Related papers: Towards an astronomical foundation model for stars…

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them…

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

Significant progress in the development of highly adaptable and reusable Artificial Intelligence (AI) models is expected to have a significant impact on Earth science and remote sensing. Foundation models are pre-trained on large unlabeled…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks and domains, with data playing a central role in enabling these advances. Despite this success, the preparation and effective utilization of…

We use methods of differential astrometry to construct a small field inertial reference frame stable at the micro-arcsecond level. Such a high level of astrometric precision can be expected with the end-of-mission standard errors to be…

We briefly review some constraints (Owing to the limited number of pages of present review, only a sub-sample of the topics discussed during the talk are briefly summarized. For the interested readers we are pleased to send them upon…

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…

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently…

Near-future astronomical survey experiments, such as LSST, possess system requirements of unprecedented fidelity that span photometry, astrometry and shape transfer. Some of these requirements flow directly to the array of science imaging…

Machine learning techniques offer a plethora of opportunities in tackling big data within the astronomical community. We present the set of Generalized Linear Models as a fast alternative for determining photometric redshifts of galaxies, a…

Large language models (LLMs) have demonstrated unprecedented emergent capabilities, including content generation, translation, and simulation of human behavior. Field experiments, on the other hand, are widely employed in social studies to…

Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range…

Characterizing protostellar outflows is fundamental to understanding star formation feedback, yet traditional methods are often hindered by projection effects and complex morphologies. We present a multi-modal deep learning framework that…

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

Just as humans can become disoriented in featureless deserts or thick fogs, not all environments are conducive to the Localization Accuracy and Stability (LAS) of autonomous robots. This paper introduces an efficient framework designed to…

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Information on the spectral types of stars is of great interest in view of the exploitation of space-based imaging surveys. In this article, we investigate the classification of stars into spectral types using only the shape of their…

Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys…

With the exponential increase in online scientific literature, identifying reliable domain-specific data has become increasingly important but also very challenging. Manual data collection and filtering for domain-specific scientific…

In this study, we use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framework has been proposed as a method to solve computer vision…