Allen Institute for Artificial Intelligence, contributing to various research projects.
Education
- PhD: University of Washington, Advisors: Ali Farhadi and Ludwig Schmidt; Predoctoral Researcher: Allen Institute for Artificial Intelligence, Advised by: Mohammad Rastegari and Aniruddha Kembhavi.
Background
- Currently a PhD student at the University of Washington, working on problems related to robust machine learning. Previously, he was a predoctoral researcher on the PRIOR (vision) group at the Allen Institute for Artificial Intelligence (AI2).
Miscellany
- Information about personal interests and hobbies not provided.
Co-authors