AI RESEARCH
UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization
arXiv CS.CV
•
ArXi:2606.00351v1 Announce Type: new Personalized visual understanding has advanced significantly, yet existing approaches struggle to localize and extract specific concepts when input images contain multiple objects. Many prior methods rely heavily on segmentation-based supervision or exhibit poor compositional generalization, limiting their ability to accurately disentangle and manipulate individual concepts. In this work, we propose UniVerse, a Unified Modulation Framework for segmentation-free, disentangled multi-concept personalization in diffusion transformers.