AI RESEARCH
SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
arXiv CS.LG
•
ArXi:2605.22743v1 Announce Type: new Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive post-hoc fusion or freeze adaptation subspaces, which limit expressiveness and concept fidelity. To address this trade-off, we propose Sequential regularized LoRA (SeqLoRA), a constrained continual learning framework that jointly optimizes both LoRA factors via bilevel optimization.