Tootfinder

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang
https://arxiv.org/abs/2508.20511

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages, curated with strict quality control protocols. However, we study data in four languages (Asante Twi, Japanese, Jinghpaw, and South Azerbaijani) and uncover critical shortcomings in the benchmark's suitability for truly multilingual evaluation. Human assessments…

🇺🇦 #NowPlaying on KEXP's #VarietyMix
The Lonely Forest:
🎵 We Sing in Time
#TheLonelyForest
https://trans-records.bandcamp.com/track/we-sing-in-time
https://open.spotify.com/track/6AkH6HrwBvlNS3PnoH9cYu
Please 🔁 BOOST to share what you like
- your followers don't see if you ⭐ favourite a post

Monitoring and performance of AugerPrime
Bel\'en Andrada (for the Pierre Auger Collaboration)
https://arxiv.org/abs/2507.08723 https://

Monitoring and performance of AugerPrime
The upgrade of Pierre Auger Observatory, AugerPrime, is a multi-hybrid system designed to improve the sensitivity and precision of ultra-high-energy cosmic ray measurements. It includes scintillator detectors positioned both atop the enhanced Water-Cherenkov detectors and buried nearby for direct muon measurements, along with radio and fluorescence detectors. In this contribution, we present an overview of the monitoring tools developed for all the components of AugerPrime, focusing on real-tim…

Adaptive Attention Residual U-Net for curvilinear structure segmentation in fluorescence microscopy and biomedical images
Achraf Ait Laydi, Louis Cueff, Mewen Crespo, Yousef El Mourabit, H\'el\`ene Bouvrais
https://arxiv.org/abs/2507.07800

Adaptive Attention Residual U-Net for curvilinear structure segmentation in fluorescence microscopy and biomedical images
Segmenting curvilinear structures in fluorescence microscopy remains a challenging task, particularly under noisy conditions and in dense filament networks commonly seen in vivo. To address this, we created two original datasets consisting of hundreds of synthetic images of fluorescently labelled microtubules within cells. These datasets are precisely annotated and closely mimic real microscopy images, including realistic noise. The second dataset presents an additional challenge, by simulating…