Leqi Zhang — accepted AI-conference papers

2026

Breaking Down Market Barriers: Distilled Prompt-Tuning Approach for Cross-Market Recommendation

Leqi Zhang, Wayne Lu, Haiyang Zhang, Elliott Wen, Zhixuan Liang, Jia Wang

AAAI 2026technical

Cross-market recommendation (CMR) faces severe challenges from distribution shifts between data-rich source markets and sparse target markets. Existing methods rely on a pre-training and fine-tuning paradigm for knowledge transfer, yet suffer from two key limitations: i) the objective gap between pr

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

PU-BENCH: A UNIFIED BENCHMARK FOR RIGOROUS AND REPRODUCIBLE PU LEARNING

Qiuyi Chen, Haiyang Zhang, Leqi Zhang, Changchun Li, Jia Wang, Wei Wang

ICLR 2026poster

Positive-Unlabeled (PU) learning, a challenging paradigm for training binary classifiers from only positive and unlabeled samples, is fundamental to many applications. While numerous PU learning methods have been proposed, the research is systematically hindered by the lack of a standardized and com…

Cited by 0 Source ↗code ↗Scholar ↗