2 papers
cs.CV2026
MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
Benjamin Aubin, Gonzalo Iñaki Quintana, Onur Tasar +4
Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, dedupl…
cs.CV2025
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
Clément Chadebec, Onur Tasar, Sanjeev Sreetharan +1
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image trans…