Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

• URL: http://arxiv.org/abs/2510.01954v1
• Date: Thu, 02 Oct 2025 12:23:57 GMT
• Title: Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
• Authors: Yongyi Su, Haojie Zhang, Shijie Li, Nanqing Liu, Jingyi Liao, Junyi Pan, Yuan Liu, Xiaofen Xing, Chong Sun, Chen Li, Nancy F. Chen, Shuicheng Yan, Xulei Yang, Xun Xu,
• Abstract summary: We introduce Patch-as-Decodable Token (PaDT) to generate both textual and diverse visual outputs.<n>Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images.<n>We show PaDT consistently achieves state-of-the-art performance, even compared with significantly larger MLLM models.
• Score: 88.68484904214142
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as generating coordinates as text for detection, which limits performance and prevents dense prediction tasks like segmentation. To overcome these challenges, we introduce Patch-as-Decodable Token (PaDT), a unified paradigm that enables MLLMs to directly generate both textual and diverse visual outputs. Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images and interleaved seamlessly with LLM's output textual tokens. A lightweight decoder then transforms LLM's outputs into detection, segmentation, and grounding predictions. Unlike prior methods, PaDT processes VRTs independently at each forward pass and dynamically expands the embedding table, thus improving localization and differentiation among similar objects. We further tailor a training strategy for PaDT by randomly selecting VRTs for supervised fine-tuning and introducing a robust per-token cross-entropy loss. Our empirical studies across four visual perception and understanding tasks suggest PaDT consistently achieving state-of-the-art performance, even compared with significantly larger MLLM models. The code is available at https://github.com/Gorilla-Lab-SCUT/PaDT.

Related papers

• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models [75.88232735646018]
  Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos.<n>Existing methods attempt to prune redundant vision tokens, revealing substantial redundancy in visual representations.<n>We propose CoViPAL, a layer-wise contextualized visual token pruning method that employs a Plug-and-Play Pruning Module (PPM) to predict and remove redundant vision tokens before they are processed by the LVLM.
  arXiv  Detail & Related papers  (2025-08-24T07:47:00Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [66.04061083611863]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation.<n>We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE)<n>DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models [6.467840081978855]
  multimodal large language models (MM-LLMs) have achieved significant success in various tasks.<n>Main computational burden arises from processingd text and visual tokens.<n>We propose a dynamic pruning algorithm that identifies the inflection point in the visual CLS token similarity curve.
  arXiv  Detail & Related papers  (2024-09-02T10:49:10Z)
• 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)
• TokenPacker: Efficient Visual Projector for Multimodal LLM [37.1071749188282]
  The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) We propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. Our approach compresses the visual tokens by 75%89%, while achieves comparable or even better performance across diverse benchmarks.
  arXiv  Detail & Related papers  (2024-07-02T16:10:55Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language.<n>This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok)<n>SeTok groups visual features into semantic units via a dynamic clustering algorithm.<n>The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Masked and Permuted Implicit Context Learning for Scene Text Recognition [8.742571493814326]
  Scene Recognition (STR) is difficult because of variations in text styles, shapes, and backgrounds. We propose a masked and permuted implicit context learning network for STR, within a single decoder.
  arXiv  Detail & Related papers  (2023-05-25T15:31:02Z)
• 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)

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.