Search papers, labs, and topics across Lattice.
4
0
7
Forget complex memory architectures: simple retrieval and generation, when carefully tuned for signal density, can outperform sophisticated methods in conversational agents.
Time series foundation models in federated learning can be significantly improved by representing data as discrete prototypical memories, rather than relying on continuous latent spaces.
Urban data from over 100 cities can be unified into a single foundation model that generalizes zero-shot to new cities and tasks.
Forget wrestling with complex time series queries: Sonar-TS lets you ask in plain English and then uses generated Python code to pinpoint the answer.
