Search papers, labs, and topics across Lattice.
3
0
7
Most social LLMs fail to achieve verifiable success in coordination tasks, even when rated highly by conversational judges.
SAGE reveals that a multi-agent, evidence-grounded approach can outperform larger models in understanding Chinese ancient documents, challenging the notion that size alone drives performance.
IterCAD achieves a remarkable improvement in CAD code quality by enabling iterative refinement, correcting errors that traditional one-shot methods overlook.