Tootfinder

This https://arxiv.org/abs/2505.23019 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Stairway to Success: Zero-Shot Floor-Aware Object-Goal Navigation via LLM-Driven Coarse-to-Fine Exploration
Object-Goal Navigation (OGN) remains challenging in real-world, multi-floor environments and under open-vocabulary object descriptions. We observe that most episodes in widely used benchmarks such as HM3D and MP3D involve multi-floor buildings, with many requiring explicit floor transitions. However, existing methods are often limited to single-floor settings or predefined object categories. To address these limitations, we tackle two key challenges: (1) efficient cross-level planning and (2) z…

Oof. #OpenStreetMap minutely replication is currently broken: https://community.openstreetmap.org/t/131884
For me this means that recent edits I made are not queryable via O…

Is OSM partially down? New data isn't able to be queried on the map, and new data isn't being rendered
I’m finding that I can pull data into JOSM and iD that I know exists (due to recently pushed edits), but a query on the map doesn’t list them (not to mention that they also aren’t being rendered; however, when something’s awaiting rendering, I always, at least by my experience, can still query it). For example, this query should list building=toilets, but it doesn’t. If I edit that location in iD I can see the aforementioned feature, and I can also pull it into JOSM, but it isn’t b…

Accurate Mediterranean Sea forecasting via graph-based deep learning
Daniel Holmberg, Emanuela Clementi, Italo Epicoco, Teemu Roos
https://arxiv.org/abs/2506.23900

Accurate Mediterranean Sea forecasting via graph-based deep learning
Accurate ocean forecasting systems are essential for understanding marine dynamics, which play a crucial role in sectors such as shipping, aquaculture, environmental monitoring, and coastal risk management. Traditional numerical solvers, while effective, are computationally expensive and time-consuming. Recent advancements in machine learning have revolutionized weather forecasting, offering fast and energy-efficient alternatives. Building on these advancements, we introduce SeaCast, a neural n…

I just played a bit with #openstreetmap, and wow, this is a mess! The renderers are doing their best, but what should they do with buildings tagged as "…

What is Past is Prologue:
#Paleoclimate constraints on #ECS Equilibrium #ClimateSensitivity #GreenhouseGas sensitivity of Earth's #Climate
First of 3 papers this summer.
My career trajectory has been building towards using past climate archives to narrow the possibilities of future climate. But it is HARD. And computationally expensive.
The next two papers of this project will rule out some high and low sensitivity simulations using Past Climate (Proxy) archives and Data Assimilation. Those should be out in preprint in the next couple of months.
We hope this project (first to constrain earth climate sensitivity using coupled atmosphere-ocean earth system models) will be streamlined in the future and applied widely.
https://essopenarchive.org/users/921675/articles/1297441-on-the-sensitivity-of-climate-sensitivity-in-a-coupled-climate-model

Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
Piotr Gai\'nski, Oussama Boussif, Andrei Rekesh, Dmytro Shevchuk, Ali Parviz, Mike Tyers, Robert A. Batey, Micha{\l} Koziarski
https://arxiv.org/abs/2506.19865

Scalable and Cost-Efficient de Novo Template-Based Molecular Generation
Template-based molecular generation offers a promising avenue for drug design by ensuring generated compounds are synthetically accessible through predefined reaction templates and building blocks. In this work, we tackle three core challenges in template-based GFlowNets: (1) minimizing synthesis cost, (2) scaling to large building block libraries, and (3) effectively utilizing small fragment sets. We propose \textbf{Recursive Cost Guidance}, a backward policy framework that employs auxiliary m…

On the Efficacy of Ocean Formation with a Primordial Hydrogen Atmosphere
Darius Modirrousta-Galian, Jun Korenaga
https://arxiv.org/abs/2506.10417 https://

On the Efficacy of Ocean Formation with a Primordial Hydrogen Atmosphere
It has been suggested that Earth's present water budget formed from oxidation reactions between its initial hydrogen-rich primordial atmosphere and its magma ocean. Here we examine this hypothesis by building a comprehensive atmosphere-magma ocean model. We find that water formation is unlikely for two reasons. First, any water formed from oxidation reactions in the magma ocean would quickly outgass because of the water-poor atmosphere above. Second, the top boundary layer of the magma ocean be…

MLOps with Microservices: A Case Study on the Maritime Domain
Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Rowanne Trapmann (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)

MLOps with Microservices: A Case Study on the Maritime Domain
This case study describes challenges and lessons learned on building Ocean Guard: a Machine Learning-Enabled System (MLES) for anomaly detection in the maritime domain. First, the paper presents the system's specification, and architecture. Ocean Guard was designed with a microservices' architecture to enable multiple teams to work on the project in parallel. Then, the paper discusses how the developers adapted contract-based design to MLOps for achieving that goal. As a MLES, Ocean Guard emplo…

Ultra-lightweight multi-functional gyroid-based metamaterial for simultaneous sound insulation, vibration suppression, and impact mitigation in all directions
Evan Kluge, Osama R. Bilal
https://arxiv.org/abs/2506.09321

Ultra-lightweight multi-functional gyroid-based metamaterial for simultaneous sound insulation, vibration suppression, and impact mitigation in all directions
Multi-functional materials are increasingly essential in many applications due to their ability to serve multiple purposes, simultaneously. Metamaterials can offer tailored functionality based on carefully designed tessellating basic building blocks, or unit cells, in space. These unit cells are most commonly designed for a single objective, for example, to mitigate an impact, insulate sound, or dampen vibrations. However, a metamaterial that can mitigate impact, attenuate elastic vibrations, i…