Tootfinder

FS-DFM: Neue Apple-KI-Modelle spucken lange Texte sehr schnell aus
Mittels "Few-Step Discrete Flow-Matching" will Apple beim Output großer Sprachmodelle den Turbo einschalten. Kooperationspartner ist eine US-Hochschule.

Writer Stephanie Wambugu on speaking across generations
#creativity
https://

Writer Stephanie Wambugu on speaking across generations – The Creative Independent
Writer Stephanie Wambugu discusses the conflict of art-world representation, acting as a vessel of human emotion, and resisting trend forecasting.

Spagnola: So many heroes in this heroic victory https://www.dallascowboys.com/news/spagnola-so-many-heroes-in-this-heroic-victory

Spokane ICE protesters, including Stuckart, arrested by federal agents (Spokesman.com)
https://www.spokesman.com/stories/2025/jul/15/spokane-ice-protesters-including-stuckart-arrested/
http://www.memeorandum.com/250715/p109#a250715p109

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions
Jun Zhan, Mingyang Han, Yuxuan Xie, Chen Wang, Dong Zhang, Kexin Huang, Haoxiang Shi, DongXiao Wang, Tengtao Song, Qinyuan Cheng, Shimin Li, Jun Song, Xipeng Qiu, Bo Zheng
https://arxiv.org/abs/2509.09716

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions
Spoken language models (SLMs) have emerged as a unified paradigm for speech understanding and generation, enabling natural human machine interaction. However, while most progress has focused on semantic accuracy and instruction following, the ability of SLMs to adapt their speaking style based on spoken instructions has received limited attention. We introduce Voice Style Adaptation (VSA), a new task that examines whether SLMs can modify their speaking style, such as timbre, prosody, or persona…

🇺🇦 Auf radioeins läuft...
Sophia Kennedy:
🎵 Imaginary Friend (Radio Edit)
#NowPlaying #SophiaKennedy
https://sophiakennedy.bandcamp.com/track/imaginary-friend
https://open.spotify.com/track/7CbVZ2Yzl0TtcCERaJDZSR

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
Nizar El Ghazal, Antoine Caubri\`ere, Valentin Vielzeuf
https://arxiv.org/abs/2510.09424

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing p…

More than a dozen Border Patrol agents turned up in downtown Los Angeles on Thursday
at a rally and news conference that
Gov. Gavin Newsom was holding on congressional redistricting.
The governor’s event had nothing to do with immigration,
and local elected officials expressed outrage
that the federal agents decided to stand there in a brazen show of force outside a museum
where Mr. Newsom and other leaders were speaking.
As the governor was preparin…

Border Patrol Agents Show Up in Force at Newsom Rally
The armed and masked agents assembled outside a museum where the governor was speaking in what Mayor Karen Bass of Los Angeles called “a provocative act.”

Some Swiss-German speaking folks just don't realize how impolite and disrespectful it is to default to Swiss-German in the middle of conversations, Zoom calls, or similar professional situations where they know for a fact that there are non-Swiss-German speaking attendees (or from abroad!) in the meeting. Whatever the language chosen for a particular meeting, and for the sake of inclusivity and understanding, be respectful. Even native Germans and Austrians struggle with Swiss-German, p…

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Donghang Wu (Tony), Haoyang Zhang (Tony), Jun Chen (Tony), Xiangyu (Tony), Zhang, Hexin Liu, Eng Siong Chng, Fei Tian, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu
https://arxiv.org/abs/2510.09592

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially. Enabling SLMs to think while speaking, similar to humans, is attracting increasing attention. We present, for the first time, Mind-Paced Speaking (MPS), a brain-inspired framework that enables high-fidelity, real-time reasoning. Similar to how humans utilize distinct brain regions for thinking and responding, we propo…