@annabavaresco.bsky.social and
@tlmnhut.bsky.social show: supervised pruning of a DNN’s feature space better aligns with human category representations, selects distinct subspaces for different categories, and more accurately predicts people’s preferences for GenAI images.
doi.org/10.1145/3768...

✨ Do self-supervised speech models learn to encode language-specific linguistic features from their training data, or only more language-general acoustic correlates?

At #Interspeech2025 we presented our new Wav2Vec2-NL model and SSL-NL evaluation dataset to test this!

📄 arxiv.org/abs/2506.00981

⬇️

Had such a great time presenting our tutorial on Interpretability Techniques for Speech Models at #Interspeech2025! 🔍

For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...

As always, I'm thankful to Raquel Fernández, who supervised this work, agreed to pose for the moderately cringe picture, and presented this other work carried out together with @mdhk.net and Sandro Pezzelle 👇

arxiv.org/abs/2407.17914

I also had the opportunity to present this work on experiential semantic information in multimodal and language-only models, recently published at CoNLL 👇

aclanthology.org/2025.conll-1...

What a privilege to have #CCN2025 in (an exceptionally warm and sunny) Amsterdam this year!

It was my first time attending the conference, and being surrounded by so many talented researchers whose interests are similar to mine has been a deeply enriching experience ✨