Linnea Evanson, PhD

Postdoc | Former PhD Student @ École Normale Supérieure | Former Research Scientist Intern @ Meta AI | Studying how AI and our brains learn language!

[Yohann Benchetrit @BenchetritYoha1]

We’re very happy to share our latest paper:
“Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation“ with up to 68% gain in brain-to-image image decoding!
📝https://t.co/IWYNSUCb8s
🧵Details in thread below:

[Joséphine Raugel @JRaugel]

1/ We’re so glad to share this new study 💫
Does the brain learn like a Deep Net? 🧠⚙️
- 📄Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
- 🔗https://t.co/yrb4otBEYk
Thread below 🧵

[Jean-Rémi King @JeanRemiKing]

Announcing: a new interactive tool for a quick and simple start of encoding or encoding:
🧠 fMRI, EEG, MEG, iEEG, spikes… preprocessing
💬 text 🔊 audio ▶️ video 🏞️ image… embeddings

📦 pip install neuralset
🔍https://t.co/rHOZuvU2tk

#NeuroAI #OpenSource

[Hubert Banville @hubertjbanville]

🧠 Introducing NeuralBench: a unified, open-source framework to benchmark NeuroAI models.

v1.0: 36 EEG tasks, 94 datasets, task-specific + foundation models. MEG/fMRI ready.

MIT-licensed, FAIR's Brain & AI @AIatMeta.

Code: https://t.co/WdROYdjjNY
Paper: https://t.co/zD29kxgEMI

[Marktechpost AI @Marktechpost]

Meta FAIR Releases NeuralSet: A Python Package for Neuro-AI That Supports fMRI, M/EEG, Spikes, and HuggingFace Embeddings

Every other tool supports some. NeuralSet supports all.

Key Points:

→ One unified PyTorch DataLoader for fMRI, MEG, EEG, iEEG, fNIRS, EMG, and spike recordings

→ Native HuggingFace integration: DINOv2, CLIP, Wav2Vec, Whisper, GPT-2, LLaMA, VideoMAE — out of the box

→ Stimulus embeddings are always temporally aligned with neural recordings — no manual alignment code

→ Pydantic validation catches config errors at initialization, not hours into a cluster run

→ Same script runs on your laptop and a SLURM cluster — one config flag change

→ Hash-based caching means running a large language model over an entire corpus happens once, then never again

The core design principle is structure–data decoupling.

The entire experiment is represented as lightweight event metadata — a pandas DataFrame. No raw signals are loaded until a PyTorch DataLoader actually needs them. You can filter, explore, and recombine terabyte-scale datasets without touching a single file.

📦 pip install neuralset

↗ Full analysis: https://t.co/1Jd5GHlAhn

↗ Docs: https://t.co/otMeR1Kl7C

↗ Paper: https://t.co/fGbPuQLdvk

@AIatMeta @Meta_Engineers @Meta @JeanRemiKing @JRaugel
@JarodLevy
@EvansonLinnea
@LucyZ47712090
@juliengadonneix
@asantosrevilla
@SHouhamdi98568
@BenchetritYoha1
@stephanedascoli
@DahanSimon
@hubertjbanville
@teonbrooks
@klbegany
@shubhkhanna__
@PierreOrhan
@alexisthual
@honualx
...

[Linnea Evanson, PhD @EvansonLinnea]

@teonbrooks
@klbegany
@shubhkhanna__
@PierreOrhan
@alexisthual
@honualx
C Bel J Bonnaire
@c_caucheteux
T Desbordes P Diego-Simón J Millet S Panchavati A Ratouchniak M Careil & Jérémy Rapin.

[Linnea Evanson, PhD @EvansonLinnea]

Releasing NeuralSet — a Python framework for Neuro-AI research ⚡

Unifies brain recordings (fMRI, EEG, MEG, iEEG) + multimodal features (text, audio, video, images) into model-ready PyTorch batches in a few lines of code 🧠🤖

`pip install neuralset`

Paper + code 👇

[Linnea Evanson, PhD @EvansonLinnea]

Made possible thanks to the team at @AIatMeta, Fondation Adolphe de Rothschild, and Ecole normale supérieure:

@JRaugel
@JarodLevy
@EvansonLinnea
@LucyZ47712090
@juliengadonneix
@asantosrevilla
@SHouhamdi98568
@BenchetritYoha1
@stephanedascoli
@DahanSimon
@hubertjbanville
...

[Stéphane d'Ascoli @stephanedascoli]

Today we’re happy to release the framework which powered TRIBE v2 and many other projects from the team! We hope this can speed up research in Neuro-AI 🧠

[Jarod Levy @JarodLevy]

Excited to announce neuralset! 🚀🚀🚀

The new library that turns raw neuro-recordings into AI-ready tensors in seconds.

📦 `pip install neuralset`
💻 Code: https://t.co/O6l6w6447K
📄 Paper: https://t.co/akUXXImpDH

Details below 🧵👇

[Jean-Rémi King @JeanRemiKing]

💫 Introducing NeuralSet:
a simple, fast, scalable Python package for Neuro-AI

📦 pip install neuralset
📄 https://t.co/OkSTKRlwwy
🔍 https://t.co/rHOZuvU2tk

Supports
🧠 fMRI, EEG, MEG, ECoG, spike… preprocessing
💬 text 🔊 audio ▶️ video 🏞️ image… embeddings

🧵 Details👇

[Linnea Evanson, PhD @EvansonLinnea]

Great opportunity to work with the Rothschild Foundation Hospital on neuro foundation models.

[Jean-Rémi King @JeanRemiKing]

🧠 the Digital Brain Project is now live:

$5M total · up to $500k per selected team

Let's open-source the modeling of the human brain brain activity!

➡️Apply on: https://t.co/W4HFA5PQBX

[Linnea Evanson, PhD @EvansonLinnea]

Exciting new work by @juliengadonneix! Super happy to be part of it.

[Julien Gadonneix @juliengadonneix]

🔥 We're very pleased to release our latest study 🧠: "Temporal structure of the language hierarchy within small cortical patches" 📄 https://t.co/DDnefJNtgY
🧵 Summary thread below: 1/7

[Julien Gadonneix @juliengadonneix]

🔥 We're very pleased to release our latest study 🧠: "Temporal structure of the language hierarchy within small cortical patches" 📄 https://t.co/DDnefJNtgY
🧵 Summary thread below: 1/7

[Stéphane d'Ascoli @stephanedascoli]

🚨 We're very happy to introduce TRIBE v2: a foundation model of the brain's responses to sight, sound & language.

📄 Paper: https://t.co/uHwgOvTrRD
▶️ Demo: https://t.co/9ZX6XcOXSM
💻 Code: https://t.co/PCc2yKyh1D
🤗 Model: https://t.co/GiTKzsHUhY

[Jean-Rémi King @JeanRemiKing]

🧠Happy to share the 2025 highlights of our Brain & AI team @AIatMeta, pushing, one paper at a time, towards a unified model of cognition in the human brain.

🧵The thread ⬇️
#NeuroAI

[Linnea Evanson, PhD @EvansonLinnea]

Project:
Linear language decoding of intracranial (sEEG) brain signal.
Explore the contribution of different frequencies of neural signal on a variety of linguistic representations in the brain… and how those representations change during development (from 2 years to adulthood)

[Linnea Evanson, PhD @EvansonLinnea]

🚨 Hiring: Master’s student intern
📅 Early 2026 | 📍 Rothschild Foundation Hospital, Paris
🧠 Looking for someone with experience in messy neural data (ideally sEEG) + deep learning
👤 Supervised by myself, in the team of @JeanRemiKing
🔗 Apply: https://t.co/uMAnPoTIDj

[Linnea Evanson, PhD @EvansonLinnea]

Come check out our tutorial on scaling language decoding at CCN!

[Jean-Rémi King @JeanRemiKing]

Our Brain and AI team will be at #ccn2025 this week: 3 highlights:

1. 🏆1st place for the Algonauts competition: https://t.co/3dqPudzl0W
2. 🗣️Keynote:https://t.co/m2mmVy2b7V
3. 🚀Tutorial: Scale your decoding pipeline in the notebook: https://t.co/zIM3AR12vG