Building the future of neural interfaces from EMG signals at Meta Reality Labs. Ex Research director at Inria, scikit-learn co-founder, mne-python creator.
Paris, France
Joined July 2007
- Tweets1.8K
- Following1.1K
- Followers6.9K
- Likes2.9K
No cameras. No gloves. Reconstructing hand pose from surface EMG at the wrist with a @Meta Neural Band.
It's track 4 in our NeurIPS 2026 Neural Interfaces competition. Real wearable data and real $$$ for the winners!
👉 neural-interfaces26.github.i…
As my team says 👋🤙✌️🤌🖐️!
Alexandre Gramfort retweeted
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms.
Collab led by Ambroise Heurtebise, with @PierreAblin, @agramfort, and Aapo Hyvarinen.
Oral presentation on Dec 7 at the Workshop on Causality for Impact.
Paper link: machinelearning.apple.com/re…
Have you ever typed import mne in #Python?
Did it help you publish a paper, save hours, or even land your dream job? 💡
Now’s your chance to give back — @mne_news can finally receive 💸 donations to keep the lights on (CIs, forum, etc.) 🙌 github.com/sponsors/mne-tool…
Alexandre Gramfort retweeted
Excited that NeurIPS this year has a workshop on foundational models for neural signals that includes EMG in addition to the usual other neural signals, thanks to @agramfort!
Great science and friends moments this year at @NeurIPSConf see you next year 👋
I will be at @NeurIPSConf 2024 in Vancouver next week. Ping me if you want to grab ☕️ or🍺 and chat about ML stuff for biosignals (EMG, EEG, MEG, …)
Alexandre Gramfort retweeted
1/
We just open-sourced two large wrist electromyography (EMG) datasets - one towards typing without a keyboard and the other for predicting hand poses - with baselines.
We believe these will help advance research into making high bandwidth non-invasive neuromotor interfaces a reality!
Alexandre Gramfort retweeted
⚠️ Launch Alert 🚀 Today, we're launching the first official and global @scikit_learn practitioner certification program, level 1️⃣ Thank you @Inria and @Artefact_Global for being our launch partners! Be the among the first to get certified 👉 certification.probabl.ai/
I see reports saying that GPT 4o or OpenAI o1 can implement papers by reading the method section. Maybe we can use LLMs as (self-)reviewer 2. If your paper cannot be reimplemented from the pdf then it means your writing is not clear enough ? 😂
🚀 I'm thrilled to share that I've joined a community of proud investors in @probabl_ai, a mission-driven company that is the official brand operator of @scikit_learn, the leading #MachineLearning #OpenSource framework and its 1.5 billion downloads! papers.probabl.ai/announcing…
Thanks @biomag2024 for having me giving this keynote talk showcasing our work at Meta Reality Labs on the future of neuromotor interfaces using surface electromyography (sEMG) signals 🙌
Day 3 of #biomag2024 kicks off with a captivating keynote from Alex Gramfort @agramfort on "Training machines to decode electromyography signals for high bandwidth human-computer interfaces that work across people"
For more details on this work you can read this preprint biorxiv.org/content/10.1101/…
Neuroscience needs a career path for software engineers 👍👍👍 thetransmitter.org/craft-and…
Alexandre Gramfort retweeted
🚀 Exciting News! Benchopt 1.6.0 is here with a ton of new features to make ML benchmarking easier than ever! 🎉
🔗 Changelog: benchopt.github.io/whats_new…
🧵👇
Great work @apmellot 🙌
This Post is from an account that no longer exists. Learn more
Alexandre Gramfort retweeted
With benchopt, we are trying to make it easy to interact and extend this huge benchmark!
We are pushing hard to make it easy to integrate new methods even if you don't know MOABB!
If you develop new BCI methods, come and try them on the github.com/benchopt/benchmar…
Alexandre Gramfort retweeted
Really cool paper from @FabianGloeckle, @syhw et al @AIatMeta showing the importance of learning to predict beyond the next word:
arxiv.org/abs/2404.19737
I'm real pleased as we showed last year that this objective better accounts for brain activity: xitter.cf/c_caucheteux/status/16…
Our paper is out in Nature Human Behaviour🔥🔥
‘Evidence of a predictive coding hierarchy in the human brain listening to speech’
📄nature.com/articles/s41562-0…
💡Unlike language models, our brain makes distant & hierarchical predictions
with @agramfort and @JeanRemiKing
Thread👇
Alexandre Gramfort retweeted
Someone asked me recently why the Paris AI ecosystem is so 🔥 these days.
On the surface, it looks like Paris became a major #AI center overnight, but it didn't.
It took time and didn't appear by accident.
Here is a story that started more than 10 years ago.
👇
For those of you who were wondering what I’ve been doing since I joined @Meta Reality Labs late 2022. Here is the first detailed scientific communication about our work.
You can read the paper at: biorxiv.org/content/10.1101/…
