Peiyuan Li — accepted AI-conference papers

2026

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Peiyuan Li, Yongqi Huang, Jitao Zhao, Dongxiao He, Di Jin, Weixiong Zhang

IJCAI 2026

Heterogeneous Graph Prompt Learning (HGPL) has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenario

Cited by 0 Scholar ↗

2026

VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer

Yanning Hou, Peiyuan Li, Zirui Liu, Yitong Wang, Yanran Ruan, Jianfeng Qiu +1

CVPR 2026

Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-t

Cited by 0 Source ↗code ↗Scholar ↗