Related papers: Cryo-Bench: Benchmarking Foundation Models for Cry…
The increasing availability of geospatial foundation models has the potential to transform remote sensing applications such as land cover classification, environmental monitoring, and change detection. Despite promising benchmark results,…
Training deep neural networks remains computationally intensive due to the itera2 tive nature of gradient-based optimization. We propose Gradient Flow Matching (GFM), a continuous-time modeling framework that treats neural network training…
Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to…
Foundation models are reshaping medical imaging, yet their application in echocardiography remains limited, hindered by a heavy reliance on private datasets that prevent reproducible comparison. Echocardiography poses unique challenges,…
Artificial Intelligence (AI) Foundation models (FMs), pre-trained on massive unlabelled datasets, have the potential to drastically change AI applications in ocean science, where labelled data are often sparse and expensive to collect. In…
The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and informed decision-making. Earth Observation (EO), powered by satellite data and Machine Learning (ML),…
Foundation models (FMs) are a popular topic of research in AI. Their ability to generalize to new tasks and datasets without retraining or needing an abundance of data makes them an appealing candidate for applications on specialist…
Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines,…
The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data from dense geophone deployments, distributed acoustic sensing (DAS) arrays, and large-scale 2D and…
Pathology foundation models (PFMs) have rapidly advanced and are becoming a common backbone for downstream clinical tasks, offering strong transferability across tissues and institutions. However, for dense prediction (e.g., segmentation),…
We introduce NeuCo-Bench, a novel benchmark framework for evaluating (lossy) neural compression and representation learning in the context of Earth Observation (EO). Our approach builds on fixed-size embeddings that act as compact,…
High-fidelity Monte Carlo simulations and complex inverse problems, such as mapping smeared experimental observations to ground-truth states, are computationally intensive yet essential for robust data analysis. Conditional Flow Matching…
Simulating fluid flow around arbitrary shapes is key to solving various engineering problems. However, simulating flow physics across complex geometries remains numerically challenging and computationally resource-intensive, particularly…
Pre-trained Foundation Models (PFMs) have ushered in a paradigm-shift in Artificial Intelligence, due to their ability to learn general-purpose representations that can be readily employed in a wide range of downstream tasks. While PFMs…
Foundation models (FMs), large neural networks pretrained on extensive and diverse datasets, have revolutionized artificial intelligence and shown significant promise in medical imaging by enabling robust performance with limited labeled…
Foundation Models (FMs) have shown impressive performance on various text and image processing tasks. They can generalize across domains and datasets in a zero-shot setting. This could make them suitable for automated quality inspection…
Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As…
This paper introduces WavesFM, a novel Wireless Foundation Model (WFM) framework, capable of supporting a wide array of communication, sensing, and localization tasks. Our proposed architecture combines a shared Vision Transformer (ViT)…
Visual foundation models (VFMs) have become increasingly popular due to their state-of-the-art performance. However, interpretability remains crucial for critical applications. In this sense, self-explainable models (SEM) aim to provide…
As urbanization and climate change progress, urban heat island effects are becoming more frequent and severe. To formulate effective mitigation plans, cities require detailed air temperature data. However, predictive analytics methods based…