297 citations · 1.5k across the 199 of their papers we have counts for
21 papers · 1 filter
Geometry-Aware Diffusion Approximate Posterior Sampling for Sparse-View and Limited-Angle CT
Honglei Brinkmann, Carola-Bibiane Schönlieb, Ander Biguri
Sparse-view computed tomography (CT) reduces radiation dose and acquisition time and may mitigate motion artifacts. However, angular undersampling provides insufficient information…
Beyond Unimodal Bases: Pullback Geometry for Multimodal Data
Honglei Brinkmann, Lucas Ng, Georgios Batzolis +3
Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high-dimensional data. For these operations to be statistically meaningful, paths…
Mixed-Noise Plug-and-Play with Infimal Convolution Fidelities and Multiple Priors
Ziqi Qin, Hong Ye Tan, Ander Biguri +2
Plug-and-Play (PnP) algorithms are a class of iterative methods for inverse imaging. Within an optimization algorithm, they combine a flexible fidelity term, encoding the forward o…
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
Mar Gonzàlez I Català, Haitz Sáez de Ocáriz Borde, Davide Murari +3
Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accuracy, which ignores the path t…
Learning piecewise-smooth dynamical systems
Davide Murari, Erik Jansson, Chris Budd OBE +1
Discovering dynamical systems from trajectory data is a central problem in applied mathematics and engineering. Whilst recent advances in machine learning have led to strong progre…
Recovering protein conformations from single-particle cryo-EM data via indirect shape matching gradient flows
Erik Jansson, Jonathan Krook, Ozan Öktem +1
Single-particle cryo-electron microscopy images a macromolecule as many noisy tomographic projections of its electrostatic potential. We reconstruct the protein backbone directly f…
1-Lipschitz Neural Networks on Hadamard Manifolds
Davide Murari, Marta Ghirardelli, Ben Adcock +3
Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strategies are designed for Euclidean space…
CBCT-IQ: A Publicly Available Annotated Cone-Beam CT Dataset for Image Quality Assessment and Benchmarking
Sepideh Hatamikia, Anna Breger, Clemens Karner +14
Medical image quality plays a critical role in diagnostic accuracy, especially in X-ray-based imaging modalities such as cone-beam computed tomography (CBCT), where image quality m…
Rethinking Clinical Relevance in Chest X-ray Machine Learning: How Evaluation References Define Performance
Panagiotis Fytas, Ian Selby, Clemens Karner +14
Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment. However, commonly used report-derived…
DeepCormack: Fermi surface tomography using model-based data-driven algorithms
Georg F. B. Lovric, Bryn Drury, Carola-Bibiane Schönlieb +2
The experimental reconstruction of the 3D two-photon momentum density (TPMD) via angular correlation of electron-positron annihilation radiation (ACAR) is a particularly useful met…
Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
Alex Massucco, Leonardo Del Grande, Marcello Carioni +2
In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretica…
Muon is Not That Special: Random or Inverted Spectra Work Just as Well
Zakhar Shumaylov, Nathaël Da Costa, Peter Zaika +6
The recent empirical success of the Muon optimizer has renewed interest in non-Euclidean optimization, typically justified by similarities with second-order methods, and linear min…
CATO: Charted Attention for Neural PDE Operators
Chun-Wun Cheng, Sifan Wang, Carola-Bibiane Schönlieb +1
Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, existing transformer-based oper…
Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
James Rowbottom, Nick Huang, Carola-Bibiane Schönlieb +1
State estimation is a critical task in scientific, engineering and control applications. Since the reliability of reconstructions depends on the number and position of sensors, opt…
Adaptive Coordinate Transforms for Neural Operators
Chaoyu Liu, Zhonghao Li, Gaohang Chen +5
Neural operators have achieved promising performance on partial differential equations (PDEs), but most existing models are built on fixed Eulerian coordinates. This mismatch betwe…
Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
Meira Iske, Carola-Bibiane Schönlieb
Many normalizing flow architectures impose regularity constraints, yet their distributional approximation properties are not fully characterized. We study the expressivity of bi-Li…
Bridging Input Feature Spaces Towards Graph Foundation Models
Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua +2
Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and di…
No-reference based automatic parameter optimization for iterative reconstruction using a novel search space aware crow search algorithm
Poorya MohammadiNasab, Ander Biguri, Philipp Steininger +9
Iterative reconstruction technique's ability to reduce radiation exposure by using fewer projections has attracted significant attention. However, these methods typically require a…
ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
Chun-Wun Cheng, Yanqi Cheng, Peiyuan Jing +4
Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution…
Towards Improved Sentence Representations using Token Graphs
Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Zorah Lähner +1
Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling m…
Approximation Theory for Lipschitz Continuous Transformers
Takashi Furuya, Davide Murari, Carola-Bibiane Schönlieb
Stability and robustness are critical for deploying Transformers in safety-sensitive settings. A principled way to enforce such behavior is to constrain the model's Lipschitz const…