paper-with-me

Papers

End-to-End Vision Tokenizer Tuning

2025-05-15 · Wenxuan Wang, Fan Zhang, Yufeng Cui, Haiwen Diao, Zhuoyan Luo, Huchuan Lu, Jing Liu, Xinlong Wang

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The vision tokenizer optimized for low-level reconstruction is agnostic to downstream tasks requiring varied representations and semantics. This decoupled paradigm introduces a critical misalignment: The loss of the vision tokenization can be the representation bottleneck for target tasks. For example, errors in tokenizing text in a given image lead to poor results when recognizing or generating them. To address this, we propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks. Unlike prior autoregressive models that use only discrete indices from a frozen vision tokenizer, ETT leverages the visual embeddings of the tokenizer codebook, and optimizes the vision tokenizers end-to-end with both reconstruction and caption objectives. ETT can be seamlessly integrated into existing training pipelines with minimal architecture modifications. Our ETT is simple to implement and integrate, without the need to adjust the original codebooks or architectures of the employed large language models. Extensive experiments demonstrate that our proposed end-to-end vision tokenizer tuning unlocks significant performance gains, i.e., 2-6% for multimodal understanding and visual generation tasks compared to frozen tokenizer baselines, while preserving the original reconstruction capability. We hope this very simple and strong method can empower multimodal foundation models besides image generation and understanding.

📄 PDF Abstract BibTeX arXiv:2505.10562

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationQuestion AnsweringVisual Question Answering

Similar Papers 제목 키워드 기반

What Makes for Good Visual Tokenizers for Large Language Models?

2023-05-20 · Guangzhi Wang, Yixiao Ge, Xiaohan Ding, Mohan Kankanhalli 외

We empirically investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs). In our benchmark, which is curated to evaluat…

Image CaptioningObject CountingQuestion AnsweringVisual Question Answering

Tokenization of Gaze Data

2025-03-28 · Tim Rolff, Jurik Karimian, Niklas Hypki, Susanne Schmidt 외

A considerable part of the performance of today's large language models (LLM's) and multimodal large language models (MLLM's) depends on their tokenization strategies. While tokenizers are extensively researched for text…

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

2024-03-12 · CVPR 2024 1 · Lei Zhu, Fangyun Wei, Yanye Lu

In this work, we investigate the potential of a large language model (LLM) to directly comprehend visual signals without the necessity of fine-tuning on multi-modal datasets. The foundational concept of our method views …

DeblurringDecoderDenoisingImage Captioning+6

Getting the most out of your tokenizer for pre-training and domain adaptation

2024-02-01 · Gautier Dagan, Gabriel Synnaeve, Baptiste Rozière

Tokenization is an understudied and often neglected component of modern LLMs. Most published works use a single tokenizer for all experiments, often borrowed from another model, without performing ablations or analysis t…

Code GenerationDomain AdaptationHumanEvalmbpp

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

2026-09-08 · Siting Li, Zhengyang Wang, Simon Shaolei Du, Xi Chen 외 hf

Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how vi…

Continual Pretraining