Tootfinder

CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
Md Hasibul Amin, Mohammadreza Mohammadi, Jason D. Bakos, Ramtin Zand
https://arxiv.org/abs/2505.22868 …

CrossNAS: A Cross-Layer Neural Architecture Search Framework for PIM Systems
In this paper, we propose the CrossNAS framework, an automated approach for exploring a vast, multidimensional search space that spans various design abstraction layers-circuits, architecture, and systems-to optimize the deployment of machine learning workloads on analog processing-in-memory (PIM) systems. CrossNAS leverages the single-path one-shot weight-sharing strategy combined with the evolutionary search for the first time in the context of PIM system mapping and optimization. CrossNAS se…

Time For 9 o'clock #HashTagGames hosted by @… Let's play!
#MovieSubPlots

Viewing large language models as compression machines helps explain why they seem at turns big-brained and pea-brained. To learn more, join me for Honey, AI Shrunk the Archive, an IEEE/UMaine AI webinar next Thursday 3 April at noon Eastern
https://ai.umaine.edu/webinars

Nothing I’m trying to write is "flowing"...it's all laborious.
I'm encouraged by "Your labor isn’t a sign of defeat" from @… wherein she quotes Verlyn Klinkenborg:
"if you accept that writing is hard work, And that’s what it feels like when you’re writing, Then everything is as it should be. Your labor is…

Feedbackless Feed
A (non)social feedbackless feed to nowhere

Join Kevin Liang at this year's Berlin Buzzwords, where he will discuss how Apache Solr/Lucene builds dense vector indexes and talk about how he and his team optimised their dense vector setup, sharing the challenges they faced and the best practices they learned along the way.
Learn more: https…

Time For 9 o'clock #HashTagGames hosted by @…
It's Customer Experience Day. Let's play!
#ComplaintsAtFictionalBiz

ah yes, a representative for an obscure IPTV app targeting the Latin market, using a Chinese Telegram account made in the past 10 days. not suspicious at all.

This https://arxiv.org/abs/2503.09649 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Technical Insights and Legal Considerations for Advancing Federated Learning in Bioinformatics
Federated learning leverages data across institutions to improve clinical discovery while complying with data-sharing restrictions and protecting patient privacy. As the evolution of biobanks in genetics and systems biology has proved, accessing more extensive and varied data pools leads to a faster and more robust exploration and translation of results. More widespread use of federated learning may have the same impact in bioinformatics, allowing access to many combinations of genotypic, pheno…