对话式图像编辑的下一步操作推荐研究 What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems

精读摘要

对话式助手越来越多地推荐后续编辑来帮用户延续任务，但现有系统主要面向纯文本交互，图像创作场景被忽视。研究团队从 Qwen App 收集了 10 万条真实多轮图像创作对话，发现 80.1% 依赖图像内容，说明多模态推荐是刚需。图像场景的后续编辑建议需要同时满足三个条件：符合用户偏好、方向多样、且能在当前图像上真正执行。 Conversational assistants increasingly recommend follow-up edits, but existing systems target text-only interactions, leaving image creation underexplored. The authors collected 100,000 real multi-turn image-creation conversations from the Qwen App and found 80.1 percent are image-dependent. Useful image edit suggestions must reflect user preferences, offer diverse directions, and remain executable on the current image.