Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Peng, Zelin, Xu, Zhengqin, Liu, Qingyang, Yang, Xiaokang, Shen, Wei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.20322
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918253661519872
author Peng, Zelin
Xu, Zhengqin
Liu, Qingyang
Yang, Xiaokang
Shen, Wei
author_facet Peng, Zelin
Xu, Zhengqin
Liu, Qingyang
Yang, Xiaokang
Shen, Wei
contents Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computational resources (e.g., thousands of GPUs) for training to achieve cross-modal alignment at multi-granularity levels. We argue that a key source of this inefficiency lies in the vision encoders they widely equip with, e.g., CLIP and SAM, which lack the alignment with language at multi-granularity levels. To address this issue, in this paper, we leverage hyperbolic space, which inherently models hierarchical levels and thus provides a principled framework for bridging the granularity gap between visual and textual modalities at an arbitrary granularity level. Concretely, we propose an efficient training paradigm for MLLMs, dubbed as HyperET, which can optimize visual representations to align with their textual counterparts at an arbitrary granularity level through dynamic hyperbolic radius adjustment in hyperbolic space. HyperET employs learnable matrices with Möbius multiplication operations, implemented via three effective configurations: diagonal scaling matrices, block-diagonal matrices, and banded matrices, providing a flexible yet efficient parametrization strategy. Comprehensive experiments across multiple MLLM benchmarks demonstrate that HyperET consistently improves both existing pre-training and fine-tuning MLLMs clearly with less than 1\% additional parameters. Code is available at https://github.com/godlin-sjtu/HyperET
format Preprint
id arxiv_https___arxiv_org_abs_2510_20322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
Peng, Zelin
Xu, Zhengqin
Liu, Qingyang
Yang, Xiaokang
Shen, Wei
Computer Vision and Pattern Recognition
Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computational resources (e.g., thousands of GPUs) for training to achieve cross-modal alignment at multi-granularity levels. We argue that a key source of this inefficiency lies in the vision encoders they widely equip with, e.g., CLIP and SAM, which lack the alignment with language at multi-granularity levels. To address this issue, in this paper, we leverage hyperbolic space, which inherently models hierarchical levels and thus provides a principled framework for bridging the granularity gap between visual and textual modalities at an arbitrary granularity level. Concretely, we propose an efficient training paradigm for MLLMs, dubbed as HyperET, which can optimize visual representations to align with their textual counterparts at an arbitrary granularity level through dynamic hyperbolic radius adjustment in hyperbolic space. HyperET employs learnable matrices with Möbius multiplication operations, implemented via three effective configurations: diagonal scaling matrices, block-diagonal matrices, and banded matrices, providing a flexible yet efficient parametrization strategy. Comprehensive experiments across multiple MLLM benchmarks demonstrate that HyperET consistently improves both existing pre-training and fine-tuning MLLMs clearly with less than 1\% additional parameters. Code is available at https://github.com/godlin-sjtu/HyperET
title HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.20322