Yu Cheng

User interest modeling is foundational to recommender systems. However, sparse and noisy behaviors make traditional item-level sequence models brittle, especially for new and low-activity users. Furthermore, relying solely on a user's own history limits exploration and reinforces the ''filter bub...

Semantic IDs derived from Multi-modal Large Language Models (MLLMs) integrate rich content semantics into recommendation systems but often lack the collaborative signals crucial for capturing user behavior. Additionally, static generation fails to adapt to evolving data distributions, causing cod...