Papers with coarse-to-fine attention process

1 papers
DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models may deviate from this pattern due to attention drift and underutilization of visual evidence.
Approach: They propose a Dual-Indicator Guided Contrastive Alignment (DICA) that tracks visual attention and output image correlations to improve visual grounding.
Outcome: The proposed model outperforms existing approaches and significantly reduces hallucinations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations