most citedGSQA: An End-to-End Model for Generative Spoken Question Answering

5 citations · 5 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt

Shangxun Li, Youngjung Uh

Text-to-image diffusion models excel at generating high-quality images from natural language descriptions but often fail to preserve subject consistency across multiple outputs, li…