CLASP reduces visual tokens in MLLMs through class-adaptive multi-layer fusion and dual-stage pruning of salient and completion tokens, outperforming prior single-layer static methods across benchmarks and architectures.
(36)).Naively, computing ρn,t = max j∈Pn u⊤ n,tun,j for all t∈ U n costs O((Mn −K 1)K1d)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
CLASP reduces visual tokens in MLLMs through class-adaptive multi-layer fusion and dual-stage pruning of salient and completion tokens, outperforming prior single-layer static methods across benchmarks and architectures.