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.

unicodelang: Languages spoken by country (2015)
A bipartite network of languages and the countries in which they are spoken, as estimated by Unicode. Edges are weighted by the proportion of the given country's population that is literate in a particular language.
This network has 868 nodes and 1255 edges.
Tags: Informational, Relatedness, Weighted

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…

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…

Am heutigen #SchiffsSamstag ein von mir mit meinem alten Händie geknipsten Foto der niederländischen Brigg APHRODITE auf der Elbe bei Nienstedten (Hamburg).

I’ve spoken with my boss (he’s a bit of a dickhead but his heart’s in the right place) and confirmed that I won’t be getting fired for opposing Israel’s ongoing genocide and supporting the human rights of the Palestinian people to live with freedom and dignity like the rest of us but not everyone is as lucky.

Pro-Palestinian influencer Dr. Nahla Al-Sarraj fired following Zionist smear campaign
Dr. Nahla Al-Sarraj gained hundreds of thousands of social media followers by discussing the Gaza genocide. She was fired after a pressure campaign from Israel lobby groups that she believes aimed to silence her. Despite this, she remains unbowed.

Spagnola: Don’t think George curious anymore https://www.dallascowboys.com/news/spagnola-don-t-think-george-curious-anymore

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…

Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
Guojian Li, Qijie Shao, Zhixian Zhao, Shuiyuan Wang, Zhonghua Fu, Lei Xie
https://arxiv.org/abs/2510.11732 …

Serial-Parallel Dual-Path Architecture for Speaking Style Recognition
Speaking Style Recognition (SSR) identifies a speaker's speaking style characteristics from speech. Existing style recognition approaches primarily rely on linguistic information, with limited integration of acoustic information, which restricts recognition accuracy improvements. The fusion of acoustic and linguistic modalities offers significant potential to enhance recognition performance. In this paper, we propose a novel serial-parallel dual-path architecture for SSR that leverages acoustic…

Hi everyone,
@… and I had the honour of speaking to four lovely people from Gaza today over video chat on Signal and we’d like to welcome them to the Gaza Verified family:
• @…
• @…

Gaza Verified
I’ve personally had video conversations on Signal with the people from Gaza whose Mastodon accounts on the fediverse are listed here and I verify that their accounts are genuine. – Aral Balkan