Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
5
The GameHorizon Suite, a unified data and evaluation suite that measures gameplay capabilities at different horizons for diverse model families, can provide a standardized yardstick for evaluating gameplay capabilities across horizons and model families.
Current multimodal agents are nowhere near human-level gaming, even when given precise semantic actions, revealing critical gaps in real-time interaction and context handling.
