Portrait de Amin Mansouri

Amin Mansouri

Collaborateur·rice alumni - UdeM
Superviseur⋅e principal⋅e
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Causalité
Raisonnement
Traitement du langage naturel

Publications

Object-Centric Architectures Enable Efficient Causal Representation Learning
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees… (voir plus) (up to some reasonable equivalence class). Common to all of these approaches is the assumption that (1) the latent variables are represented as
Reusable Slotwise Mechanisms
Trang Nguyen
Khuong Nguyen
Nguyen Duy Khuong
Dianbo Liu
Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generali… (voir plus)zation in novel scenarios. However, achieving this capability necessitates not only an effective scene representation but also an understanding of the mechanisms governing interactions among object subsets. Recent studies have made significant progress in representing scenes using object slots. In this work, we introduce Reusable Slotwise Mechanisms, or RSM, a framework that models object dynamics by leveraging communication among slots along with a modular architecture capable of dynamically selecting reusable mechanisms for predicting the future states of each object slot. Crucially, RSM leverages the Central Contextual Information (CCI), enabling selected mechanisms to access the remaining slots through a bottleneck, effectively allowing for modeling of higher order and complex interactions that might require a sparse subset of objects. Experimental results demonstrate the superior performance of RSM compared to state-of-the-art methods across various future prediction and related downstream tasks, including Visual Question Answering and action planning. Furthermore, we showcase RSM's Out-of-Distribution generalization ability to handle scenes in intricate scenarios.
Object-centric causal representation learning
Extended Abstract Track
Jason Hartford
Christian Shewmake
Simone Azeglio
Arianna Di Bernardo
Nina Miolane