2 papers
stat.ML2022
Diffusion bridges vector quantized Variational AutoEncoders
Max Cohen, Guillaume Quispe, Sylvain Le Corff +2
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 em…
cs.AI2021
Learning Natural Language Generation from Scratch
Alice Martin Donati, Guillaume Quispe, Charles Ollion +3
This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement le…