Picture for Tianxiang Wu

Tianxiang Wu

PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures

Add code
Oct 30, 2024
Viaarxiv icon

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training

Add code
Aug 01, 2024
Viaarxiv icon