GAFU 框架：解锁统一多模态模型中的细粒度视觉理解
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
GAFU 框架通过将生成端视觉表示压缩为紧凑的 G token，提升统一多模态模型的细粒度视觉理解能力，支持任务条件检索。在 VStar-Bench、OmniSpatial 和 VSR-Bench 上，GAFU 相比相同数据的 SFT 基线模型最大相对提升达 20.00%、17.94% 和 8.62%。
Published on Oct 14
Authors:
,
,
,
,
,
,
,
Abstract
GAFU leverages native generation-side representations to improve fine-grained visual understanding in unified multimodal models by compressing them into compact tokens for task-conditioned retrieval.
Fine-grained visual understanding requires distinguishing subtle differences in local attributes and spatial relations, yet remains challenging for existing vision-language models. Unified multimodal models (UMMs) offer a new opportunity through generation pathways that preserve rich visual information complementary to understanding. However, existing generation-assisted understanding methods mainly rely on generative supervision or explicit generation and have not systematically explored direct use of native generation-side representations. To address this gap, we systematically analyze what generation-side representations offer for fine-grained understanding, finding that they are more sensitive to fine-grained semantic changes, capture task-relevant changes missed by understanding-side representations, and depend on correct spatial organization for this advantage. Guided by these findings, we design GAFU, a post-training framework that unlocks native generation-side information for fine-grained understanding. It compresses generation-side visual representations into compact \(G\) tokens that preserve fine-grained visual details, enabling task-conditioned retrieval by the understanding pathway. Experiments show that GAFU consistently outperforms SFT baselines trained on the same data across diverse visual understanding tasks and UMM architectures, with maximum relative improvements of 20.00\%, 17.94\%, and 8.62\% on VStar-Bench, OmniSpatial, and VSR-Bench, respectively. Overall, GAFU converts complementary information from the generation pathway into gains in fine-grained visual understanding, providing an effective path toward synergy between generation and understanding in UMMs.
View arXiv page View PDF GitHub 2 Add to collection
Get this paper in your agent:
hf papers read 2610.23987
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.23987 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.23987 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.23987 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
来源: Hugging Face Daily Papers · huggingface.co