Saved in:
Bibliographic Details
Main Authors: Li, Tianle, Rao, Yongming, Hu, Winston, Cheng, Yu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917958776782848
author Li, Tianle
Rao, Yongming
Hu, Winston
Cheng, Yu
author_facet Li, Tianle
Rao, Yongming
Hu, Winston
Cheng, Yu
contents Encoder-free multimodal large language models(MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal architecture that mitigates this issue. BREEN leverages a learnable query and image experts to achieve comparable performance with significantly less training data. The learnable query, positioned between image and text tokens, is supervised by the output of a pretrained CLIP model to distill visual knowledge, bridging the gap between visual and textual modalities. Additionally, the image expert processes image tokens and learnable queries independently, improving efficiency and reducing interference with the LLM's textual capabilities. BREEN achieves comparable performance to prior encoder-free state-of-the-art models like Mono-InternVL, using only 13 million text-image pairs in training about one percent of the data required by existing methods. Our work highlights a promising direction for data-efficient encoder-free multimodal learning, offering an alternative to traditional encoder-based approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12446
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries
Li, Tianle
Rao, Yongming
Hu, Winston
Cheng, Yu
Computer Vision and Pattern Recognition
Artificial Intelligence
Encoder-free multimodal large language models(MLLMs) eliminate the need for a well-trained vision encoder by directly processing image tokens before the language model. While this approach reduces computational overhead and model complexity, it often requires large amounts of training data to effectively capture the visual knowledge typically encoded by vision models like CLIP. The absence of a vision encoder implies that the model is likely to rely on substantial data to learn the necessary visual-semantic alignments. In this work, we present BREEN, a data-efficient encoder-free multimodal architecture that mitigates this issue. BREEN leverages a learnable query and image experts to achieve comparable performance with significantly less training data. The learnable query, positioned between image and text tokens, is supervised by the output of a pretrained CLIP model to distill visual knowledge, bridging the gap between visual and textual modalities. Additionally, the image expert processes image tokens and learnable queries independently, improving efficiency and reducing interference with the LLM's textual capabilities. BREEN achieves comparable performance to prior encoder-free state-of-the-art models like Mono-InternVL, using only 13 million text-image pairs in training about one percent of the data required by existing methods. Our work highlights a promising direction for data-efficient encoder-free multimodal learning, offering an alternative to traditional encoder-based approaches.
title BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.12446