← 研踪 PaperTrailarXiv:2611.13334 · v1
Disentangling Multimodal Rotary Positional Embedding in Vision-Language Models
首次提交 2026-11-10 07:00
版本更新 2026-11-10 07:00
雷达观测 2026-11-11 11:04
摘要
Vision-language models widely adopt Multimodal Rotary Position Embedding (MRoPE), an extension of Rotary Position Embedding (RoPE) that incorporates temporal, height, and width axes to encode the spatial structure of visual tokens. However, MRoPE also assigns height and width coordinates to text tokens that lack inherent spatial structure, introducing spatial positional effects into text-vision attention. Existing MRoPE variants explore different frequency allocations and coordinate layouts, with their designs suggesting different intuitions about these cross-modal effects: they may provide useful spatial references for associating language with visual regions, or introduce unnecessary positional preferences that hinder text-vision interactions. In this work, we disentangle intra-visual spatial structure from cross-modal spatial effects to investigate this question. We identify a constraint of shared coordinate layouts that prevents eliminating cross-modal spatial effects while preserving intra-visual spatial encoding, and develop controlled experiments to isolate their respective contributions. Our results across multiple model scales, MRoPE variants, and benchmarks show that cross-modal spatial effects provide little additional benefit as spatial references and can even impair model performance, while intra-visual spatial encoding remains useful for fine-grained grounding.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-10 07:00 · 最新观测版本
Disentangling Multimodal Rotary Positional Embedding in Vision-Language Models
Vision-language models widely adopt Multimodal Rotary Position Embedding (MRoPE), an extension of Rotary Position Embedding (RoPE) that incorporates temporal, height, and width axes to encode the spatial structure of visual tokens. However, MRoPE also assigns height and width coordinates to text tokens that lack inherent spatial structure, introducing spatial positional effects into text-vision attention. Existing MRoPE variants explore different frequency allocations and coordinate layouts, with their designs suggesting different intuitions about these cross-modal effects: they may provide useful spatial references for associating language with visual regions, or introduce unnecessary positional preferences that hinder text-vision interactions. In this work, we disentangle intra-visual spatial structure from cross-modal spatial effects to investigate this question. We identify a constraint of shared coordinate layouts that prevents eliminating cross-modal spatial effects while preserving intra-visual spatial encoding, and develop controlled experiments to isolate their respective contributions. Our results across multiple model scales, MRoPE variants, and benchmarks show that cross-modal spatial effects provide little additional benefit as spatial references and can even impair model performance, while intra-visual spatial encoding remains useful for fine-grained grounding.
查看此版本解读 →查看此版本原文 ↗