关注
Thibault Castells
Thibault Castells
Research engineer at Nota.ai
在 nota.ai 的电子邮件经过验证
标题
引用次数
引用次数
年份
Superloss: A generic loss for robust curriculum learning
T Castells, P Weinzaepfel, J Revaud
Advances in Neural Information Processing Systems 33, 4308-4319, 2020
912020
On architectural compression of text-to-image diffusion models
BK Kim, HK Song, T Castells, S Choi
342023
Shortened llama: A simple depth pruning for large language models
BK Kim, G Kim, TH Kim, T Castells, S Choi, J Shin, HK Song
arXiv preprint arXiv:2402.02834, 2024
122024
Bk-sdm: Architecturally compressed stable diffusion for efficient text-to-image generation
BK Kim, HK Song, T Castells, S Choi
Workshop on Efficient Systems for Foundation Models@ ICML2023, 2023
102023
Automatic neural network pruning that efficiently preserves the model accuracy
T Castells, SK Yeom
arXiv preprint arXiv:2111.09635, 2021
62021
LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
T Castells, HK Song, BK Kim, S Choi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
42024
Bk-sdm: A lightweight, fast, and cheap version of stable diffusion
BK Kim, HK Song, T Castells, S Choi
arXiv preprint arXiv:2305.15798, 2023
42023
Superloss: A generic loss for robust curriculum learning
P Weinzaepfel, J Revaud, T Castells
US Patent App. 17/383,860, 2022
42022
EdgeFusion: On-Device Text-to-Image Generation
T Castells, HK Song, T Piao, S Choi, BK Kim, H Yim, C Lee, JG Kim, ...
arXiv preprint arXiv:2404.11925, 2024
12024
Method and apparatus for information flow based automatic neural network compression that preserves the model accuracy
Y Seul-Ki, T Castells
US Patent App. 18/056,644, 2023
2023
Supplementary Material for SuperLoss: A Generic Loss for Robust Curriculum Learning
T Castells, P Weinzaepfel, J Revaud
系统目前无法执行此操作,请稍后再试。
文章 1–11