Unified Multimodal Understanding via Byte-Pair Visual Encoding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Wanpeng, Feng, Yicheng, Luo, Hao, Li, Yijiang, Yue, Zihao, Zheng, Sipeng, Lu, Zongqing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909666973319168
author Zhang, Wanpeng
Feng, Yicheng
Luo, Hao
Li, Yijiang
Yue, Zihao
Zheng, Sipeng
Lu, Zongqing
author_facet Zhang, Wanpeng
Feng, Yicheng
Luo, Hao
Li, Yijiang
Yue, Zihao
Zheng, Sipeng
Lu, Zongqing
contents Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal understanding by applying byte-pair encoding to visual tokens. Unlike conventional approaches that rely on modality-specific encoders, our method directly incorporates structural information into visual tokens, mirroring successful tokenization strategies in text-only language models. We introduce a priority-guided encoding scheme that considers both frequency and spatial consistency, coupled with a multi-stage training procedure based on curriculum-driven data composition. These enhancements enable the transformer model to better capture cross-modal relationships and reason with visual information. Comprehensive experiments demonstrate improved performance across diverse vision-language tasks. By bridging the gap between visual and textual representations, our approach contributes to the advancement of more capable and efficient multimodal foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23639
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unified Multimodal Understanding via Byte-Pair Visual Encoding
Zhang, Wanpeng
Feng, Yicheng
Luo, Hao
Li, Yijiang
Yue, Zihao
Zheng, Sipeng
Lu, Zongqing
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal understanding by applying byte-pair encoding to visual tokens. Unlike conventional approaches that rely on modality-specific encoders, our method directly incorporates structural information into visual tokens, mirroring successful tokenization strategies in text-only language models. We introduce a priority-guided encoding scheme that considers both frequency and spatial consistency, coupled with a multi-stage training procedure based on curriculum-driven data composition. These enhancements enable the transformer model to better capture cross-modal relationships and reason with visual information. Comprehensive experiments demonstrate improved performance across diverse vision-language tasks. By bridging the gap between visual and textual representations, our approach contributes to the advancement of more capable and efficient multimodal foundation models.
title Unified Multimodal Understanding via Byte-Pair Visual Encoding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.23639