Marianne de Heer Kloots

✨ Do current neural speech models show human-like linguistic biases in speech perception? We took inspiration from classic phonetic categorization experiments to explore where sensitivity to phonotactic context emerges in Wav2Vec2 models 🔍 (w/ @wzuidema.bsky.social) 📑 arxiv.org/abs/2407.03005 ⬇️

Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe At #EMNLP2026 @emnlpmeeting.bsky.social, @gaofeishen.com presents our poster tomorrow (Sun 25 Oct), 16:00–17:30, Hall H, Poster Session B. 📄 https://aclanthology.org/2026.emnlp-main.654/

door AI dreigen we nu te verliezen wat ons uiteindelijk mens maakt: andermans teksten beoordelen op gebruik van AI

🤖🧠NEW PAPER🧠🤖 What is the relationship between neural networks & symbolic systems? Based on evidence from mechanistic interpretability, we argue for a quasi-symbolic view of cognition: Neural nets implement symbols but only approximately Link: www.sciencedirect.com/science/arti... 1/n

Our workshop has been accepted to COLING! Keep an eye out for updates, for example through our shiny new subscribe button 👀 what-llms-can-not-do.org/subscribe

Great news! Our workshop what-llms-can-not-do.org is going to COLING 2027 in Macau! Hope to see you there!

delighted to share my review article, out now in Trends in Cognitive Sciences! i have been thinking a lot about dynamics lately. this article outlines three key principles - persistence, parallelism, and time-stamped encoding - that support human speech comprehension 🧠✨🌀

Time after time: neural codes of speech comprehension https://pubmed.ncbi.nlm.nih.gov/42830249/

I’m presenting this today at #SNL2026 in Geneva! See you at poster A5 in the morning session 🎉

the Gwilliams Lab and friends are at SNL 2026!! if you're into speech comprehension, intracranial and non-invasive time series, from single neurons to the whole cortex, across ages, using both classic linguistic approaches and advanced ML techniques - we've got something for you! 🧠 🌀 ✨

To make sense of speech, listeners must segment sound streams into pieces. Across languages, people do so based more on consonants than vowels. A new @science.org study investigates the phenomenon via EEG recording in humans & dogs, finding that dogs also show consonant bias in word segmentation.🗣️🐶🧪

📣📣📣 Preprint Alert! 📣📣📣 Do predictive processes shape brain representations during learning? We investigated the effect of Predictive Coding by training identical recurrent networks with different optimization procedures and then comparing them to human EEG under the same visual learning task.

Excited to share our review in @cp-neuron.bsky.social with @lauriebayet.bsky.social and @mickbonner.bsky.social! We describe how implementing principles from child development can advance the mechanistic plausibility and capacities of AI models We packed A LOT into this review, here's a quick 🧵

🦀New preprint! (w/ @najoung.bsky.social)🦞 Is grammaticality a major organizing principle of NLM representations? We show that many NLMs exhibit abstract rep. separation for grammaticality. We believe this work addresses debates about confounds in measuring model gram. knowledge. [1/10]

LLMs are everywhere, as are companies advertising LLM-powered products by their “beyond-human” performance levels. But how do LLMs *actually* fare against humans across the board? Join our effort to organize empirical evidence from the field into a systematic and publicly accessible overview ⬇️

Ever feel like it's too hard to keep track of what LLMs cannot do as well as humans? We're making your life easier over at: what-llms-can-not-do.github.io We're compiling a list of papers testing the abilities of LLMs against humans. Check it out! And you can help contribute too!

I fear that placing too much emphasis on a specific interpretation of dimensionality, or treating dimensionality as an end-all quantification of some aspect of neural computation, may lead us down the wrong path, writes @mattperich.bsky.social. #neuroskyence www.thetransmitter.org/neural-dynam...

look at my new babylm paper! arxiv.org/abs/2609.11870 basically, i initialize token embeddings with representations from an image encoder rather than randomly and then train text-only as usual. kind of a visual demonstration to start off the word learning process

A group of 25 Fields Medalists, including myself, have made a joint declaration on Math and AI: mathandai.org . We welcome additional signatories. See also this article in the Economist announcing the declaration: www.economist.com/science-and-...

I’m presenting this today at #CLIN36 in Brussels! See you at poster 25 in the afternoon session 🎉

🤖🧠NEW PAPER🧠🤖 (The result of an 8-year project!) LLMs seem very different from symbolic systems. Yet LLMs excel in symbolic domains (e.g., language/code/math). How do they do it? Our finding: LLM representations have implicit symbolic structure! Link in thread ⬇️ 1/n

New preprint 🐝🧵 arxiv.org/abs/2608.25779 Bee species signal food via their waggle dance in different ways. Species with horizontal combs point straight at food. Species with vertical combs dance relative to gravity instead. How could a population evolve from one system to the other?

New perspective piece out in @cp-neuron.bsky.social with Zaid Zada, @adelegoldberg.bsky.social, and Uri Hasson! We try to articulate some of our excitement about LLMs and discuss what kinds of insights they might provide into the neural computations supporting natural language in the human brain.

New Blog post: Which Data Repository Should you Use? In light of OSF closing down, I compare Zenodo, Dataverse, ResearchBox, PsychArchive, and local repositories on six important dimensions. If you want to know which to pick: It depends! daniellakens.blogspot.com/2026/08/whic...

I've been unsettled lately when reading messages and papers. It feels like I'm dissociating. Everything seems a bit alien, even if it's completely human. I've had a realization: When our simulations finally exited the Uncanny Valley, they brought the Uncanny with them.

Today is the only day you can experience Ray Bradbury’s “There Will Come Soft Rains” on the day it is set. Audio: archive.org/details/brad... PDF: thephilosopher.net/bredberi/wp-...

Let’s study learning trajectories in self-supervised speech models! 🔊 Do they reflect the hierarchical organization of spoken language? We have analyzed a lot of training checkpoints to find out 🌠 Preprint: arxiv.org/abs/2604.02043 ⬇️

1/5 Over a decade of comparing deep neural networks to the human brain—but what have we actually learned? Our new @cp-trendscognsci.bsky.social Feature Review synthesizes a decade of brain–DNN comparisons, asking what they reveal about brain function across vision and language.

Our ability to speak involves remarkable feats of motor sequencing that most of us take completely for granted. The new issue of @science.org has a fascinating essay by Sergey Stavisky, covering his team's use of brain-computer interfaces to restore speech for people with neurological injuries. 🧠🗣️🧪👇

Our paper "Rarely categorical, highly separable representations along the cortical hierarchy" is now out in Nature! www.nature.com/articles/s41... In this paper, we studied whether the brain is well-organized and interpretable, both globally and locally. (See thread below.)

What's more nonsensical: smashing a pumpkin using a number, or growing flowers inside a sneeze? Our paper on graded inconceivability is out now in Cognition! Come for the cognitive science 🧠🔍, stay for the whimsy 🌼🧚! 🔗Journal link: bit.ly/gradedInconCog

The full BBS treatment from me and @futrell.bsky.social on "How linguistics learned to stop worrying and love the LMs" is now out, with all the commentaries and our response. If you "Save PDF", it will give you the whole target article + commentary + response pdf: www.cambridge.org/core/journal...

Linguists should learn to love speech-based deep learning models www.cambridge.org/core/journal... "Once the bottleneck of text can be replaced...modelling more human-like linguistic processes..[& handle] the vast majority of local & regional language varieties that are rarely or never written down"