Cédric Rommel 🦋 @ICLR 🇧🇷

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

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

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.

[David Sussillo @SussilloDavid]

Human-Computer Input via a Wrist-Based sEMG Wearable
https://t.co/XNNsLzfyTN

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

@andrewgwils @micahgoldblum In the same vein, I also feel that great ideas are often simple in some sense, and can easily be misjudged as being simplistic. Also scientists (and reviewers) are skeptical “by design” :)

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

@PessoaBrain Not so much out of context honestly, and probably annoyed most of the neuro part of the public 😅

I think this slide came up when justifying the “scale is all you need” hypothesis. But he did insist on the assumption of the first line

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

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]

Our first contributed talk is from Cédric Rommel on "ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation".

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

@TacoCohen @johannbrehmer @pimdehaan Very well deserved ! And the presentation was also super clear !

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

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 @VLetzelter]

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.

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

Our team at @RealityLabs is also open-sourcing two EMG datasets at #NeurIPS2024 :

emg2pose and emg2qwerty

Check it out if you want to try predicting hand poses and typed text from a new challenging data modality!

[Jesse Marshall @jessedmarshall]

emg2pose: Hand pose estimation anywhere with neuromotor interfaces

A Dataset and Benchmark @ Neurips 2024 https://t.co/6i9xwinnCu

See blog: https://t.co/tvLqddClM3

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

@neur_reps ✨Joint work with the amazing @VLetzelter , @nemka_ , @RenaudMarlet, @quobbe , @ptrkprz and Eduardo Valle✨

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

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.

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

If you’re at #Neurips2024 next week, come meet us in poster session 3 on Thu 12 Dec 11 a.m.!

Or at our oral presentation during the @neur_reps workshop on Saturday 14th!

Paper: https://t.co/VZupvBGS4w
Github: https://t.co/xCD6iJ0LB5

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

Oh boy, something definitely happened in 2022 ! 😅

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

If you are at #ICML2024 , come chat with @VLetzelter , David and I about conditional density estimation and ill-posed ML tasks this afternoon !

Poster session 4 - 1:30pm - poster # 1506

[Victor Letzelter @VLetzelter]

Interested in ill-posed learning tasks, uncertainty prediction, conditional density estimation or multi-head deep neural networks ?

In our new paper, accepted at #ICML24, we tackle these challenges by exploring the Winner-Takes-All (WTA) training scheme.
[1/n]

[Cédric Rommel 🦋 @ICLR 🇧🇷 @ccrommel]

I’ll be attending #ICML2024 next week to present this excellent work led by @VLetzelter ! Looking forward to chat about ill-posed machine learning tasks, data augmentation, pose estimation, eeg decoding or anything else ML at the poster session or around some coffee !

[Victor Letzelter @VLetzelter]

Interested in ill-posed learning tasks, uncertainty prediction, conditional density estimation or multi-head deep neural networks ?

In our new paper, accepted at #ICML24, we tackle these challenges by exploring the Winner-Takes-All (WTA) training scheme.
[1/n]