Search papers, labs, and topics across Lattice.
3
0
6
11
Robots can now predict not just immediate actions but also the next stages of complex tasks, leading to more efficient manipulation strategies.
Early trajectory decoding from video diffusion models can cut planning latency by nearly 50% without sacrificing decision quality.
Fine-grained evaluation reveals that current text-to-audio models fail to preserve speech content and control audio attributes effectively.
