Related papers: Maven: A Multimodal Foundation Model for Supernova…

Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in…

Integrating heterogeneous datasets across different measurement platforms is a fundamental challenge in many scientific applications. A common example arises in deconvolution problems, such as cell type deconvolution, where one aims to…

Supernovae (SNe) that have been multiply-imaged by gravitational lensing are rare and powerful probes for cosmology. Each detection is an opportunity to develop the critical tools and methodologies needed as the sample of lensed SNe…

Deep models suffer from limited generalization capability to unseen domains, which has severely hindered their clinical applicability. Specifically for the retinal vessel segmentation task, although the model is supposed to learn the…

Time domain astronomy has emerged as a vibrant research field in recent years, focusing on celestial objects that exhibit variable magnitudes or positions. Given the urgency of conducting follow-up observations for such objects, the…

Whilst astronomy as a science is historically founded on observations at optical wavelengths, studying the Universe in other bands has yielded remarkable discoveries, from pulsars in the radio, signatures of the Big Bang at submm…

Geometric machine learning models such as graph neural networks have achieved remarkable success in recent years in chemical and materials science research for applications such as high-throughput virtual screening and atomistic…

Consistency models, which were proposed to mitigate the high computational overhead during the sampling phase of diffusion models, facilitate single-step sampling while attaining state-of-the-art empirical performance. When integrated into…

Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…

The advances in remote sensing technologies have boosted applications for Earth observation. These technologies provide multiple observations or views with different levels of information. They might contain static or temporary views with…

A long-standing challenge in developing machine learning approaches has been the lack of high-quality labeled data. Recently, models trained with purely synthetic data, here termed synthetic clones, generated using large-scale pre-trained…

Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing robustness benchmarks provide important stress tests, but…

On-board processing of hyperspectral data with machine learning models would enable unprecedented amount of autonomy for a wide range of tasks, for example methane detection or mineral identification. This can enable early warning system…

Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be observed, yet the corresponding symmetry transformation…

Scientific machine learning (SciML) increasingly requires models that capture multimodal conditional uncertainty arising from ill-posed inverse problems, multistability, and chaotic dynamics. While recent work has favored highly expressive…

Few-shot learning aims to transfer information from one task to enable generalization on novel tasks given a few examples. This information is present both in the domain and the class labels. In this work we investigate the complementary…

Vision-Language Models (VLMs), such as recent Qwen and Gemini models, are positioned as general-purpose AI systems capable of reasoning across domains. Yet their capabilities in scientific imaging, especially on unfamiliar and potentially…

Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The…

The Astrophysical Multimessenger Observatory Network (AMON) has been built with the purpose of enabling near real-time coincidence searches using data from leading multimessenger observatories and astronomical facilities. Its mission is to…

The ability to build a model on a source task and subsequently adapt such model on a new target task is a pervasive need in many astronomical applications. The problem is generally known as transfer learning in machine learning, where…