pith. machine review for the scientific record. sign in

ECoFLaP: Efficient coarse-to-fine layer-wise pruning for vision-language models.arXiv preprint arXiv:2310.02998,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

LinMU: Multimodal Understanding Made Linear

cs.CV · 2026-01-04 · conditional · novelty 6.0

LinMU achieves linear-complexity multimodal understanding by swapping self-attention for an M-MATE dual-branch block and distilling from a frozen teacher VLM, matching accuracy with up to 2.7x faster TTFT and 9x higher throughput.

citing papers explorer

Showing 1 of 1 citing paper.

  • LinMU: Multimodal Understanding Made Linear cs.CV · 2026-01-04 · conditional · none · ref 19

    LinMU achieves linear-complexity multimodal understanding by swapping self-attention for an M-MATE dual-branch block and distilling from a frozen teacher VLM, matching accuracy with up to 2.7x faster TTFT and 9x higher throughput.