From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs

• URL: http://arxiv.org/abs/2502.09093v1
• Date: Thu, 13 Feb 2025 09:04:28 GMT
• Title: From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs
• Authors: Mingxiao Li, Fang Qu, Zhanpeng Chen, Na Su, Zhizhou Zhong, Ziyang Chen, Nan Du, Xiaolong Li,
• Abstract summary: Vision Dynamic Embedding-Guided Pretraining (VDEP) is a hybrid autoregressive training paradigm for MLLMs. The proposed method seamlessly integrates into standard models without architectural changes. Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods.
• Score: 23.011836329934255
• License:
• Abstract: While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into autoregressive training. Existing MLLMs primarily focused on recovering information from textual inputs, often neglecting the effective processing of image data. In contrast, the key improvement of this work is the reinterpretation of multimodal alignment as a process of recovering information from input data, with particular emphasis on reconstructing detailed visual features.The proposed method seamlessly integrates into standard models without architectural changes. Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods.

Related papers

• Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent [72.1517476116743]
  Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue. We introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation forgetting. We propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations.
  arXiv  Detail & Related papers  (2025-02-17T12:26:34Z)
• PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures [5.513631883813244]
  We propose a framework that textbfPre-textbfIntegratestextbfPrompt information into the visual encoding process using existingmodules of MLLMs. Our model maintains excellent generation even when half of the visual tokens are reduced.
  arXiv  Detail & Related papers  (2024-10-30T15:05:17Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex [4.57590454144072]
  Recently, there has been a surge in the popularity of pre trained large language models (LLMs) This paper proposes a new multi-modal training paradigm, aligning with LLM, encoding fMRI activity in visual cortex.
  arXiv  Detail & Related papers  (2024-01-08T12:30:23Z)
• Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models [121.83413400686139]
  This paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. We introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline.
  arXiv  Detail & Related papers  (2024-01-06T02:02:34Z)
• LAMM: Label Alignment for Multi-Modal Prompt Learning [17.478967970736115]
  We introduce an innovative label alignment method named textbfLAMM, which can adjust the category embeddings of downstream datasets through end-to-end training. Our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios. Our methodology exhibits the preeminence in continual learning compared to other prompt tuning methods.
  arXiv  Detail & Related papers  (2023-12-13T15:29:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.