Search papers, labs, and topics across Lattice.
3
0
6
PearlVLA achieves state-of-the-art performance in action generation by refining plans in latent space, enabling low-latency execution without sacrificing deliberation quality.
MPCoT achieves long-horizon VLA performance gains without increasing token latency, revolutionizing how we approach inference in complex control tasks.
By explicitly structuring and managing retrieval state, EfficientGraph-RAG achieves state-of-the-art RAG performance while slashing large-model token usage by over 3x.
