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

arXiv:2607.27902v1 Announce Type: new 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 will be released soon.

Related

• Masked Next-Scale Prediction for Self-supervised Scene Text Recognition
• Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
• SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
• GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning

Source: arXiv cs.CV | 2026-07-31