AI RESEARCH
MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation
arXiv CS.CV
•
ArXi:2603.21937v1 Announce Type: new Subject-driven image generation is increasingly expected to fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provide several subject images, a background reference, and long, entity-indexed prompts to control multiple people within one scene. In this setting, a key failure mode is cross-subject attribute misbinding: attributes are preserved, edited, or transferred to the wrong subject.