Sébastien Lachapelle
@seblachap
Followers
709
Following
271
Statuses
96
Research Scientist at SAIL Montreal (Samsung) interested in causality and identifiable representation learning. PhD from @Mila_Quebec, @UMontrealDIRO
Montréal, CA
Joined March 2016
1/ Excited for our oral presentation at #NeurIPS2023 on "Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation"! A theoretical paper about object-centric representation learning (OCRL), disentanglement & extrapolation
4
28
107
This was a really fun collaboration :) Working on this project allowed me to gain a better understanding of the linear representation hypothesis in LLM by formalizing it using ideas from identifiable/causal representation learning. Check it out!
Yo! We have an accepted paper at #AISTATS2025!! Time to prepare for Thailand 🪷🏖️🌴🐒 Huge thanks to my coauthors @luigigres, @sweichwald, and @seblachap for all the joint effort! More details soon 👇
0
1
6
@_romain_lopez_ Merci! :) I'm sure we'll bump into each other at a conference very soon. We should definitely find something to work on together!
0
0
0
RT @_romain_lopez_: Honored to be selected as a 2024 #STATWunderkind! Grateful for all my mentors & collaborators from @genentech and @Stan…
0
10
0
0
0
1
New work from the great Alexia et al. from the Samsung Lab in Montreal on molecule generation, check it out!
Any-Property-Conditional Molecule 🧪 Generation with Self-Criticism 👩🏫 using Spanning Trees New work at the SAIT AI Lab on generating molecules with masked Transformers + self-criticism! Blog: Code: arXiv:
0
1
10
If you're at ICLR this week, make sure to check out our work on causal representation learning, which got a spotlight! :)
✨ ICLR2024 Spotlight ✨ Still want to identify causal variables in a partially observed setup? 🦥 We present a unified framework for studying the identifiability of representations learned from simultaneously, partially observed views, such as different data modalities. 🍍
1
3
22
RT @Danrunnnn: 🎉 Excited to share that our paper “A Sparsity Principle for Partially Observable Causal Representation Learning” was accepte…
0
11
0
0
0
1
The field of "causal representation learning" really grew since the first version of this work in 2022. I made considerable efforts to give a coherent review of all the works that's been happening recently, but it's likely that I missed a few. Reach out if that's the case!
0
0
4
RT @JuliaKaltenborn: The ML community has been calling for a large scale climate dataset. In our recent Neurips 2023 publication, we introd…
0
48
0
RT @JKugelgen: Interested in identifiable causal representation learning with flexible nonlinear modules? 👇 A summary of our #NeurIPS pape…
0
20
0