Tootfinder

Neologism Learning for Controllability and Self-Verbalization
John Hewitt, Oyvind Tafjord, Robert Geirhos, Been Kim
https://arxiv.org/abs/2510.08506 https://

Neologism Learning for Controllability and Self-Verbalization
Humans invent new words when there is a rising demand for a new useful concept (e.g., doomscrolling). We explore and validate a similar idea in our communication with LLMs: introducing new words to better understand and control the models, expanding on the recently introduced neologism learning. This method introduces a new word by adding a new word embedding and training with examples that exhibit the concept with no other changes in model parameters. We show that adding a new word allows for …

Three updates to old posts this morning:
Another post pointing out CSS-only widgets are problematic:
https://adrianroselli.com/2023/03/css-only-widgets-are-inaccessible.html#Update02
Narrator is getting a Braille viewer:

CSS-only Widgets Are Inaccessible
Usually. I originally titled this InacCSS-onlyible. I even made this typographically, er, distinct image. Then I realized it was silly and will instead use the neologism in a talk so I can hear the groans IRL. Interactive widgets powered with only CSS are relatively common as people are playing with…

Who doesn’t love a good buzzword? It’s possible that half the tech industry (and a good proportion of tech journalism) wouldn’t exist if the industry didn’t hunger for a neologism. One of the latest (but not the latest) is vibe coding.
https://www.computing.co.uk/interview/2025

Don’t vibe that code
Azul’s CTO on when and when not to use LLMs to assist software development

« Tous se préparent Š l’après-thermique. »
This post by the Brussels DSO features a nice neologism.
One third of capacity increase requests by non-residential users in the Brussels region are for EV charging. In my opinion, this also suggests a huge potential for smarter energy management.

Pourquoi les entreprises bruxelloises demandent-elles plus de #puissance électrique ? | Sibelga
Pourquoi les entreprises bruxelloises demandent-elles plus de #puissance électrique ? La réponse tient en 2 mots : mobilité électrique ! Chaque jour, nous recevons des demandes de renforcement du réseau. Et dans plus d'1/3 des cas, c’est pour installer des #bornes de recharge pour véhicules électriques. Les Cliniques universitaires Saint-Luc, la prison de Haren, le site Mercedes… Tous se préparent à l’après-thermique. Chez Sibelga, la transition vers une mobilité durable et…

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
Yanfan Du, Jun Zhang, Bin Wang, Jin Qiu, Lu Huang, Yuan Ge, Xiaoqian Liu, Tong Xiao, Jingbo Zhu
https://arxiv.org/abs/2508.18701

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability estimation for robust speech-to-text system, which is lightweight, flexible, and accurate. Attention2Probability converts cross-attention weights between speech and terminology into presence probabili…