Related papers: AION-1: Omnimodal Foundation Model for Astronomica…
Deep learning methods have significantly advanced the development of intelligent rinterpretation in remote sensing (RS), with foundational model research based on large-scale pre-training paradigms rapidly reshaping various domains of Earth…
Type Ia supernovae (SNe Ia) were instrumental in establishing the acceleration of the universe's expansion. By virtue of their combination of distance reach, precision, and prevalence, they continue to provide key cosmological constraints,…
There is a global aging population requiring the need for the right tools that can enable older adults' greater independence and the ability to age at home, as well as assist healthcare workers. It is feasible to achieve this objective by…
Ocean modeling is a powerful tool for simulating the physical, chemical, and biological processes of the ocean, which is the foundation for marine science research and operational oceanography. Modern numerical ocean modeling mainly…
We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable…
This work introduces ILIAS, a new test dataset for Instance-Level Image retrieval At Scale. It is designed to evaluate the ability of current and future foundation models and retrieval techniques to recognize particular objects. The key…
The low-frequency sky below $\sim$15 MHz (20 m) is obscured by the Earth's ionosphere, the layer of charged particles above the neutral atmosphere. Single spacecraft have made measurements in this band, but cannot achieve high or even…
As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement.…
Measurement of the global 21-cm signal during Cosmic Dawn (CD) and the Epoch of Reionization (EoR) is made difficult by bright foreground emission which is 2-5 orders of magnitude larger than the expected signal. Fitting for a…
Inertial odometry (IO) directly estimates the position of a carrier from inertial sensor measurements and serves as a core technology for the widespread deployment of consumer grade localization systems. While existing IO methods can…
Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptability of visual features. These issues are particularly…
Ultrasound images vary widely across scanners, operators, and anatomical targets, which often causes models trained in one setting to generalize poorly to new hospitals and clinical conditions. The Foundation Model Challenge for Ultrasound…
We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of…
In astronomy, we are witnessing an enormous increase in the number of source detections, precision, and diversity of measurements. Additionally, multi-epoch data is becoming the norm, making time-series analyses an important aspect of…
Context. The [CII] 158micron far-infrared fine-structure line is one of the dominant cooling lines of the star-forming interstellar medium (ISM). Hence [CII] emission originates in and thus can be used to trace a range of ISM processes.…
Recent advances in geometric foundation models have emerged as a promising alternative for addressing the challenge of dense reconstruction in monocular visual simultaneous localization and mapping (SLAM). Although geometric foundation…
Accurate motion tracking of snow particles in avalanche events requires robust localization in global navigation satellite system (GNSS)-denied outdoor environments. This paper introduces AoI-FusionNet, a tightly coupled deep learning-based…
Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the multimodal real world. In the era of…
Gaia mission will offer an exceptional opportunity to perform variability studies. The data homogeneity, its optimised photometric systems, composed of 11 medium and 4-5 broad bands, the high photometric precision in G band of one milli-mag…
We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from…