Hugo Richard

[Ana Luísa Pinho 🦋 @ALuisaPinho]

The #IBC 3rd-release data-paper is out! We validate naturalistic tasks using #FastSRM, an unsupervised model where a shared response and individual maps are learnt jointly from fMRI time series. Check it out! https://t.co/Qaj6ota2hs @BertrandThirion @hr1ch3rd @NeuroSpin_91

[Masha Vladimirova @iamvladimirova]

Since I joined @CriteoAILab, I started digging into applied causality topics. Our recent work “Maximizing the Success Probability of Policy Allocations in Online Systems” got accepted to AAAI-24 🥳!
https://t.co/XFjziS9bEI
Ping @artembetley @RahierThibaud
🧵🧵🧵

[Jean-Yves Franceschi @jy_franceschi]

Looking forward to present at #NeurIPS2023, NOLA & Paris, a unification framework for diffusion models and GANs.

It opens up the possibility to train generators with diffusion and GANs without generators!

📜 https://t.co/TRTjgFRFnW
🖥️ https://t.co/HOLfG2nTz2

[Ana Luísa Pinho 🦋 @ALuisaPinho]

The preprint on the #IBC-dataset 3rd-release is out! We showcase the application of #FastSRM to extract, from naturalistic stimuli, functional networks of the visual, auditory and language systems. Check it out! https://t.co/SKcqbhFGuN @BertrandThirion

[ApertureNeuro @ApertureOHBM]

New paper by @hr1ch3rd and @BertrandThirion offers a fast, memory efficient, and identifiable application of the shared response model https://t.co/ijd7Qxd2Ol

[Hugo Richard @hr1ch3rd]

@CriteoAILab

[Hugo Richard @hr1ch3rd]

Notably, we demonstrate, both theoretically
and through simulations, how preemptive algo-
rithms can greatly outperform non-preemptive
ones when the durations of different job types
are far from one another, a phenomenon that does
not occur when the type durations are known. 6/6

[Hugo Richard @hr1ch3rd]

In both cases, we design algorithms that achieve sublinear excess cost, compared to the performance with known types, and prove lower bounds for the non-preemptive case. 5/6

[Hugo Richard @hr1ch3rd]

We then move to two learning scenarios where
the types are unknown: non-preemptive problems,
where each started job must be completed before
moving to another job; and preemptive problems,
where job execution can be paused in the favor of
moving to a different job. 4/6

[Hugo Richard @hr1ch3rd]

We study single-machine scheduling of jobs, each
belonging to a job type that determines its dura-
tion distribution. We start by analyzing the scenario where the type characteristics are known. 3/6

[Hugo Richard @hr1ch3rd]

Joint work with Nadav Merlis*, Flore Sentenac*, Corentin Odic, Mathieu Molina and Vianney Perchet.
Paper: https://t.co/EjH7TO2f8J
Code: https://t.co/NDmSOyWZPI
*equal contribution

Come see our poster today between 2PM and 3:30PM at Exhibit Hall 1 ! 2/6

[Hugo Richard @hr1ch3rd]

[ICML 2023, Exhibit Hall 1, Today at 2 PM] On a scheduling problem, we learn hints about job sizes as more jobs are scheduled. We use hints to make better scheduling decision via a combination of bandits methods and worse case scheduling algorithm. 1/6

[Zaccharie Ramzi @ZaccharieRamzi]

📢📢 New preprint: https://t.co/GIjdbnFMmv

"Test like you Train in Implicit Deep Learning"

w. @PierreAblin @tomamoral @gabrielpeyre

We investigate whether implicit deep learning models benefit from more test-time inner iterations.

[Chris Chambers @chrisdc77]

Following Elsevier's decision to raise the APC for NeuroImage to $3,450, all editors (inc. EiCs @fmrib_steve @tobergmann @BirteUta) from NeuroImage and NeuroImage:Reports have resigned, effective immediately. I am joining this action and have also resigned https://t.co/0aamG7bemJ

[Antonia Machlouzarides-Shalit @Antonia_Machlou]

C'est un honneur de recevoir le #SophIA Award 2022, et d'être intégrée et soutenue par @InriaStartup, @IncubatPacaEst, et @3IAcotedazur. Merci à Marco Lorenzi d'avoir collaboré avec nous, et nous avons hâte de poursuivre notre plan d'action cette année!

[Alexis Thual @alexisthual]

Our paper on using Optimal Transport to compare human cortical surfaces was accepted at #NeurIPS22 🥳
We implement a new OT solver (FUGW) to compare human brains although their anatomy and functional activity patterns differ a lot.
https://t.co/MvB7Xevoel
https://t.co/djYFTIonmX

[Raphael Meudec @raphaelmeudec]

Thrilled to give an oral tomorrow at 10:30 at #OHBM22!

We successfully decode 50 cognitive processes from fMRI maps by exploiting the large amount of data in @Neurovault and leveraging the @CognitiveAtlas ontology

See you in M1 for the Modeling and Analysis Activation session!

[Alexis Thual @alexisthual]

Thrilled to give a demo brain-cockpit 🧠🚀, a web-based viewer @StanDehaene, @BertrandThirion and I have been working on to explore deep phenotyping fMRI data and individual alignments!
See you @OHBM friends in M1 at 13:00 ☺️

[Norman Lab @ptoncompmemlab]

Now out in @ApertureOHBM! Our comprehensive overview, led by @manojneuro, of the @UseBrainIAK toolkit for advanced fMRI analysis https://t.co/3tgGANtkCJ