一作ACL 2026Findings· Findings of ACL
VIDA : A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification
Yanshan Liu · Hongbo Zhang · Zhen Sun · Jiaheng Wei · Kaishun Wu
摘要
In complex domains like interior design, user requests are often ambiguous and multimodal. Professional designers address this by asking strategic clarification questions based on hierarchical priorities, a capability lacking in current Vision-Language Models (VLMs). When fine-tuned on dialogue d...