UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
- 类型：arxiv
- 标识：2609.12397
- 链接：https://arxiv.org/abs/2609.12397
- 主分类：multimodal
- 形态：method
- TLDR：Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their evaluation remains largely lagging. Existing methods, whether embedding-based or Multi-modal Large Language Model (MLLM)-based, evaluate alignment with each modal condition in isolation, which contradicts the simultaneous condition alignment objective of multi-modal image generation, leading to poor consistency with human judgments. To address this challenge, we propose UFO, the first unified framework for omni-condit
- 副分类：evaluation
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-18-agent-rag-longcontext-candidates.json