Publications
You can also find my articles on my Google scholar profile.
* denotes equal contribution.
From Pixels to Prose: A Large Dataset of Dense Image Captions
Under Review Vasu Singla*, Kaiyu Yue*, Sukriti Paul, Reza Shirkavand, Mayuka Jayawardhana, Alireza Ganjdanesh, Heng Huang, Abhinav Bhatele, Gowthami Somepalli, Tom Goldstein
PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
Under Review Alex Hanson, Allen Tu, Vasu Singla, Mayuka Jayawardhana, Matthias Zwicker, Tom Goldstein
A Simple and Efficient Baseline for Data Attribution on Images
Accepted at NeurIPS 2023 ATTRIB Workshop
Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein
Why Diffusion Models Memorize and How to Mitigate Copying
Accepted at NeurIPS 2023
Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
What Can We Learn from Unlearnable Datasets?
Accepted at NeurIPS 2023
Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein
Diffusion art or digital forgery? investigating data replication in diffusion models
Accepted at CVPR 2023
Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
Learning with noisy labels using low-dimensional model trajectory
Accepted at NeurIPS 2022 DistShift Workshop
Vasu Singla, Shuchin Aeron, Toshiaki Koike-Akino, Kieran Parsons, Matthew Brand, Ye Wang
Autoregressive Perturbations for Data Poisoning
Accepted at NeurIPS 2022
Pedro Sandoval-Segura*, Vasu Singla*, Jonas Geiping, Micah Goldblum, Tom Goldstein, David W. Jacobs
Poisons That Are Learned Faster Are More Effective
Accepted at CVPR 2022 The Art of Robustness Workshop
Pedro Sandoval-Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein
CutMixWords: Data Augmentation for Accent Robust Speech Recognition
Vasu Singla*, Sayantan Mahinder*, Bortik Bandyopadhyay, Srinivas Chappidi
Shift Invariance Can Reduce Adversarial Robustness
Accepted at NeurIPS 2021 (Poster)
Short Version at ICLR 2021 Security and Safety in Machine Learning
Songwei Ge*, Vasu Singla*, Ronen Basri, David Jacobs
Low Curvature Activations Reduce Overfitting in Adversarial Training
Accepted at ICCV 2021 (Poster)
Short Version at ICLR 2021 Security and Safety in Machine Learning
Vasu Singla, Sahil Singla, David Jacobs, Soheil Feizi
ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
Rohun Tripathi*, Vasu Singla*, Mahyar Najibi, Bharat Singh, Abhishek Sharma, Larry Davis