Thibault Castells — accepted AI-conference papers

2024

"BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion"

Bo-Kyeong Kim*, Hyoung-Kyu Song, Thibault Castells, Shinkook Choi

ECCV 2024poster

"Text-to-image (T2I) generation with Stable Diffusion models (SDMs) involves high computing demands due to billion-scale parameters. To enhance efficiency, recent studies have reduced sampling steps and applied network quantization while retaining the original architectures. The lack of architectura…

Cited by 32 Source ↗PDF ↗code ↗Scholar ↗

2020

SuperLoss: A Generic Loss for Robust Curriculum Learning

Thibault Castells, Philippe Weinzaepfel, Jerome Revaud

NeurIPS 2020poster

Curriculum learning is a technique to improve a model performance and generalization based on the idea that easy samples should be presented before difficult ones during training. While it is generally complex to estimate a priori the difficulty of a given sample, recent works have shown that curric…

Cited by 107 Source ↗PDF ↗code ↗Scholar ↗