Jincheng Liao — accepted AI-conference papers

2026

CompBench: Benchmarking Complex Instruction-guided Image Editing

Bohan Jia, Wenxuan Huang, Yuntian Tang, Junbo Qiao, Jincheng Liao, Shaosheng Cao +10

CVPR 2026

While real-world applications increasingly demand intricate scene manipulation, existing instruction-guided image editing benchmarks often oversimplify task complexity and lack comprehensive, fine-grained instructions. To bridge this gap, we introduce CompBench, a large-scale benchmark specifically

Cited by 0 Source ↗code ↗Scholar ↗

2025

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

Yunshuai Zhou, Junbo Qiao, Jincheng Liao, Wei Li, Simiao Li, Jiao Xie +3

AAAI 2025technical

Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗