Cédric Rommel 🦋

@ccrommel

Research Scientist at @Meta | AI and neural interfaces | Interested in data augmentation, generative models, geometric DL, brain decoding, human pose, …

Paris, France

cedricrommel.github.io

Joined October 2015

895 Following

461 Followers

Replies Reposts Media

Pinned
Cédric Rommel 🦋
@ccrommel
Dec 4, 2024
Inferring 3D human poses from video is highly ill-posed because of depth ambiguity. Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.
GIF
2
Cédric Rommel 🦋
@ccrommel
Sep 21
Think your decoding model can read hand-poses from an EMG wristband? Come show us your 💪 and break our baselines on a real-world industry problem!
Alexandre Gramfort
@agramfort
Sep 21
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.io As my team says 👋🤙✌️🤌🖐️!
00:00
Cédric Rommel 🦋
@ccrommel
Jun 30
Decoding typing from brain activity — no surgery needed. Brain2QwertyV2, led by @JarodLevy and @LucyZ47712090, narrows the gap with invasive BCIs using LLMs on MEG and paves the way toward real-time language decoding! Proud to have collaborated with this talented team!
Jarod Levy
@JarodLevy
Jun 29
🧠⌨️ Decode language from brain activity without surgery. 🧠⌨️ Brain2Qwerty V1 is officially published in Nature Neuroscience. Today, we're releasing Brain2Qwerty V2. We achieve unprecedented performance for a non-invasive MEG setup. Details below 🧵👇
GIF
1
Cédric Rommel 🦋
@ccrommel
Dec 15, 2024
Thanks for the nice workshop ! It was great to be able to share our work, listen to great talks and have many interesting conversations !
Symmetry and Geometry in Neural Representations
@neur_reps
Dec 14, 2024
Our first contributed talk is from Cédric Rommel on "ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation".
Cédric Rommel 🦋
@ccrommel
Dec 6, 2024
Yet another great work on multi-hypothesis learning by @VLetzelter accepted to #NeurIPS2024 ! In this paper they show that simulated annealing can help to make the winner-takes-all loss more stable and robust, demonstrating its useful in many ill-posed real-world applications!
Victor Letzelter @ ICML 2026
@VLetzelter
Nov 25, 2024
Working on ill-posed machine learning tasks, interested in multi-heads neural networks and data #uncertainty quantification ? Sharing here our latest research, which will be presented at @NeurIPSConf in December.
GIF