← Search

Andres Felipe Cruz-Salinas

2 accepted papers

2025

u-$\mu$P: The Unit-Scaled Maximal Update Parametrization

ICLR 2025spotlight

The Maximal Update Parametrization ($\mu$P) aims to make the optimal hyperparameters (HPs) of a model independent of its size, allowing them to be swept using a cheap proxy model rather than the full-size target model. We present a new scheme, u-$\mu$P, which improves upon $\mu$P by combining it wit…

Cited by 7SourcePDFScholar
2023

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

NeurIPS 2023poster

The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nua…

Cited by 23SourcePDFScholar