Related papers: AION-1: Omnimodal Foundation Model for Astronomica…
We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series…
While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building multimodal foundation models is a natural next step, but it…
Gaia is a fully-approved all-sky astrometric and photometric survey due for launch in 2011. It will measure accurate parallaxes and proper motions for everything brighter than G=20 (ca. 10^9 stars). Its primary objective is to study the…
The rapid advancement of foundation models has revolutionized visual representation learning in a self-supervised manner. However, their application in remote sensing (RS) remains constrained by a fundamental gap: existing models…
We present VisionFM, a foundation model pre-trained with 3.4 million ophthalmic images from 560,457 individuals, covering a broad range of ophthalmic diseases, modalities, imaging devices, and demography. After pre-training, VisionFM…
The Internet of Drones (IoD) recently gained momentum due to its high adaptability to a wide variety of complex scenarios. Indeed, Unmanned Aerial Vehicles (UAVs) can successfully be employed in different applications, thanks to some…
The Laser Interferometer Space Antenna (LISA) will be a transformative experiment for gravitational wave astronomy, and, as such, it will offer unique opportunities to address many key astrophysical questions in a completely novel way. The…
The International Axion Observatory (IAXO) is a next generation axion helioscope aiming at a sensitivity to the axion-photon coupling of a few 10^{-12} GeV^{-1}, i.e. 1-1.5 orders of magnitude beyond sensitivities achieved by the currently…
Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety…
The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor data. While foundation models excel in single-modal…
Gaia will observe more than one billion objects brighter than V=20, including stars, asteroids, galaxies and quasars. As Gaia performs real time detection (i.e. without an input catalogue) the intrinsic properties of most of these objects…
Aerosols influence weather and climate by interacting with radiation through absorption and scattering. These effects heavily rely on the optical properties of aerosols, which are mainly governed by attributes such as morphology, size…
Hyperspectral Imaging, employed in satellites for space remote sensing, like HYPSO-1, faces constraints due to few labeled data sets, affecting the training of AI models demanding these ground-truth annotations. In this work, we introduce…
This work presents SSL4EO-S12 v1.1, a multimodal, multitemporal Earth Observation dataset designed for pretraining large-scale foundation models. Building on the success of SSL4EO-S12, this extension updates the previous version to fix…
State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While this paradigm has revolutionized RGB generation, Earth observation (EO)…
Earth observation (EO), aiming at monitoring the state of planet Earth using remote sensing data, is critical for improving our daily lives and living environment. With a growing number of satellites in orbit, an increasing number of…
In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations…
Type Ia Supernovae (SNe Ia) are crucial tools to measure the accelerating expansion of the universe, comprising thousands of SNe across multiple telescopes. Accurate measurements of cosmological parameters with SNe Ia require a robust…
In recent years, the foundation models have swept the computer vision field and facilitated the development of various tasks within different modalities. However, it remains an open question on how to design an infrared foundation model. In…
The International AXion Observatory (IAXO) is a large scale axion helioscope that will look for axions and axion-like particles produced in the Sun with unprecedented sensitivity. BabyIAXO is an intermediate experimental stage that will be…