Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing editors mainly emphasize edit reliability and long-horizon stability, but rarely control the semantic boundary of each edit. Our pilot analyses of post-edit behaviors and internal neuronal activities reveal a scope gap behind reliable edits: instance-level success neither guarantees transfer to valid cross-modal variants nor prevents leakage to unrelated inputs, while e
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%huggingface/transformers →
- LinkedLinked via arxiv author · 85%Siyuan Li →
“Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing”
- LinkedLinked via arxiv author · 85%Youyuan Zhang →
“Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing”
- LinkedLinked via arxiv author · 85%Ruitong Liu →
“Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing”
- LinkedLinked via arxiv author · 85%Junxi Wang →
“Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing”
- LinkedLinked via arxiv author · 85%Jing Li →
“Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing”