Follow
Vivek Ramanujan
Vivek Ramanujan
Verified email at cs.washington.edu - Homepage
Title
Cited by
Cited by
Year
What's hidden in a randomly weighted neural network?
V Ramanujan*, M Wortsman*, A Kembhavi, A Farhadi, M Rastegari
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
4012020
Datacomp: In search of the next generation of multimodal datasets
SY Gadre, G Ilharco, A Fang, J Hayase, G Smyrnis, T Nguyen, R Marten, ...
Advances in Neural Information Processing Systems 36, 2024
3582024
Supermasks in superposition
M Wortsman*, V Ramanujan*, R Liu, A Kembhavi, M Rastegari, J Yosinski, ...
Advances in Neural Information Processing Systems 33, 15173-15184, 2020
3252020
Soft threshold weight reparameterization for learnable sparsity
A Kusupati, V Ramanujan, R Somani, M Wortsman, P Jain, S Kakade, ...
International Conference on Machine Learning, 5544-5555, 2020
2522020
Matryoshka representations for adaptive deployment
A Kusupati, G Bhatt, A Rege, M Wallingford, A Sinha, V Ramanujan, ...
arXiv preprint arXiv:2205.13147 3, 2022
102*2022
Improving shape deformation in unsupervised image-to-image translation
A Gokaslan, V Ramanujan, D Ritchie, KI Kim, J Tompkin
Proceedings of the European Conference on Computer Vision (ECCV), 649-665, 2018
942018
Effects of parameter norm growth during transformer training: Inductive bias from gradient descent
W Merrill, V Ramanujan, Y Goldberg, R Schwartz, N Smith
arXiv preprint arXiv:2010.09697, 2020
342020
Forward compatible training for representation learning
V Ramanujan, PKA Vasu, A Farhadi, O Tuzel, H Pouransari
arXiv preprint arXiv:2112.02805, 2021
23*2021
On the connection between pre-training data diversity and fine-tuning robustness
V Ramanujan, T Nguyen, S Oh, A Farhadi, L Schmidt
Advances in Neural Information Processing Systems 36, 2024
202024
Llc: Accurate, multi-purpose learnt low-dimensional binary codes
A Kusupati, M Wallingford, V Ramanujan, R Somani, JS Park, K Pillutla, ...
Advances in neural information processing systems 34, 23900-23913, 2021
122021
Neural Priming for Sample-Efficient Adaptation
M Wallingford*, V Ramanujan*, A Fang, A Kusupati, R Mottaghi, ...
arXiv preprint arXiv:2306.10191, 2023
112023
Neural radiance field codebooks
M Wallingford, A Kusupati, A Fang, V Ramanujan, A Kembhavi, ...
arXiv preprint arXiv:2301.04101, 2023
102023
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
S Geng, CY Hsieh, V Ramanujan, M Wallingford, CL Li, PW Koh, ...
arXiv preprint arXiv:2406.05184, 2024
12024
Data Curation for Large Scale Detection Pretraining
V Ramanujan, H Zhang, Y Yang, A Farhadi, AT Toshev, L Schmidt, ...
1
When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization
V Ramanujan, K Tirumala, A Aghajanyan, L Zettlemoyer, A Farhadi
arXiv preprint arXiv:2412.16326, 2024
2024
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
M Wallingford, A Bhattad, A Kusupati, V Ramanujan, M Deitke, S Kakade, ...
arXiv preprint arXiv:2412.07770, 2024
2024
On the Connection between Pre-training Data Diversity and Robustness
V Ramanujan, T Nguyen, L Schmidt, A Farhadi
First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at …, 0
The system can't perform the operation now. Try again later.
Articles 1–17