25 citations · 65 across the 12 of their papers we have counts for
13 papers
Zero-Shot Vision Encoder Grafting via LLM Surrogates
Kaiyu Yue, Vasu Singla, Menglin Jia +6
Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden…
Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
Alex Hanson, Allen Tu, Geng Lin +3
3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differe…
From Pixels to Prose: A Large Dataset of Dense Image Captions
Vasu Singla, Kaiyu Yue, Sukriti Paul +7
Training large vision-language models requires extensive, high-quality image-text pairs. Existing web-scraped datasets, however, are noisy and lack detailed image descriptions. To…
PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting
Alex Hanson, Allen Tu, Vasu Singla +3
Recent advances in novel view synthesis have enabled real-time rendering speeds with high reconstruction accuracy. 3D Gaussian Splatting (3D-GS), a foundational point-based paramet…
A Simple and Efficient Baseline for Data Attribution on Images
Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum +2
Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs duri…
Understanding and Mitigating Copying in Diffusion Models
Gowthami Somepalli, Vasu Singla, Micah Goldblum +2
Images generated by diffusion models like Stable Diffusion are increasingly widespread. Recent works and even lawsuits have shown that these models are prone to replicating their t…
What Can We Learn from Unlearnable Datasets?
Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping +2
In an era of widespread web scraping, unlearnable dataset methods have the potential to protect data privacy by preventing deep neural networks from generalizing. But in addition t…
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
Gowthami Somepalli, Vasu Singla, Micah Goldblum +2
Cutting-edge diffusion models produce images with high quality and customizability, enabling them to be used for commercial art and graphic design purposes. But do diffusion models…
Autoregressive Perturbations for Data Poisoning
Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping +3
The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been pro…
Poisons that are learned faster are more effective
Pedro Sandoval-Segura, Vasu Singla, Liam Fowl +4
Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical us…
Shift Invariance Can Reduce Adversarial Robustness
Songwei Ge, Vasu Singla, Ronen Basri +1
Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivit…
Low Curvature Activations Reduce Overfitting in Adversarial Training
Vasu Singla, Sahil Singla, David Jacobs +1
Adversarial training is one of the most effective defenses against adversarial attacks. Previous works suggest that overfitting is a dominant phenomenon in adversarial training lea…
ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
Rohun Tripathi, Vasu Singla, Mahyar Najibi +3
The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines. Unfortunately, for the region proposal stage of…