Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost by pruning redundant visual tokens, but permanently discard visual evidence that may become useful in subsequent layers. We instead ask whe...
Jing-Di Lei, Junxian Li, Di Zhang et al.
· 0 citations