Communication-Inspired Tokenization for Structured Image Representations

• URL: http://arxiv.org/abs/2602.20731v1
• Date: Tue, 24 Feb 2026 09:53:50 GMT
• Title: Communication-Inspired Tokenization for Structured Image Representations
• Authors: Aram Davtyan, Yusuf Sahin, Yasaman Haghighi, Sebastian Stapf, Pablo Acuaviva, Alexandre Alahi, Paolo Favaro,
• Abstract summary: COMmunication inspired Tokenization (COMiT) is a framework for learning structured discrete visual token sequences.<n>Our experiments demonstrate that while semantic alignment provides grounding, attentive sequential tokenization is critical for inducing interpretable, object-centric token structure.
• Score: 74.17163003465537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for reconstruction and compression, often yielding tokens that capture local texture rather than object-level semantic structure. Inspired by the incremental and compositional nature of human communication, we introduce COMmunication inspired Tokenization (COMiT), a framework for learning structured discrete visual token sequences. COMiT constructs a latent message within a fixed token budget by iteratively observing localized image crops and recurrently updating its discrete representation. At each step, the model integrates new visual information while refining and reorganizing the existing token sequence. After several encoding iterations, the final message conditions a flow-matching decoder that reconstructs the full image. Both encoding and decoding are implemented within a single transformer model and trained end-to-end using a combination of flow-matching reconstruction and semantic representation alignment losses. Our experiments demonstrate that while semantic alignment provides grounding, attentive sequential tokenization is critical for inducing interpretable, object-centric token structure and substantially improving compositional generalization and relational reasoning over prior methods.

Related papers

• VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction [83.50898344094153]
  VQRAE produces Continuous semantic features for image understanding and tokens for visual generation within a unified tokenizer.<n>Design enables negligible semantic information for maintaining the ability of multimodal understanding, discrete tokens.<n>VQRAE presents competitive performance on several benchmarks of visual understanding, generation and reconstruction.
  arXiv  Detail & Related papers  (2025-11-28T17:26:34Z)
• Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer [50.69959748410398]
  We introduce MingTok, a new family of visual tokenizers with a continuous latent space for unified autoregressive generation and understanding.<n>MingTok adopts a three-stage sequential architecture involving low-level encoding, semantic expansion, and visual reconstruction.<n>Built on top of it, Ming-UniVision eliminates the need for task-specific visual representations, and unifies diverse vision-language tasks under a single autoregrsssive prediction paradigm.
  arXiv  Detail & Related papers  (2025-10-08T02:50:14Z)
• Tokenize Image as a Set [17.142970970610616]
  We introduce an unordered token set representation to dynamically allocate coding capacity based on regional semantic complexity.<n>To address the challenge of modeling discrete sets, we devise a dual transformation mechanism that transforms sets into fixed-length integer sequences.<n>Experiments demonstrate our method's superiority in semantic-aware representation and generation quality.
  arXiv  Detail & Related papers  (2025-03-20T17:59:51Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• Lexical Manifold Reconfiguration in Large Language Models: A Novel Architectural Approach for Contextual Modulation [0.0]
  A structured approach was developed for dynamically reconfiguring token embeddings through continuous geometric transformations.<n>A manifold-based transformation mechanism was integrated to regulate lexical positioning, allowing embeddings to undergo controlled shifts.<n> Empirical evaluations demonstrated that embedding reconfiguration contributed to reductions in perplexity, improved lexical coherence, and enhanced sentence-level continuity.
  arXiv  Detail & Related papers  (2025-02-12T22:11:07Z)
• Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation [0.0]
  The integration of structured hierarchical embeddings into transformer-based architectures introduces a refined approach to lexical representation.<n>A projection mechanism that maps tokens onto a structured manifold provides improved lexical alignment.<n>The refined hierarchical organization of embeddings provides greater interpretability in lexical modeling.
  arXiv  Detail & Related papers  (2025-02-08T00:49:32Z)
• Contextually Structured Token Dependency Encoding for Large Language Models [0.0]
  Self-attention mechanisms capture dynamic contextual dependencies, but their reliance on learned weight distributions limits the preservation of long-range hierarchical structures in generated sequences.<n>Dependency-aware token encoding introduces a structured approach to embedding, ensuring relational constraints are embedded within token representations.<n> Empirical evaluations indicate reductions in perplexity across diverse linguistic benchmarks, suggesting improvements in contextual coherence and predictive consistency in autoregressive text generation.
  arXiv  Detail & Related papers  (2025-01-30T08:51:48Z)
• Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning [81.24269148865555]
  A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability. We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency. Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically.
  arXiv  Detail & Related papers  (2022-12-12T15:40:30Z)
• Single-Stream Multi-Level Alignment for Vision-Language Pretraining [103.09776737512078]
  We propose a single stream model that aligns the modalities at multiple levels. We achieve this using two novel tasks: symmetric cross-modality reconstruction and a pseudo-labeled key word prediction. We demonstrate top performance on a set of Vision-Language downstream tasks such as zero-shot/fine-tuned image/text retrieval, referring expression, and VQA.
  arXiv  Detail & Related papers  (2022-03-27T21:16:10Z)

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.