← Search

Chenhan Fu

2 accepted papers

2025

ITERATE: Image-Text Enhancement, Retrieval, and Alignment for Transmodal Evolution with LLMs

COLING 2025main

Inspired by human cognitive behavior, we introduce visual modality to enhance the performance of pure text-based question-answering tasks with the development of multimodal models. However, obtaining corresponding images through manual annotation often entails high costs. Faced with this challenge,…

Cited by 0SourcePDFScholar