372 citations · 641 across the 71 of their papers we have counts for
12 papers · 1 filter
Spectral Geometry of Attention: From Information Routing to Uncertainty
Giulio Viganò, Simone Melzi, Maks Ovsjanikov
In this work, we study transformer attention through the lens of spectral geometry and operator theory. We view each attention head as a functional map between Hilbert spaces of fu…
Pattern Formation in Transformers
Erkan Turan, Gaspard Abel, Maks Ovsjanikov
What are the inductive biases of a Transformer architecture? Existing theory on how the forward pass shapes representations either considers whether Transformers escape from rank c…
The Computational Basis of Confidence in Large Language Models
Dharshan Kumaran, Viorica Patraucean, Maks Ovsjanikov +2
Reliable confidence -- the probability that a model's own answer is correct -- is essential for the trustworthy deployment of language models. Existing work has largely evaluated c…
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
Erkan Turan, Nicolas Dufour, Maks Ovsjanikov
Generative Modeling via Drifting~\citep{deng2026drifting} has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet its success is…
Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors
Erkan Turan, Gaspard Abel, Maysam Behmanesh +2
Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features co…
Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov
Graph alignment, the problem of identifying corresponding nodes across multiple graphs, is fundamental to numerous applications. Most existing unsupervised methods embed node featu…
Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization
Erkan Turan, Aristotelis Siozopoulos, Louis Martinez +3
Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly sampling and lacking interpretability of t…
Smoothed Graph Contrastive Learning via Seamless Proximity Integration
Maysam Behmanesh, Maks Ovsjanikov
Graph contrastive learning (GCL) aligns node representations by classifying node pairs into positives and negatives using a selection process that typically relies on establishing…
AtomSurf : Surface Representation for Learning on Protein Structures
Vincent Mallet, Souhaib Attaiki, Yangyang Miao +2
While there has been significant progress in evaluating and comparing different representations for learning on protein data, the role of surface-based learning approaches remains…
TIDE: Time Derivative Diffusion for Deep Learning on Graphs
Maysam Behmanesh, Maximilian Krahn, Maks Ovsjanikov
A prominent paradigm for graph neural networks is based on the message-passing framework. In this framework, information communication is realized only between neighboring nodes. T…
Matrix Decomposition on Graphs: A Functional View
Abhishek Sharma, Maks Ovsjanikov
We propose a functional view of matrix decomposition problems on graphs such as geometric matrix completion and graph regularized dimensionality reduction. Our unifying framework i…
Geometric Matrix Completion: A Functional View
Abhishek Sharma, Maks Ovsjanikov
We propose a totally functional view of geometric matrix completion problem. Differently from existing work, we propose a novel regularization inspired from the functional map lite…