activity
20242026
collaborators

7 papers

cs.LG2026

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning

Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau +1

Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories. S…

stat.ML2026

Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing

Danru Xu, Sébastien Lachapelle, Sara Magliacane

Causal representation learning (CRL) aims to identify the underlying latent variables from high-dimensional observations, even when variables are dependent with each other. We stud…

cs.LG2026

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations

Shruti Joshi, Andrea Dittadi, Sébastien Lachapelle +1

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, c…

cs.LG2025

On the Identifiability of Latent Action Policies

Sébastien Lachapelle

We study the identifiability of latent action policy learning (LAPO), a framework introduced recently to discover representations of actions from video data. We formally describe d…

stat.ML2025

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling

Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald +1

We analyze identifiability as a possible explanation for the ubiquity of linear properties across language models, such as the vector difference between the representations of "eas…

cs.LG2024

Causal Representation Learning in Temporal Data via Single-Parent Decoding

Philippe Brouillard, Sébastien Lachapelle, Julia Kaltenborn +6

Scientific research often seeks to understand the causal structure underlying high-level variables in a system. For example, climate scientists study how phenomena, such as El Niñ…