Adriana Romero-Soriano

6

Papers

49

Total Citations

Papers (6)

Improved baselines for vision-language pre-training

Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance

Boosting Latent Diffusion with Perceptual Objectives

Controlling Multimodal LLMs via Reward-guided Decoding

DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions