Can Biases in ImageNet Models Explain Generalization?
Paper • 2404.01509 • Published
Paul Gavrikov
paulgavrikov
AI & ML interests
multimodal, computer vision, robustness, interpretability
Recent Activity
new activity 5 days ago
Qwen/Qwen3.6-35B-A3B:Image - resolution - tokens updated a Space 9 days ago
paulgavrikov/visualoverload-submit updated a dataset 17 days ago
paulgavrikov/visualoverloadOrganizations
authored 11
papers over 1 year ago
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Paper • 2403.09193 • Published • 9
On the Interplay of Convolutional Padding and Adversarial Robustness
Paper • 2308.06612 • Published
An Extended Study of Human-like Behavior under Adversarial Training
Paper • 2303.12669 • Published
The Power of Linear Combinations: Learning with Random Convolutions
Paper • 2301.11360 • Published
Does Medical Imaging learn different Convolution Filters?
Paper • 2210.13799 • Published
Robust Models are less Over-Confident
Paper • 2210.05938 • Published
Adversarial Robustness through the Lens of Convolutional Filters
Paper • 2204.02481 • Published
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
Paper • 2203.15331 • Published
How Do Training Methods Influence the Utilization of Vision Models?
Paper • 2410.14470 • Published • 5
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
Paper • 2410.06154 • Published • 16