MS-Resampler deploys multiple scope-specific resamplers with explicit spatial priors and adaptive fusion to outperform single-scope global cross-attention in MLLMs on ten benchmarks with minimal added cost.
arXiv preprint arXiv:2512.18910 (2025) 4
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
-
MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs
MS-Resampler deploys multiple scope-specific resamplers with explicit spatial priors and adaptive fusion to outperform single-scope global cross-attention in MLLMs on ten benchmarks with minimal added cost.