Vandegar Maxime

Turning images to 3D | Neural Radiance Fields

[Vandegar Maxime @VandegarM]

Happy to announce that our work (and my very first paper) "Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference" got accepted @aistats2021! 

Nice work w/ @Michael_A_Kagan, @WehenkelAntoine & @glouppe.

[Gilles Louppe @glouppe]

Now accepted at #aistats2021! Congratulations to my incoming PhD student @VandegarM for his first paper! Excited to see what's next :) (with @WehenkelAntoine and @Michael_A_Kagan)

[apoorv @_apoorvnandan]

underrated repo, good variety of papers

[Vandegar Maxime @VandegarM]

@_apoorvnandan That explains the overnight stars! 🌟 Thanks for the shoutout and support

[sacha lewin @SachaLewin]

Thrilled to announce my first paper, "Dynamic NeRFs for Soccer Scenes", which was accepted at the MMSports 2023 workshop (@ ACM Multimedia)!

It features a part of my master's thesis work, in which I explore the use of dynamic NeRFs for the task of reconstructing soccer replays.

[Gilles Louppe @glouppe]

We are presenting two posters today at #AISTATS2021! 📢Come and say hi to @WehenkelAntoine and @VandegarM 👋
https://t.co/ASeye4ElsG
https://t.co/kSMbBtLyEK

[Gilles Louppe @glouppe]

📢 My research group has an open position for a PhD candidate in deep-learning for simulation-based inference. Details available at https://t.co/8JGUJyuwi6 PM for further details 🤖🔭

[Antoine Wehenkel @WehenkelAntoine]

And here is the second good news of the day 🥳
Our paper Graphical Normalizing Flows with my advisor @glouppe has been accepted @Aistats2020 !!

[Michael Kagan @Michael_A_Kagan]

Great to work with @VandegarM @WehenkelAntoine @glouppe on this new take on an established method... Empirical Bayes + normalizing flows to learn source distributions from corrupted observations. For HEP, we can unfold in many dimensions and without discretization into histograms

[Gilles Louppe @glouppe]

What if you want to do posterior inference but don't have a prior to start with? In this new work led by @VandegarM, we investigate how the empirical Bayesian can use neural density estimators to estimate a source distribution over uncorrupted samples from noise-corrupted ones.