Xavier Suau Cuadros — accepted AI-conference papers

2022

Self-conditioning Pre-Trained Language Models

Xavier Suau Cuadros, Luca Zappella, Nicholas Apostoloff

ICML 2022spotlight

In this paper we aim to investigate the mechanisms that guide text generation with pre-trained Transformer-based Language Models (TLMs). Grounded on the Product of Experts formulation by Hinton (1999), we describe a generative mechanism that exploits expert units which naturally exist in TLMs. Such…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2017

Collaborative voting of 3D features for robust gesture estimation

Daniel van Sabben, Javier Ruiz Hidalgo, Xavier Suau Cuadros, Josep R. Casas

ICASSP 2017accepted

Human body analysis raises special interest because it enables a wide range of interactive applications. In this paper we present a gesture estimator that discriminates body poses in depth images. A novel collaborative method is proposed to learn 3D features of the human body and, later, to estimate…

Cited by 0 Source ↗Scholar ↗