Multimodal Models

Consistency Should Be the Priority for Unified Multimodal Models

A position paper arguing that consistency across views, modalities, and prompts should be the priority research target for unified multimodal models.

Feb 3, 2026

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries

CultureVLM characterizes and improves cultural understanding of vision-language models across more than 100 countries using culturally-grounded benchmarks and training procedures.

Jun 11, 2025