1 citations · 1 across the 8 of their papers we have counts for
11 papers
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Adam Pardyl, Siddhartha Gairola, Sukrut Rao +4
Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those…
WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing
Dominik Matuszek, Bartosz Zieliński, Tomasz Danel +1
When a graph neural network (GNN) explainer produces an unexpected attribution on a molecule, the attribution alone cannot reveal whether the explainer has failed or the model has…
DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
Adam Wróbel, Siddhartha Gairola, Jacek Tabor +3
Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet producing stable and high-resolution attribution maps for these models remains challenging. A…
ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classification
Mikołaj Janusz, Adam Wróbel, Bartosz Zieliński +1
Prototypical parts-based models offer a "this looks like that" paradigm for intrinsic interpretability, yet they typically struggle with ImageNet-scale generalization and often req…
SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
Turhan Can Kargin, Wojciech Jasiński, Adam Pardyl +2
Visual Foundation Models (VFMs), such as DINO and CLIP, excel in semantic understanding of images but exhibit limited spatial reasoning capabilities, which limits their applicabili…
Milnor meets Hopf and Toeplitz at the K-theory of quantum projective planes
Francesco D'Andrea, Piotr M. Hajac, Tomasz Maszczyk +1
We explore applications of the celebrated construction of the Milnor connecting homomorphism from the odd to the even K-groups in the context of Hopf--Galois theory. For a finitely…
Enhancing Chemical Explainability Through Counterfactual Masking
Łukasz Janisiów, Marek Kochańczyk, Bartosz Zieliński +1
Molecular property prediction is a crucial task that guides the design of new compounds, including drugs and materials. While explainable artificial intelligence methods aim to scr…
Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis
Sebastian Musiał, Bartosz Zieliński, Tomasz Danel
Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, th…
Efficient Multi-Source Knowledge Transfer by Model Merging
Marcin Osial, Bartosz Wójcik, Bartosz Zieliński +1
While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models online. Addressing this multi-source trans…
Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks
Tomasz Michalski, Adam Wróbel, Andrea Bontempelli +6
Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations based on case-based reasoning, such as "thi…
FlySearch: Exploring how vision-language models explore
Adam Pardyl, Dominik Matuszek, Mateusz Przebieracz +3
The real world is messy and unstructured. Uncovering critical information often requires active, goal-driven exploration. It remains to be seen whether Vision-Language Models (VLMs…