7 papers
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…
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…
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…
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…
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…
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…