Search papers, labs, and topics across Lattice.
5
0
8
7
G0.5 achieves unprecedented performance in robot reasoning and action by merging decision-making and execution into a single autoregressive framework, outperforming existing models across seven challenging benchmarks.
MADE transforms the labor-intensive process of model deployment into a streamlined, automated workflow, achieving a notable 68.85% success rate in making models ready-to-call APIs.
Robust multimodal few-shot knowledge graph completion is achievable even in data-scarce scenarios with the novel DuPLeR framework.
Ditch fixed compute budgets: this new flow-matching method for robotic control adaptively allocates computation, speeding up simple tasks and focusing on complex ones.
World Action Models can ditch the slow, iterative "imagine-then-execute" loop at test time without sacrificing performance, achieving a 4x speedup.
