Xingsong Ye

3 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver ❓ The Questioner

Venues

CVPR (1) ICCV (1) NAACL (1)

Top co-authors

Yongkun Du (2) Zhineng Chen (2) Jiaxin Zhang (1) Jinlan Fu (1) Junwen Duan (1) Jing Lyu (1) Xuanjing Huang (1) Xipeng Qiu (1) Yunbo Tao (1) Siyin Wang (1)

Research topics

Artificial Intelligence (2) Machine Learning (2) Core AI (2) Learning Types · Machine Learning (2) Computer Vision (1) Deep Learning (1) Natural Language Processing (1) Application Areas (1) Applications (1) Domain-Specific (1) Learning Types · Deep Learning (1)

Keywords

scene text recognition (2) data annotation (1) ai safety (1) safety alignment (1) diffusion model (1) synthetic data (1) vision-language model (1) data synthesis (1) domain gap (1) ethical alignment (1) self-evolution learning (1) cross-modality safety (1) text generation (1) character-aware diffusion (1)

Papers

What's Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution CVPR 2026 Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models NAACL 2025 TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition ICCV 2025