works on
multimodal large language models 1reinforcement learning 1scene text spotting 1single-patch optimization 1visual token grounding 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

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

Rui Tang, Wentao Yang, Peirong Zhang +4

The paper introduces a vision-centric framework called SPaTS that uses a single visual token per text instance and reinforcement learning to improve scene text spotting accuracy an…