ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting
Published in IJCNLP-AACL, 2025
This paper explores Visual Instruction Rewriting, a novel approach that transforms multimodal instructions into text-only commands, allowing seamless integration of lightweight on-device instruction rewriter VLMs (250M parameters) with existing conversational AI systems, enhancing vision data privacy.