Qiushi Wang — accepted AI-conference papers

2026

Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance

Minxing Luo, Linlong Fan, Qiushi Wang, Ge Wu, Yiyan Luo, Yuhang Yu +4

CVPR 2026

Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image quality and textual readability. To address this, we introduce **TIGER** (**T**ext-**I**mage **G**uided sup**E**r-**R**esolution), a novel two-stage frame

Cited by 0 Source ↗Scholar ↗

2025

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models

Yuchen Fan, Yuzhong Hong, Qiushi Wang, Junwei Bao, Hongfei Jiang, Yang Song

AAAI 2025technical

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling typically with a cross-entropy objective, requiring a large am…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗