Search papers, labs, and topics across Lattice.
Affiliation:
3
7
6
18
Personal LLM agents can significantly improve recommendation quality by mediating platform rankings with cross-platform history, but naive mediation introduces substantial harmful overrides.
Stop hand-crafting hints for RL agents: HiLL learns to generate adaptive hints that actually improve the agent's performance on the original task, not just the hinted one.
Synthetic data from non-conversational signals can outperform real dialogue in low-resource Conversational Recommender Systems, transforming how we approach data scarcity.
