Log inSign up
Mariya Toneva
482 posts
@mtoneva1

Mariya Toneva

@mtoneva1
Faculty at @mpi_sws_ working at the intersection of ML, NLP, and cognitive neuroscience. Yogurt snob.
Saarbrücken, Germany
mtoneva.com
Joined January 2019
585
Following
3,080
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @mtoneva1
    Mariya Toneva
    @mtoneva1
    Sep 4, 2025
    So excited and honored to receive an ERC Starting Grant for the project BrainAlign!! BrainAlign will bring LLMs closer to human understanding by directly aligning them with the human brain. Stay tuned for our findings, and multiple postdoc and PhD openings in the coming years!
    Image
    40
  • @mtoneva1
    Mariya Toneva
    @mtoneva1
    Jul 23
    Really eye-opening to survey NeuroAI work across both vision and language--many questions have been answered in one field but remain open in the other! See 🦋 for a fun fact about the origin story..
    @DotaDong
    Dota Tianai Dong
    @DotaDong
    Jul 21
    1/5 Over a decade of comparing deep neural networks to the human brain—but what have we actually learned? Our new @TrendsCognSci Feature Review synthesizes a decade of brain–DNN comparisons, asking what they reveal about brain function across vision and language.
    Image
  • @mtoneva1
    Mariya Toneva
    @mtoneva1
    Jun 22
    It was a lot of fun to write this piece! Makes me so excited for the symposium about The Modern Neuroscience Lab in the Age of AI at FENS in a little more than 2 weeks 🧠🤖
    @_TheTransmitter
    The Transmitter
    @_TheTransmitter
    Jun 22
    These models were not built to explain the brain. But treating them as model organisms that we can perturb and evolve will move us closer to truly understanding the brain’s mechanics, writes @mtoneva1. thetransmitter.org/artificial-int…
    1
  • @mtoneva1
    Mariya Toneva
    @mtoneva1
    Oct 29, 2025
    Very nice work from Michela! It was very interesting to see how different the set of important stimulus words are for brain alignment vs next word prediction.
    @MProietti_
    Michela Proietti
    @MProietti_
    Oct 28, 2025
    We are excited to share our preprint presenting the first input attribution approach to investigate brain-LLM alignment: “Fine-Grained Analysis of Brain–LLM Alignment through Input Attribution”  🧠📚 with @webrot and @mtoneva1. 📄 Read the full paper: arxiv.org/abs/2510.12355 🧵
  • @mtoneva1
    Mariya Toneva
    @mtoneva1
    Aug 19, 2025
    Very proud of Omer for his line of work on brain-tuning speech models. Stay tuned for more exciting work!
    @ohmoussa2
    Omer Moussa
    @ohmoussa2
    Aug 19, 2025
    If you are attending @ISCAInterspeech, I will be giving a talk today on this work, where we show that brain-tuning speech models leads to brain-like processing stages. Looking forward to the discussion and questions! 🗓️ Aug 19, 16:00. 📍Port 1A (Area 01) #Interspeech2025
    1
Advertisement
Advertisement