Search papers, labs, and topics across Lattice.
University of Oslo
2
0
5
E2LLM cuts average waiting time by over 50% in high-demand scenarios by intelligently partitioning LLMs across heterogeneous devices.
Autonomous vehicles can drive more safely and reliably by grounding LLM reasoning in a "Commonsense World" that quantifies and leverages the trustworthiness of LLM outputs.
