Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
arXiv preprint arXiv:2402.10884 , year=
2 Pith papers cite this work, alongside 15 external citations. Polarity classification is still indexing.
2
Pith papers citing it
15
external citations · external index
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A Nash equilibrium framework for training-free multimodal step verification that uses cross-modal agreement and disagreement signals for filtering and ranking reasoning steps.
citing papers explorer
-
Deep Pre-Alignment for VLMs
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
A Nash equilibrium framework for training-free multimodal step verification that uses cross-modal agreement and disagreement signals for filtering and ranking reasoning steps.