One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting

• URL: http://arxiv.org/abs/2607.27902v2
• Date: Mon, 03 Aug 2026 05:25:10 GMT
• Title: One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting
• Abstract summary: Scene text spotting requires high-precision alignment between textual recognition and spatial localization.<n>We propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token.<n>We show that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs.
• Score: 51.09550363815034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances. To address this, we propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token and then recovers geometry via full-image refinement. To accurately identify this anchor without oracle labels, we introduce Single-Patch Selective Optimization (SPaSO), a reinforcement learning framework that optimizes discrete visual-token selection using patch-level rewards. To further improve representation robustness and localization precision, we introduce Directional Embedding Alignment (DEA) to suppress unstable norm bias by decoupling feature magnitude and direction, and Patch-Enhanced Decoding (PED) to fuse the routed anchor with language semantics and cross-attend over the full-image feature map for geometry-aware boundary regression beyond coordinate-space surrogates. Extensive experiments demonstrate that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs. Code is available at https://github.com/eeNickTang/SPaTS.

Related papers

• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models [22.803631190636313]
  We introduce Timage, a paradigm that recasts multimodal understanding as an alignment problem solved at the input.<n>The study positions deliberate input reconstruction as a powerful, architecture-neutral lever for strengthening multimodal reasoning.
  arXiv  Detail & Related papers  (2026-06-18T08:40:41Z)
• Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models [84.78794648147608]
  A persistent geometric anomaly, the Modality Gap, remains.<n>Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions.<n>We propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap into stable biases and anisotropic residuals.<n>We then introduce ReAlign, a training-free modality alignment strategy.
  arXiv  Detail & Related papers  (2026-02-02T13:59:39Z)
• Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment [66.80402022104074]
  We propose a Text Refinement and Alignment (TRA) framework that effectively utilizes textual features from visual descriptions to complement the visual features as they are semantically rich.<n>This is achieved by designing two new modules for the original point-supervised framework: a Point-based Text Refinement module (PTR) and a Point-based Multimodal Alignment module (PMA)
  arXiv  Detail & Related papers  (2026-02-01T14:35:46Z)
• SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment [8.657941729790599]
  We introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity.<n>Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches.<n>Experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance.
  arXiv  Detail & Related papers  (2025-11-03T09:41:32Z)
• Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection [65.29550320117526]
  We propose a novel framework named FineGrainedAD to improve anomaly localization performance.<n> Experiments demonstrate that the proposed FineGrainedAD achieves superior overall performance in few-shot settings.
  arXiv  Detail & Related papers  (2025-10-30T13:09:00Z)
• Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs [88.68484904214142]
  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.
  arXiv  Detail & Related papers  (2025-10-02T12:23:57Z)
• Visual Semantic Description Generation with MLLMs for Image-Text Matching [7.246705430021142]
  We propose a novel framework that bridges the modality gap by leveraging multimodal large language models (MLLMs) as visual semantics.<n>Our approach combines: (1) Instance-level alignment by fusing visual features with VSD to enhance the linguistic expressiveness of image representations, and (2) Prototype-level alignment through VSD clustering to ensure category-level consistency.
  arXiv  Detail & Related papers  (2025-07-11T13:38:01Z)
• Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation [12.893224628061516]
  The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression.<n>We propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges.<n>Our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets.
  arXiv  Detail & Related papers  (2025-01-01T14:24:04Z)

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.