Search papers, labs, and topics across Lattice.
University of Leicester
3
0
5
2
Forget external text corpora – this new method unlocks surprisingly effective sequential recommendations by cleverly routing and filtering token embeddings from multiple LLMs.
CubeGraph achieves superior RAG performance by unifying vector and spatial search, eliminating the overhead of fragmented sub-index invocations common in existing systems.
By disentangling shared account behavior in the frequency domain, DisenReason dynamically infers latent users, boosting recommendation accuracy by up to 12.56% compared to methods assuming a fixed number of users.
