labegne retweeted
This one will feel different than my usual posts. Here I will not describe some fancy new ML model but instead I will describe both the research program and engineering systems we put in place at @livingmodels to make sure we can consistently deliver frontier models in biology=>
labegne retweeted
Ok kind of hard to squeeze in between Navier-Stokes BSD and Hodge ... but I'll try anyway ; )
We are super proud to release what we think is the strongest FM on plant genomics so far BOTANIC-1 🌱
labegne retweeted
📢 Publication at BlackboxNLP Workshop @BlackboxNLP in @emnlpmeeting
"Probing Language Models on Their Knowledge Source"
by @Zineddine___t, Andrea Mogini, Jiali Mei, @bpiwowar, Patrick Gallinari
📍Miami
📆 15th Nov. 2024
➡️ arxiv.org/abs/2410.05817
labegne retweeted
Happy to share that our work has been accepted to ECCV 2022!
"STEEX: Steering Counterfactual Explanations with Semantics"🚙🔎
w/ P. Jacob, H. Ben-Younes (@LaBegne), @Mickael_Chen, P. Pérez, and M. Cord (@quobbe).
paper: arxiv.org/abs/2111.09094
code: github.com/valeoai/steex
labegne retweeted
New preprint online!
🔎🚙"Explainability of vision-based autonomous driving systems: Review and challenges"🚙🔎
arxiv.org/abs/2101.05307
We also wrote a (very) condensed version as a blog post:
valeoai.github.io/blog/2021/…
w/ H. Ben-Younes (@LaBegne), P. Pérez and M. Cord (@quobbe)
labegne retweeted
Heuritech is proud to announce the launch of the Lab - an Artificial Intelligence dedicated to Ecology. We are convinced that Machine Learning can be used to shape a more sustainable world, and that Heuritech can contribute to it. Read more!
heuritech.com/blog/articles/…
labegne retweeted
Our biases reduction method (RUBi) has been accepted at @NeurIPSConf !
Thanks to my great co-authors @cdancette @LaBegne @quobbe @deviparikh
RUBi: Reducing Unimodal Biases in Visual Question Answering
Paper: arxiv.org/abs/1906.10169
Code: github.com/cdancette/rubi.bo…
labegne retweeted
1/5 THE LONG WAIT IS OVER! I'm happy to announce the release of rayshader with 3D ggplots. Pull up your favorite ggplot viz and throw it into the new plot_gg() function, and watch rayshader transform it into 3D. #rstats #rayshader #dataviz
Blog post:
tylermw.com/3d-ggplots-with-…
labegne retweeted
On my way to #ICML2019! ✈️
Happy to present our accepted paper
"Context-Aware Zero-Shot Learning for Object Recognition"
Poster and oral presentation are ready 👌
Arxiv: arxiv.org/abs/1904.12638
labegne retweeted
Hedi Ben-younes (@LaBegne) is presently defending his PhD!
"Multimodal representation learning: towards visual reasonning"
Voici un bref résumé de mon intervention d'hier au Deep Learning Meetup, organisé par @heuritechdata et @Microsoft, à la Station F.
Soyez charitables. C'est difficile de résumer 30 minutes en qq tweets ^^
La version longue est ici : arxiv.org/abs/1809.01036
labegne retweeted
I just published “What’s easy/hard in AI & Computer Vision these days?” medium.com/p/whats-easy-hard…
labegne retweeted
I posted an popularization/introduction to #ETHEREUM scalability solutions on Medium: discover what is next on the #ETHEREUM roadmap !
medium.com/ibbc-io/overview-…
labegne retweeted
I just published my first medium post about the #PAISS2018 #DeepLearning #summerschool organized by @inria_grenoble and @naverlabseurope.
medium.com/@alexandreram/pra… …
I would be pleased to have feedbacks! feel free to share
labegne retweeted
Petit cours de démystification de l’#IA par @heuritechdata, spécialisée dans l’Intelligence Artificielle dans le domaine de la mode #Startup #StartupSpotlight
labegne retweeted
DL meetup Paris meetup.com/fr-FR/Deep-Learni… with @ogrisel @arthurmensch and Diogo Luvizon on Wed 7 March at @heuritechdata. Generalization in DL, Structured Prediction and Attention, 2D/3D pose estimation/action recogntion
labegne retweeted
Join us for our #deeplearning #meetup next Wednesday, the 7th of March, in our office in Paris with @ogrisel, @arthurmensch and Diogo Luvizon! meetup.com/fr-FR/Deep-Learni… via @MeetupFR






















