InfoTok: Regulating Information Flow for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs

• URL: http://arxiv.org/abs/2602.01554v1
• Date: Mon, 02 Feb 2026 02:47:48 GMT
• Title: InfoTok: Regulating Information Flow for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
• Authors: Lv Tang, Tianyi Zheng, Bo Li, Xingyu Li,
• Abstract summary: multimodal large language models (MLLMs) integrate image understanding and generation in a single framework.<n>We introduce a capacity-constrained perspective, highlighting that in shared-token unified MLLMs the visual tokenizer behaves as a compute-bounded learner.<n>Motivated by this perspective, we propose InfoTok, an information-regularized visual tokenization mechanism.
• Score: 29.96158942341168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unified multimodal large language models (MLLMs) integrate image understanding and generation in a single framework, with the visual tokenizer acting as the sole interface that maps visual inputs into tokens for downstream tasks. However, existing shared-token designs are mostly architecture-driven and lack an explicit criterion for what information tokens should preserve to support both understanding and generation. Therefore, we introduce a capacity-constrained perspective, highlighting that in shared-token unified MLLMs the visual tokenizer behaves as a compute-bounded learner, so the token budget should prioritize reusable structure over hard-to-exploit high-entropy variations and redundancy. Motivated by this perspective, we propose InfoTok, an information-regularized visual tokenization mechanism grounded in the Information Bottleneck (IB) principle. InfoTok formulates tokenization as controlling information flow from images to shared tokens to multimodal outputs, yielding a principled trade-off between compression and task relevance via mutual-information regularization. We integrate InfoTok into three representative unified MLLMs without introducing any additional training data. Experiments show consistent improvements on both understanding and generation, supporting information-regularized tokenization as a principled foundation for learning a shared token space in unified MLLMs.

Related papers

• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Quantizing Text-attributed Graphs for Semantic-Structural Integration [6.721504414917793]
  Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains.<n>With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning.<n>We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using a frozen codebook.
  arXiv  Detail & Related papers  (2025-07-20T09:18:02Z)
• Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach [55.861432910722186]
  UniToCom is a unified token communication paradigm that treats tokens as the fundamental units for both processing and wireless transmission.<n>We propose a generative information bottleneck (GenIB) principle, which facilitates the learning of tokens that preserve essential information.<n>We employ a causal Transformer-based multimodal large language model (MLLM) at the receiver to unify the processing of both discrete and continuous tokens.
  arXiv  Detail & Related papers  (2025-07-02T14:03:01Z)
• Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM [21.967692616735196]
  multimodal large language models (MLLMs) have emerged as a key approach in achieving artificial general intelligence.<n>We propose an object-centric visual tokenizer based on Slot Attention specifically for MLLMs.<n>This work is the first demonstration of the feasibility of object-centric slot attention performed with MLLMs and in-the-wild natural images.
  arXiv  Detail & Related papers  (2025-05-23T10:43:45Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models.<n>How MLLMs process and utilize visual information remains unclear.<n>We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning [10.761218096540976]
  Multimodal reasoning in Large Language Models (LLMs) struggles with incomplete knowledge and hallucination artifacts.<n>We propose Vision-align-to-Language integrated Knowledge Graph (VaLiK), a novel approach for constructing Multimodal Knowledge Graphs.
  arXiv  Detail & Related papers  (2025-03-17T09:31:14Z)
• Enhancing Item Tokenization for Generative Recommendation through Self-Improvement [67.94240423434944]
  Generative recommendation systems are driven by large language models (LLMs)<n>Current item tokenization methods include using text descriptions, numerical strings, or sequences of discrete tokens.<n>We propose a self-improving item tokenization method that allows the LLM to refine its own item tokenizations during training process.
  arXiv  Detail & Related papers  (2024-12-22T21:56:15Z)
• Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
  High-resolution images and videos pose a barrier to their broader adoption.<n> compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.<n>We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
  arXiv  Detail & Related papers  (2024-11-26T09:36:02Z)
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens [57.37893387775829]
  We introduce a fast and balanced clustering method, named Semantic Equitable Clustering (SEC)<n>SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner.<n>We propose a versatile vision backbone, SECViT, to serve as a vision language connector.
  arXiv  Detail & Related papers  (2024-05-22T04:49:00Z)
• ActiveMLP: An MLP-like Architecture with Active Token Mixer [54.95923719553343]
  This paper presents ActiveMLP, a general-like backbone for computer vision. We propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate contextual information from other tokens in the global scope into the given one. In this way, the spatial range of token-mixing is expanded and the way of token-mixing is reformed.
  arXiv  Detail & Related papers  (2022-03-11T17:29:54Z)

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.