Tian-Yi Che — accepted AI-conference papers

2025

Distribution-Consistency-Guided Multi-modal Hashing

Jin-Yu Liu, Xian-Ling Mao, Tian-Yi Che, Rong-Cheng Tu

AAAI 2025technical

Multi-modal hashing methods have gained popularity due to their fast speed and low storage requirements. Among them, the supervised methods demonstrate better performance by utilizing labels as supervisory signals compared with unsupervised methods. Currently, for almost all supervised multi-modal h…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

SQLWOZ: A Realistic Task-Oriented Dialogue Dataset with SQL-Based Dialogue State Representation for Complex User Requirements

Heng-Da Xu, Xian-Ling Mao, Fanshu Sun, Tian-Yi Che, Cheng-Xin Xin, Heyan Huang

EMNLP 2025

High-quality datasets are essential for building effective task-oriented dialogue (TOD) systems. The existing TOD datasets often present overly simplified interactions, where users incrementally express straightforward requests that can be managed with basic slot-value style dialogue states, such as

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗