Search papers, labs, and topics across Lattice.
The University of Hong Kong
4
0
7
Forget static user profiles – LATTE forecasts where a user's preferences are *going*, not just where they've been, boosting personalized LLM generation.
Today's best AI agents can only solve 55% of real-world academic tasks that university students find challenging, revealing a significant gap between current AI capabilities and the demands of academic workflows.
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.
