Sébastien Lachapelle (@seblachap) profile picture

ML Researcher at LawZero. Causality, identifiable representation learning & AI safety. Previously at SAIL Montreal (Samsung), @Mila_Quebec & @UMontrealDIRO

Montréal, CA
Joined March 2016
Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)Photo by Sébastien Lachapelle (@seblachap)
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 arxiv.org/abs/2307.02598
4
27
2
106
12,967
Today is my last day as a member of Samsung AI Lab, Montreal (SAIL). A huge "thank you" to this amazing team who taught me so much during the past three years. SAIL is a truly unique environment to do research. I wish all the best to the lab and its members!
1
19
1,137
ICML 2026 in Seoul was great, feeling very grateful I'm getting paid to learn.
31
2,878
Happening now!
Presenting our work at ICML this week! Come and say hi! On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning Poster: Wed, Jul 8, 10:30 AM KST, HALL A # 508
308
Presenting our work at ICML this week! Come and say hi! On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning Poster: Wed, Jul 8, 10:30 AM KST, HALL A # 508
Action labels for BC are not cheap. Semi-supervised methods use Inverse Dynamics Models (IDMs) to fix this, but why does IDM learning actually outperform BC in this context? Our #ICML2026 paper answers this! 🇰🇷 📜 Paper: arxiv.org/abs/2602.02762 🧵
4
1
10
1,409
Just arrived in Seoul! If you're at ICML and want to have a chat, let me know!
12
1,089
I had a lot of fun meeting all the smart people at this workshop and presenting my work "On the Identifiability of Latent Action Policies" as an oral! A huge thanks to the organizers! Paper: arxiv.org/abs/2510.01337
What an awesome first day! Thank you all for joining and listening to our amazing speakers: @SchmidhuberAI, @sherryyangML, @cosmo_shirley, @Yoshua_Bengio, @ylecun, @mido_assran World Models have beautiful days ahead. This is just the beginning 🫡
1
4
26
2,489
Congratulations to my colleague at Samsung @jm_alexia for winning the ARC Prize 2025 Paper Award! 1st place! Well deserved! This is a BIG deal :)
Replying to @arcprize
ARC Prize 2025 Paper Award Winners 1st / "Less is More: Recursive Reasoning with Tiny Networks" (TRM) / A. Jolicoeur-Martineau / $50k 2nd / "Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI" (SOAR) / J. Pourcel et al. / $20k 3rd / "ARC-AGI Without Pretraining" / I. Liao et al. / $5k
1
7
940
Sébastien Lachapelle retweeted
ARC Prize 2025 Paper Award Winners 1st / "Less is More: Recursive Reasoning with Tiny Networks" (TRM) / A. Jolicoeur-Martineau / $50k 2nd / "Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI" (SOAR) / J. Pourcel et al. / $20k 3rd / "ARC-AGI Without Pretraining" / I. Liao et al. / $5k
4
29
8
276
133,805
🚨I have received the "Best Thesis Award 2025" from the Université de Montréal in the "Natural Sciences and Engineering" category! 🚨 Thesis: umontreal.scholaris.ca/items… Thesis defense: youtube.com/watch?v=Wza3sfDt… Explainer for a wide audience (in French): youtube.com/watch?v=KD3cHdkg…
My thesis is now online! umontreal.scholaris.ca/items… This is more than just a list of publications. I invested a lot of time and passion writing this thesis in hope that it will make for an interesting read. Here's a summary of what you'll find in it.
5
4
1
24
3,672
Sébastien Lachapelle retweeted
Finally published: “Top-down and bottom-up neuroscience: overcoming the clash of research cultures” nature.com/articles/s41... Looking for ways to better understand different neuroscientific perspectives and enable productive collaborations
5
47
4
183
17,189
If you're at ICML on Saturday, check out our workshop paper on identifiable steering from multi-concept shifts in language models!
I will be at the Actionable Interpretability Workshop (@ActInterp, #ICML) presenting *SSAEs* in the East Ballroom A from 1-2pm. Drop by (or send a DM) to chat about (actionable) interpretability, (actionable) identifiability, and everything in between!
9
428
My thesis is now online! umontreal.scholaris.ca/items… This is more than just a list of publications. I invested a lot of time and passion writing this thesis in hope that it will make for an interesting read. Here's a summary of what you'll find in it.
7
18
1
115
9,825