Scholar
Saksham Suri
Google Scholar ID: NrHYGZ8AAAAJ
Research Scientist, Meta Reality Labs
Citations & Impact
Citations
386
H-index
11
i10-index
12
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Publications: LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR, 2025); MAPS: Memory Augmented Panoptic Segmentation (Under Review); UVIS: Unsupervised Video Instance Segmentation (CVPR Workshop, 2024); Gen2Det: Generate to Detect (Synthetic Data for Computer Vision Workshop @ CVPR 2024); LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors (Under Submission); GRIT: GAN Residuals for Image-to-Image Translation (WACV, 2024); Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization (WACV, 2024); SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining (ICCV, 2023)
Research Experience
- Research Scientist at Meta Reality Labs, focusing on efficient foundation models; interned with Meta and Amazon during his Ph.D.
Education
- Ph.D. in Computer Science from the University of Maryland, College Park, advised by Prof. Abhinav Shrivastava; B.S. in Computer Science and Engineering from IIIT Delhi, worked at IAB Lab and Precog.
Background
- Research Interests: Solving problems using less supervision and uncurated as well as synthetic data. Recently, working on improving recognition using generation, especially with diffusion models as synthetic data sources.
Miscellany
- Information about personal interests or hobbies is not provided.
Co-authors