AI RESEARCH

StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs

arXiv CS.CV

ArXi:2605.16353v1 Announce Type: new Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT methods operate under a restrictive task-incremental setting, where each