Papers
arxiv:2507.00754

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs

Published on Jul 8, 2025
Authors:
,
,
,

Abstract

Language-Unlocked Vision Transformers (LUViT) addresses modality mismatch between vision transformers and large language models through joint pre-training with masked auto-encoding and low-rank adaptation.

The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge lies in the inherent modality mismatch between text-centric pretraining of LLMs and vision-centric training of ViTs. Direct fusion often fails to fully exploit the LLM's potential and suffers from unstable finetuning. As a result, LLM blocks are kept frozen while only the vision components are learned. As a remedy to these challenges, we introduce Language-Unlocked Vision Transformers (LUViT), a novel approach that bridges this modality mismatch through a synergistic pre-training strategy. LUViT co-adapts a ViT backbone and an LLM fusion block by (1) employing Masked Auto-Encoding (MAE) to pre-train the ViT for richer visual representations, and (2) concurrently training Low-Rank Adaptation (LoRA) layers within the LLM block using the MAE objective. This joint optimization guides the ViT to produce LLM-aligned features and the LLM to effectively interpret visual information. We demonstrate through extensive experiments that LUViT significantly improves performance on various downstream vision tasks, showcasing a more effective and efficient pathway to harness LLM knowledge for visual understanding.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2507.00754
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/2507.00754 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/2507.00754 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/2507.00754 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.