Tootfinder

MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech
Jialong Mai, Jinxin Ji, Xiaofen Xing, Chen Yang, Weidong Chen, Jingyuan Xing, Xiangmin Xu
https://arxiv.org/abs/2509.18196

MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech
Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NVs convey crucial emotional and intentional cues. Progress in NV-aware ASR has been hindered by the lack of high-quality, well-annotated datasets. To address this gap, we introduce MNV-17, a 7.55-hour…

The man suspected of the shooting at Brown University that killed two students and wounded nine others Saturday
-- and killing an MIT professor days later
-- was found dead in Salem, New Hampshire.
The suspect was identified as Claudio Manuel Neves Valente
Neves Valente had been a PhD program student in physics at Brown.
He is believed to have attended the same university in Lisbon, Portugal, as
Nuno Gomes Loureiro,
Loureiro,
who was a member of …

Suspected Brown shooter Valente is found dead, authorities say
The suspected gunman, Claudio Manuel Nueves Valente, 48, had been a graduate students in physics at Brown University in the early 2000s, authorities said.

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation
Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
https://arxiv.org/abs/2512.17820 https://arxiv.org/pdf/2512.17820 https://arxiv.org/html/2512.17820
arXiv:2512.17820v1 Announce Type: new
Abstract: Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.
toXiv_bot_toot

Any #Python newbies out there? (Or experts that need to teach Python)
Would you have a specific online tutorial to recommend for someone who wants to learn Python without any prior programming experience? One that also explains how to install it ?
I was thinking of something like this:

Welcome To The Python Tutorial
Learn to program with this free Python tutorial for beginners. It's free, easy to read and lets you practice with in-browser code examples.

Three labor unions filed a lawsuit in NY federal court to block the Trump administration from searching visa holders' social media for posts it deems hostile (David Ingram/NBC News)
https://www.nbcnews.com/tech/social-media/trump-so…

Unions sue Trump administration over social media 'surveillance'
Three unions represented by the Electronic Frontier Foundation sued the Trump administration over a program that searches social media posts of visa holders.

Big Facts: Williams 4th in pressures since arrival https://www.dallascowboys.com/news/big-facts-williams-4th-in-pressures-since-arrival

En Nombre del Progreso (In the Name of Progress)
2017 by Alfonso "Piloto" Nieves Ruiz, active in the United States, born Querétaro, Mexico. at Intuit Art Museum, West Town, #Chicago

Scientists at NeurIPS, which drew a record 26,000 attendees this year, say key questions about how AI models work and how to measure them remain unresolved (Jared Perlo/NBC News)
https://www.nbcnews.com/tech/tech-news/ai-progress-surges-resea…

AI progress surges while researchers struggle to explain It
Academics, start-up founders and researchers representing industrial titans from around the globe descended on San Diego for the top gathering in AI.

# of paragraphs for news orgs to mention that there's no discernable need to deploy troops to Portland, Oregon
The Guardian: 1st paragraph
BBC: 4th paragraph
AP: 5th paragraph
Time: 6th paragraph
Politico: 8th paragraph
NPR: 9th paragraph
CNN: 10th paragraph
NBC: 12th paragraph
Fox News: never mentioned

Modeling Student Learning with 3.8 Million Program Traces
Alexis Ross, Megha Srivastava, Jeremiah Blanchard, Jacob Andreas
https://arxiv.org/abs/2510.05056 https://

Modeling Student Learning with 3.8 Million Program Traces
As programmers write code, they often edit and retry multiple times, creating rich "interaction traces" that reveal how they approach coding tasks and provide clues about their level of skill development. For novice programmers in particular, these traces reflect the diverse reasoning processes they employ to code, such as exploratory behavior to understand how a programming concept works, re-strategizing in response to bugs, and personalizing stylistic choices. In this work, we explore what ca…