相关论文: A neuro-mathematical model for size and context re…

There are two major questions that neuroimaging studies attempt to answer: First, how are sensory stimuli represented in the brain (which we term the stimulus-based setting)? And, second, how does the brain generate cognition (termed the…

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of…

Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formalize this apparent paradox through the first scaling laws for…

We investigate the dependence of the score on noise in the data, and on the network size. As a result, we obtain the so-called "cognition transition" from good performance to zero with increasing noise. The understanding of this transition…

Perceiving the shape and material of an object from a single image is inherently ambiguous, especially when lighting is unknown and unconstrained. Despite this, humans can often disentangle shape and material, and when they are uncertain,…

Neural scaling laws aim to characterize how out-of-sample error behaves as a function of model and training dataset size. Such scaling laws guide allocation of a computational resources between model and data processing to minimize error.…

In this paper, we consider the so-called Shape Invariant Model which stands for the estimation of a function f0 submitted to a random translation of law g0 in a white noise model. We are interested in such a model when the law of the…

The aim of this review is to present an overview over available models and approaches to non-commutative gauge theory. Our main focus thereby is on gauge models formulated on flat Groenewold-Moyal spaces and renormalizability, but we will…

Estimating correspondences between deformed shape instances is a long-standing problem in computer graphics; numerous applications, from texture transfer to statistical modelling, rely on recovering an accurate correspondence map. Many…

A simple Gaussian size deconvolution method is routinely used to remove the blur of observed images caused by insufficient angular resolutions of existing telescopes, thereby to estimate the physical sizes of extracted sources and…

Recently, diffusion models were applied to a wide range of image analysis tasks. We build on a method for image-to-image translation using denoising diffusion implicit models and include a regression problem and a segmentation problem for…

Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is…

In this article, the notion of a mathematical model in science is attempted to be enlightened from several points of view. In particular, it is shown that mathematical models are introduced differently and used differently in different…

Shape-constrained functional data encompass a wide array of application fields, such as activity profiling, growth curves, healthcare and mortality. Most existing methods for general functional data analysis often ignore that such data are…

A desirable property of interpretable models is small size, so that they are easily understandable by humans. This leads to the following challenges: (a) small sizes typically imply diminished accuracy, and (b) bespoke levers provided by…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Some visual search tasks require to memorize the location of stimuli that have been previously scanned. Considerations about the eye movements raise the question of how we are able to maintain a coherent memory, despite the frequent…

Despite their impressive performance on multi-modal tasks, large vision-language models (LVLMs) tend to suffer from hallucinations. An important type is object hallucination, where LVLMs generate objects that are inconsistent with the…

The standard model of large scale structure is considered, in which the structure originates as a Gaussian adiabatic density perturbation with a nearly scale invariant spectrum. The basic theoretical tool of cosmological perturbation theory…

We study the finite-size scaling behaviour at the critical point, resulting from the addition of a homogeneous size-dependent perturbation, decaying as an inverse power of the system size. The scaling theory is first formulated in a general…