Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

• URL: http://arxiv.org/abs/2506.18898v1
• Date: Mon, 23 Jun 2025 17:59:14 GMT
• Title: Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
• Authors: Jiaming Han, Hao Chen, Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue, Lu Jiang,
• Abstract summary: This paper presents a framework that attempts to unify visual understanding and generation within a shared semantic representation.<n>At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary.<n> Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency.
• Score: 33.11867433769496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encoding and decoding to balance efficiency and visual detail, along with a generative de-tokenizer to produce high-fidelity visual outputs. To address diverse decoding needs, we utilize two complementary de-tokenizers: a fast autoregressive model and a diffusion-based model. To enhance modality fusion, we investigate advanced pre-training tasks, demonstrating improvements in both visual understanding and generation. Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency. Code, models, and data are available at https://tar.csuhan.com

Related papers

• Unified Multimodal Understanding via Byte-Pair Visual Encoding [34.96534298857146]
  Multimodal large language models (MLLMs) have made significant progress in vision-language understanding.<n>We present a framework that unifies multimodal understanding by applying byte-pair encoding to visual tokens.
  arXiv  Detail & Related papers  (2025-06-30T09:08:08Z)
• FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens [56.752362642658504]
  We present FuseLIP, an alternative architecture for multimodal embedding.<n>We propose a single transformer model which operates on an extended vocabulary of text and image tokens.<n>We show that FuseLIP outperforms other approaches in multimodal embedding tasks such as VQA and text-guided image transformation retrieval.
  arXiv  Detail & Related papers  (2025-06-03T17:27:12Z)
• Aligning Vision to Language: Text-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)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• The Narrow Gate: Localized Image-Text Communication in Vision-Language Models [36.33608889682152]
  This study investigates how vision-language models handle image-understanding tasks.<n>We find that in models with multimodal outputs, image and text embeddings are more separated within the residual stream.<n>In contrast, models trained for image and text generation tend to rely on a single token that acts as a narrow gate for visual information.
  arXiv  Detail & Related papers  (2024-12-09T16:39:40Z)
• ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models [73.34709921061928]
  We propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs)<n>We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map.<n>Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point.
  arXiv  Detail & Related papers  (2024-07-31T11:40:29Z)
• Harmonizing Visual Text Comprehension and Generation [31.605599298507293]
  We present TextHarmony, a unified and versatile multimodal generative model proficient in comprehending and generating visual text. We propose Slide-LoRA, which aggregates modality-specific and modality-agnostic LoRA experts, partially decoupling the multimodal generation space. Comprehensive experiments across various benchmarks demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2024-07-23T10:11:56Z)
• UniCode: Learning a Unified Codebook for Multimodal Large Language Models [33.48624855154342]
  We propose textbfUniCode, a novel approach within the domain of multimodal large language models (MLLMs) UniCode learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. Despite using significantly fewer parameters and less data during training, Unicode demonstrates promising capabilities in visual reconstruction and generation.
  arXiv  Detail & Related papers  (2024-03-14T03:29:58Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens [76.40196364163663]
  We propose a learning-based vision-language pre-training approach, such as CLIP. We show that our method can learn more comprehensive representations and capture meaningful cross-modal correspondence.
  arXiv  Detail & Related papers  (2023-03-27T00:58:39Z)
• MaPLe: Multi-modal Prompt Learning [54.96069171726668]
  We propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations. Compared with the state-of-the-art method Co-CoOp, MaPLe exhibits favorable performance and achieves an absolute gain of 3.45% on novel classes.
  arXiv  Detail & Related papers  (2022-10-06T17:59:56Z)
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [52.40490994871753]
  We introduce a contrastive loss to representations BEfore Fusing (ALBEF) through cross-modal attention. We propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-07-16T00:19:22Z)

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.