Vivek Ramanujan

Computer Science · Physical Sciences

8h-index344citations26works0.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(13), COVID-19 diagnosis using AI(5), Advanced Neural Network Applications(4), Generative Adversarial Networks and Image Synthesis(4), Topic Modeling(3)

Publications26 total

OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis
arXiv (Cornell University)·2025Open Access
Contrastive Flow Matching
arXiv (Cornell University)·2025Open Access
OpenThoughts: Data Recipes for Reasoning Models
arXiv (Cornell University)·2025Open Access
When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization
arXiv (Cornell University)·2024Open Access
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
arXiv (Cornell University)·2024Open Access
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
arXiv (Cornell University)·2024Open Access
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
2024
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
2024· 1 cited
On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
arXiv (Cornell University)·2023· 3 citedOpen Access
Neural Priming for Sample-Efficient Adaptation
arXiv (Cornell University)·2023· 3 citedOpen Access
DataComp: In search of the next generation of multimodal datasets
arXiv (Cornell University)·2023· 73 citedOpen Access
Neural Radiance Field Codebooks
arXiv (Cornell University)·2023Open Access
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 11 cited
Matryoshka Representation Learning
arXiv (Cornell University)·2022· 22 citedOpen Access
Forward Compatible Training for Large-Scale Embedding Retrieval Systems
arXiv (Cornell University)·2021· 2 citedOpen Access
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
arXiv (Cornell University)·2021Open Access
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
arXiv (Cornell University)·2021Open Access
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing·2021· 1 citedOpen Access
Parameter Norm Growth During Training of Transformers.
arXiv (Cornell University)·2020· 5 citedOpen Access
Soft Threshold Weight Reparameterization for Learnable Sparsity
International Conference on Machine Learning·2020· 23 cited
page 1 of 2Next →

Frequent Co-authors

Ali Farhadi(17), Aditya Kusupati(9), Matthew Wallingford(9), Sham M. Kakade(7), Aniruddha Kembhavi(6), Mitchell Wortsman(5), Ranjay Krishna(5), Raghav Somani(4), Prateek Jain(4), Roozbeh Mottaghi(4), Aaron Gokaslan(3), Alex Chengyu Fang(3), Pang Wei Koh(3), Sewoong Oh(3), Ludwig Schmidt(3), Daniel Ritchie(2), Kwang In Kim(2), James Tompkin(2), Georgios Smyrnis(2), Thao D. Nguyen(2)