AI 聊天终于开始记得你发过的图了
现在的多模态 AI 聊天，你发一张图让它改，它改完就忘；下一轮你再说「把刚才那张也调一下」，它往往接不上。这篇论文造了第一个大规模「有记忆」的多模态对话数据集：40 万轮对话、260 万轮次，专门逼模型跨轮次记住、更新、落实你不断变化的意图——比如先让你看两张图，再让你把其中一张的风格套到另一张上，它得记得哪张是哪张、你改到哪一步了。拿它训练过的模型，图像编辑能力涨了 10.3%，多轮状态交互涨了 13.23%。但评测也戳破现状：现有最强模型在这类「跨轮次有状态」的对话上依然吃力。它不是你明天就能用上的功能，但它是 AI 从「单轮工具」走向「连续协作伙伴」必须补的那块短板。
📄 原文摘要(英文)
Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be solved independently without tracking information across turns. Consequently, they provide limited supervision and evaluation for multimodal stateful interaction, which requires models to understand, maintain, update, and faithfully realize evolving dialogue states across turns. To address this gap, we introduce YANAMI, the first large-scale multimodal dialogue dataset and benchmark for stateful interaction, comprising YANAMI-400K and YANAMI-Bench. YANAMI-400K contains 400K multi-turn multimodal dialogues, with more than 2M images and 2.6M dialogue turns. The dialogues span four representative scenarios: Multi-Image Fusion, Image Editing, World Modeling, and Visual Reasoning, and require models to continuously track, preserve, and revise evolving multimodal dialogue states across turns. YANAMI-Bench comprises 400 multi-turn dialogues for systematically evaluating multimodal stateful interaction. It jointly evaluates Dialogue State Understanding and Visual Realization, characterizing the gap between models' ability to understand evolving dialogue states and their ability to faithfully realize them in visual outputs. Experiments show that fine-tuning BAGEL on YANAMI-400K improves image editing, generation, and multimodal stateful interaction by 10.3%, 2.0%, and 13.23%, respectively, while preserving its general visual understanding capabilities. Evaluations on YANAMI-Bench further reveal that existing UMMs still struggle to maintain, update, and visually realize evolving multimodal dialogue states.