Jiajia Mi — accepted AI-conference papers

2026

An Asymmetric Latent Factorization-of-Tensors Model for Relation Extraction

Weiling Li, Zhaoheng Shi, Jiajia Mi, Zhigang Liu, Jialiang Wang, Xin Luo

ICML 2026poster

Latent Factorization-of-Tensors (LFT) models are an effective approach for relation extraction. Existing LFT models assume each mode of the target tensor corresponds to a entity set and the relationships between entity sets are bipartite graphs to explore the relationships among entities within a mo…

Cited by 0 Source ↗Scholar ↗

2026

Dual-Prototype-Guided Multi-task Learning for Unsupervised Anomaly Detection and Classification

Qianhao Luo, Jiajia Mi, Mingtao Yan, JingSheng Liu, ShuYang Pang, Weiling Li

CVPR 2026

Unsupervised Anomaly Detection (UAD) and anomaly classification are frequently used in industrial and medical scenarios. Specifically, UAD identifies anomalous regions at the fine-grained pixel-level, while anomaly classification distinguishes anomaly types at the anomaly region level. However, exis

Cited by 0 Source ↗code ↗Scholar ↗