Tootfinder

A few weeks ago we passed by a building with a sign "Cruz Foam" and we wondered what it was.
Well here it is...
"Bay Area biomaterials engineers say time’s up for plastic foam - How Santa Cruz nature lovers are creating biodegradable packing materials at cost and scale"
I really wish them success; I dislike styrofoam, especially that kind that breaks into little soft rice-grain sized beads.

Bay Area biomaterials engineers say time’s up for plastic foam
Could pea starch help reduce ocean plastics and become the new plastic?

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…

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…

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 "…

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…

Day 21 of the road trip was a big day sightseeing around the Cape Leeuwin area. The Cape is the south western most tip of Australia and where the Indian Ocean meets the Southern Ocean. Wild seas, wild winds but a great day. #RoadTrip

WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
Atila Orhon, Arda Okan, Berkin Durmus, Zach Nagengast, Eduardo Pacheco
https://arxiv.org/abs/2507.10860

WhisperKit: On-device Real-time ASR with Billion-Scale Transformers
Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse s…

Evaluating the Quality of Open Building Datasets for Mapping Urban Inequality: A Comparative Analysis Across 5 Cities
Franz Okyere, Meng Lu, Ansgar Brunn
https://arxiv.org/abs/2508.12872

Evaluating the Quality of Open Building Datasets for Mapping Urban Inequality: A Comparative Analysis Across 5 Cities
While informal settlements lack focused development and are highly dynamic, the quality of spatial data for these places may be uncertain. This study evaluates the quality and biases of AI-generated Open Building Datasets (OBDs) generated by Google and Microsoft against OpenStreetMap (OSM) data, across diverse global cities including Accra, Nairobi, Caracas, Berlin, and Houston. The Intersection over Union (IoU), overlap analysis and a positional accuracy algorithm are used to analyse the simil…

I finished watching this #Netflix documentary about the #Antwerp 🇧🇪 diamond heist in 2003 and while the film itself is your typical interesting and informative Netflix-style docu, I am again peeved that #OpenStreetMap

Love a night walk on the beach. Looks like I interrupted someone’s dinner.