The deep learning revolution has enabled major AI advances in physical sciences, particularly in discovering dynamical systems from observational data. Yet the reliability of learned surrogates and symbolically discovered models is often undermined by non-uniqueness: models may fit observed trajectories perfectly, but...
Zakhar Shumaylov, P. Zaika, Philipp Scholl et al.· arXiv.org· 11 citations· ⚡1
Sparse-view computed tomography (CT) reduces radiation dose and acquisition time and may mitigate motion artifacts. However, angular undersampling provides insufficient information to determine the image uniquely and stably. Limited-angle CT, arising from restricted angular coverage, produces strongly directional infor...
Honglei Brinkmann, C. Schönlieb, A. Biguri· 0 citations
We propose SurvSurf, a neural-network-based survival model for direct, simultaneous probabilistic prediction of first-hitting times of sequential events from baseline. Unlike existing models, SurvSurf is theoretically guaranteed to never violate the monotonic relationship between the cumulative incidence functions of...
Yichen Chen, Sören Dittmer, K. Bernatowicz et al.· Robotics: Science and System...· 0 citations
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 operator, and a pretrained image denoiser, in order to deal with more severe corruptions such as blurring or downsampling when reconstructing...
Zi-Qi Qin, Hong-Wei Tan, A. Biguri et al.· 0 citations
MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code, is proposed, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code and reduces memory consumption while improving reconstruction quality.
Alexander Denker, Moshe Eliasof, Ž. Kereta et al.· arXiv.org· 2 citations
Data-driven Riemannian geometry provides nonlinear interpolation and geometric representations of high-dimensional data. For these operations to be statistically meaningful, paths between observations should preferentially traverse high-likelihood regions. Existing scalable pullback constructions typically use a unimod...
Honglei Brinkmann, Lucas Ng, Georgios Batzolis et al.· 0 citations
This work introduces answer-distribution trajectories, a stochastic-dynamics-inspired representation that tracks the model's full predictive distribution over answers as reasoning unfolds, and suggests that answer-distribution trajectories provide a rich framework for analysing and evaluating the dynamics of LLM reason...
M. Catala, Haitz Sáez de Ocáriz Borde, D. Murari et al.· 1 citation
MammoDG, a novel deep-learning framework for generalisable, robust, and reliable analysis of cross-domain multi-center mammography data, is devises, highlighting the critical importance of domain generalisation for trustworthy mammography analysis in the presence of imaging protocol variations.
Yi-Jun Yang, Shu-Jun Wang, Lihao Liu et al.· International Journal of Com...· 0 citations
This work systematically investigates how evaluation-reference choices affect model performance and ranking in both pathology classification and image quality assessment (IQA), and shows that for supervised image classifiers, changing the label source leads to substantial differences not only in performance estimates b...
Panagiotis Fytas, Ian Selby, C. Karner et al.· arXiv.org· 0 citations
This work constructs and analyzes a class of 1-Lipschitz neural networks on Hadamard manifolds, and shows improved results from the nonexpansive denoiser over static, data-only, and Log-Euclidean denoising baselines, and empirically test its convergence properties.
D. Murari, Marta Ghirardelli, Ben Adcock et al.· arXiv.org· 0 citations
This work presents a modular framework for discovering piecewise-smooth dynamical systems by first estimating switching hyperplanes from data and then learning smooth dynamics within each region using geometry-constrained neural networks.
D. Murari, Erik Jansson, Chris Budd Obe et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
