USTC Papers Study Lifelong Learning for LMMs via Multimodal Knowledge Injection

教大模型终身学习！中科大连发两篇顶会，突破「知识注入」双重困境

USTC researchers released MMEVOKE and KORE: MMEVOKE contains 9,422 samples across 159 subcategories, while KORE uses knowledge-tree augmentation and null-space constrained fine-tuning to reduce catastrophic forgetting during multimodal knowledge injection.

Why it matters: HKR-K and HKR-R are solid: the post gives dataset size plus a concrete fine-tuning mechanism. It stays in the low featured band because this is paper-level knowledge injection without production evidence or full reproducibility details.