Related papers: Climplicit: Climatic Implicit Embeddings for Globa…

Multi-agent geographical models integrate very large numbers of spatial interactions. In order to validate those models large amount of computing is necessary for their simulation and calibration. Here a new data processing chain including…

Many scientific prediction problems have spatiotemporal data- and modeling-related challenges in handling complex variations in space and time using only sparse and unevenly distributed observations. This paper presents a novel deep…

Decision trees and models that use them as primitives are workhorses of machine learning in Euclidean spaces. Recent work has further extended these models to the Lorentz model of hyperbolic space by replacing axis-parallel hyperplanes with…

Predicting individuals' next locations is a core task in human mobility modelling, with wide-ranging implications for urban planning, transportation, public policy and personalised mobility services. Traditional approaches largely depend on…

In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. While thousands of…

Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval,…

Semantic maps allow a robot to reason about its surroundings to fulfill tasks such as navigating known environments, finding specific objects, and exploring unmapped areas. Traditional mapping approaches provide accurate geometric…

Land cover classification (LCC), and monitoring how land use changes over time, is an important process in climate change mitigation and adaptation. Existing approaches that use machine learning with Earth observation data for LCC rely on…

Large data-driven physics models like DeepMind's weather model GraphCast have empirically succeeded in parameterizing time operators for complex dynamical systems with an accuracy reaching or in some cases exceeding that of traditional…

We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of…

Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps…

As large-scale heterogeneous data sets become increasingly available, adapting foundation models at low cost has become a key issue. Seminal works in natural language processing, e.g. Low-Rank Adaptation (LoRA), leverage the low "intrinsic…

The more than 200,000 glaciers outside the ice sheets play a crucial role in our society by influencing sea-level rise, water resource management, natural hazards, biodiversity, and tourism. However, only a fraction of these glaciers…

Representation learning aims to extract meaningful lower-dimensional embeddings from data, known as representations. Despite its widespread application, there is no established definition of a ``good'' representation. Typically, the…

The increasing energy demands and carbon footprint of large-scale AI require intelligent workload management in globally distributed data centers. Yet progress is limited by the absence of benchmarks that realistically capture the interplay…

An increasing focus on the electricity use and carbon emissions associated with computing has lead to pledges by major cloud computing companies to lower their carbon footprint. Data centers have a unique ability to shift computing load…

We propose a novel learning-based formulation for visual localization of vehicles that can operate in real-time in city-scale environments. Visual localization algorithms determine the position and orientation from which an image has been…

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has…

Understanding and reasoning about places and their relationships are critical for many applications. Places are traditionally curated by a small group of people as place gazetteers and are represented by an ID with spatial extent, category,…

In this paper, we demonstrate that CLIP can also be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data, all without requiring fine-tuning. We explore the case of…