6 papers
PhoneBuddy: Training Open Models for Agentic Phone Use
Zhengyang Tang, Xin Lai, Pengyuan Lyu +23
Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matter…
Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
Zhengyao Fang, Pengyuan Lyu, Chengquan Zhang +3
Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows that a large fraction of visual…
Recognition-Synergistic Scene Text Editing
Zhengyao Fang, Pengyuan Lyu, Jingjing Wu +4
Scene text editing aims to modify text content within scene images while maintaining style consistency. Traditional methods achieve this by explicitly disentangling style and conte…
WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting
Jingjing Wu, Zhengyao Fang, Pengyuan Lyu +4
Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary a…
StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
Pengyuan Lyu, Yulin Li, Hao Zhou +8
Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images pl…
Towards Unified Multi-granularity Text Detection with Interactive Attention
Xingyu Wan, Chengquan Zhang, Pengyuan Lyu +5
Existing OCR engines or document image analysis systems typically rely on training separate models for text detection in varying scenarios and granularities, leading to significant…