Multimodal LLMs exhibit functional sparsity where a small number of CoRe attention heads handle cross-modal retrieval, with ablation of the top 5% degrading performance while others have little effect.
Vlmt: Vision- language multimodal transformer for multimodal multi-hop question answering.ArXiv, abs/2504.08269, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
Multimodal LLMs exhibit functional sparsity where a small number of CoRe attention heads handle cross-modal retrieval, with ablation of the top 5% degrading performance while others have little effect.