Search papers, labs, and topics across Lattice.
The University of Hong Kong
6
0
8
12
A single high-quality item-item graph can significantly boost multimodal recommendation performance, especially in challenging cold-start situations.
Forget static user profiles – LATTE forecasts where a user's preferences are *going*, not just where they've been, boosting personalized LLM generation.
LLM agents can now remember far more, far more accurately, by "seeing" their past experiences instead of just reading about them.
Dramatically improve multimodal recommendation accuracy without any training by initializing user embeddings with item modality features and user cluster information.
LLM agents can be made more reliable by structurally verifying their internal reasoning, rather than relying on consensus which conflates agreement with faithfulness.
Forget static fusion: CAMMSR adaptively weights multimodal signals in sequential recommendations based on item category and user preferences, unlocking synergistic effects between modalities.
