Work / Research
Research projects
Research on recommender systems, multimodal and sequential learning, learning objectives, and fair representation learning. Each page collects the problem, method, findings, paper, and citation details for the corresponding project.
2026 Published
DAP - Differential Adjusted Parity
A differentiable adjusted parity loss for learning fair representations without adversarial training.
2026 Preprint
MuSTRec
A multimodal and sequential transformer-based recommender that models item structure alongside short- and long-term user preferences.
2026 Preprint
MuSICRec
A contrastive graph recommender using sequence-item views and ID-guided multimodal fusion to address sparse interaction histories.
2026 Preprint
DSL - Dual-scale Softmax Loss
A softmax loss that adapts competition within and across training instances to improve Top-K recommendation and robustness.