
JL
Junhao Li, Xinhao Zhong, Yi sun, Yuxia Qiao, Bin Chen, Shu-Tao Xia, Yaowei Wang
· 1 min read
ResearcharXiv cs.CV
C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models
arXiv:2605.19750v2 Announce Type: replace
Abstract: Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation, yet their personalization capabilities remain largely limited to static, single-concept settings. In practice, users may continuously introduce new concepts and wish to compose multiple personalized concepts within a single image. Such scenarios pose two fundamental challenges: catastrophic forgetting during sequential personalization and feature interference during multi-concept composition. In this work, we study continual and compositional personalization in VAR models and propose C2P-VAR, a unified framework addressing both challenges. For continual personalization, we introduce C2PVAR-S, which identifies concept-relevant parameters from gradient magnitudes and dynamically updates their selection during training. To preserve previously learned concepts, C2PVAR-S applies regularization only to parameters shared by the current and historical concepts, thereby reducing unnecessary interference without introducing additional model components. For multi-concept personalization, we further propose C2PVAR-M, which employs parallel global and concept-specific branches with spatially localized feature fusion and logit aggregation to achieve controllable concept placement and reduce feature entanglement. Extensive experiments on continual and multi-concept personalization demonstrate that C2P-VAR consistently outperforms existing baselines in subject fidelity, while maintaining competitive text alignment and introducing negligible storage and inference overhead. Our results establish a unified framework for scalable and controllable personalization of visual autoregressive models.
Original source
This story was published by arXiv cs.CV and written by Junhao Li, Xinhao Zhong, Yi sun, Yuxia Qiao, Bin Chen, Shu-Tao Xia, Yaowei Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


