Nathan Cornille

Learning to Plan for Language Modeling from Unlabeled Data

Causal Factor Disentanglement for Few-Shot Domain Adaptation in Video Prediction

Causal Mechanism Disentanglement to improve Few-Shot Domain Adaptation after Sparse Mechanism Shift for Next Frame Prediction

Critical Analysis of Deconfounded Pretraining to Improve Visio-Linguistic Models

Improving representation learning with Pervasive Internal Regression (PIR)

DIRT: Distributed Internal Regression Transformer