Search papers, labs, and topics across Lattice.
3
0
5
KNOWSIM uncovers that LLM performance is not uniform and shifts dramatically based on user knowledge levels, challenging traditional evaluation methods.
Routing changes in MoE models may not influence behavior as expected, with the routing term contributing less than half of the natural context effect.
Designers prefer delegating 70% of the time to co-creative AI agents, but only if the agent can interpret collaborative intent and adapt in real-time to concurrent user actions.
