Tootfinder

Anna-Karin Hatts avhopp borde vara en larmklocka. Det är dags för svenska politiker och makthavare i opinionssfären att agera.
Ett första enkelt steg finns: lämna X.
Många har redan bytt plattform till Mastodon, Bluesky m.fl. Ta ert ansvar, proffstyckare, gör det ni också.

I wrote a blog post that could be seen as depressing, but I think it's full of hope and perhaps you'll agree.
I'd like to hear what you think.
https://rasterweb.net/raster/2025/12/16/the-book-of-pete/

The Book of Pete
Something for when I am gone I guess...

Listening, Imagining \& Refining: A Heuristic Optimized ASR Correction Framework with LLMs
Yutong Liu, Ziyue Zhang, Yongbin Yu, Xiangxiang Wang, Yuqing Cai, Nyima Tashi
https://arxiv.org/abs/2509.15095

Listening, Imagining \& Refining: A Heuristic Optimized ASR Correction Framework with LLMs
Automatic Speech Recognition (ASR) systems remain prone to errors that affect downstream applications. In this paper, we propose LIR-ASR, a heuristic optimized iterative correction framework using LLMs, inspired by human auditory perception. LIR-ASR applies a "Listening-Imagining-Refining" strategy, generating phonetic variants and refining them in context. A heuristic optimization with finite state machine (FSM) is introduced to prevent the correction process from being trapped in local optima…

The Los Angeles Times Guild reached a tentative agreement with management after more than three years of bargaining, averting a strike authorized by members (Tess Patton/The Wrap)
https://www.thewrap.com/los-angeles-times-guild-averts-strike-tentative-agree…

LA Times Guild Averts Strike With Tentative Agreement After 3 Years of Bargaining
The union of journalists will meet Monday to outline the proposed deal with management "on all outstanding issues in the contract"

Finalmente terminei de corrigir essas provas. Agora é só digitar no computador. Mas jš estš tão tarde que estou pensando em deixar isso para amanhã. Os alunos que lutem com a ansiedade deles.

ACADATA: Parallel Dataset of Academic Data for Machine Translation
I\~naki Lacunza, Javier Garcia Gilabert, Francesca De Luca Fornaciari, Javier Aula-Blasco, Aitor Gonzalez-Agirre, Maite Melero, Marta Villegas
https://arxiv.org/abs/2510.12621

ACADATA: Parallel Dataset of Academic Data for Machine Translation
We present ACADATA, a high-quality parallel dataset for academic translation, that consists of two subsets: ACAD-TRAIN, which contains approximately 1.5 million author-generated paragraph pairs across 96 language directions and ACAD-BENCH, a curated evaluation set of almost 6,000 translations covering 12 directions. To validate its utility, we fine-tune two Large Language Models (LLMs) on ACAD-TRAIN and benchmark them on ACAD-BENCH against specialized machine-translation systems, general-purpos…

From Who Said What to Who They Are: Modular Training-free Identity-Aware LLM Refinement of Speaker Diarization
Yu-Wen Chen, William Ho, Maxim Topaz, Julia Hirschberg, Zoran Kostic
https://arxiv.org/abs/2509.15082

From Who Said What to Who They Are: Modular Training-free Identity-Aware LLM Refinement of Speaker Diarization
Speaker diarization (SD) struggles in real-world scenarios due to dynamic environments and unknown speaker counts. SD is rarely used alone and is often paired with automatic speech recognition (ASR), but non-modular methods that jointly train on domain-specific data have limited flexibility. Moreover, many applications require true speaker identities rather than SD's pseudo labels. We propose a training-free modular pipeline combining off-the-shelf SD, ASR, and a large language model (LLM) to d…

STaTS: Structure-Aware Temporal Sequence Summarization via Statistical Window Merging
Disharee Bhowmick, Ranjith Ramanathan, Sathyanarayanan N. Aakur
https://arxiv.org/abs/2510.09593

STaTS: Structure-Aware Temporal Sequence Summarization via Statistical Window Merging
Time series data often contain latent temporal structure, transitions between locally stationary regimes, repeated motifs, and bursts of variability, that are rarely leveraged in standard representation learning pipelines. Existing models typically operate on raw or fixed-window sequences, treating all time steps as equally informative, which leads to inefficiencies, poor robustness, and limited scalability in long or noisy sequences. We propose STaTS, a lightweight, unsupervised framework for …

Zero-shot image privacy classification with Vision-Language Models
Alina Elena Baia, Alessio Xompero, Andrea Cavallaro
https://arxiv.org/abs/2510.09253 https://

Zero-shot image privacy classification with Vision-Language Models
While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking the performance ceiling set by purpose-built models due to a lack of systematic evaluation. To address this problem, we establish a zero-shot benchmark for image privacy classification, enabling a fair comparison. We evaluate the top-3 open-source VLMs, accor…

Sources: Microsoft's US data center crunch will last through H1 2026, longer than previously outlined, as the company restricts new Azure cloud subscriptions (Brody Ford/Bloomberg)
https://www.bloomberg.com/news/articles/20