Guillaume Quispe — accepted AI-conference papers

2022

Diffusion bridges vector quantized variational autoencoders

Max Cohen, Guillaume Quispe, Sylvain Le Corff, Charles Ollion, Eric Moulines

ICML 2022spotlight

Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned embeddings. To generate new samples, an autoregressive prior distribution over the discrete states must be trained separat…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗

2022

Learning Natural Language Generation with Truncated Reinforcement Learning

Alice Martin, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin

NAACL 2022long

This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original approach to train conditional languagemodels without a supervised learning phase, by only using reinforcement learning (RL). As RL methods unsuccessfully scale to large action spaces, we dynamically truncate th…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗