Related papers: A flexible, fast and benchmarked vectorial model f…
Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…
This paper addresses the challenging problem of category-level pose estimation. Current state-of-the-art methods for this task face challenges when dealing with symmetric objects and when attempting to generalize to new environments solely…
The remarkable temporal properties of ultra-short pulsed lasers in combination with novel beam shaping concepts enable the development of completely new material processing strategies. We demonstrate the benefit of employing focus…
We study the bias and scatter in mass measurements of galaxy clusters resulting from fitting a spherically-symmetric Navarro, Frenk & White model to the reduced tangential shear profile measured in weak lensing observations. The reduced…
Diffusion models have had a profound impact on many application areas, including those where data are intrinsically infinite-dimensional, such as images or time series. The standard approach is first to discretize and then to apply…
As a newly emerging advance in deep generative models, diffusion models have achieved state-of-the-art results in many fields, including computer vision, natural language processing, and molecule design. The remote sensing (RS) community…
Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies…
An open source software package for simulating thermal neutron propagation in geometry is presented. In this system, neutron propagation can be treated by either the particle transport method or the ray-tracing method. Supported by an…
Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps.…
Particle size measurement is crucial in various applications, be it sizing droplets in inkjet printing or respiratory events, tracking particulate ejection in hypersonic impacts, or detecting floating target markers in free surface flows.…
Radiative transfer calculations are essential for modeling planetary atmospheres. However, standard methods are computationally demanding and impose accuracy-speed trade-offs. High computational costs force numerical simplifications in…
Gravitational lensing by clusters of galaxies offers a powerful probe of their structure and mass distribution. Deriving a lens magnification map for a galaxy cluster is a classic inversion problem and many methods have been developed over…
We demonstrate a hybrid distributed fiber sensing system for multi-parameter detection. The integration of phase-sensitive optical time domain reflectometry ({\Phi}-OTDR) and Brillouin optical time domain reflectometry (B-OTDR) enables…
Laser beam profilometry is an important scientific task with well-established solutions for beams propagating in air. It has, however, remained an open challenge to measure beam profiles of high-power lasers in ultra-high vacuum and in…
Accelerator-based light sources such as storage rings and free-electron lasers use relativistic electron beams to produce intense radiation over a wide spectral range for fundamental research in physics, chemistry, materials science,…
We present a novel learning-based method to build a differentiable computational model of a real fluorescence microscope. Our model can be used to calibrate a real optical setup directly from data samples and to engineer point spread…
We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically,…
Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic…
Diffusion models are state-of-the-art methods in generative modeling when samples from a target probability distribution are available, and can be efficiently sampled, using score matching to estimate score vectors guiding a Langevin…
Neural diffusion processes provide a scalable, non-Gaussian approach to modelling distributions over functions, but existing formulations are limited to single-task inference and do not capture dependencies across related tasks. In many…