Search papers, labs, and topics across Lattice.
4
0
6
8
ServerlessT2I can double the request rates of text-to-image workflows while slashing GPU resource consumption by up to three times.
Xema achieves a staggering 3.7x improvement in service level objectives for diffusion models while slashing planning time from hours to mere minutes.
Origami tentacles that deterministically coil and stochastically entangle offer a surprisingly simple and robust solution for universal robotic gripping.
Stop treating diffusion workflows as monolithic black boxes: LegoDiffusion unlocks 3x higher throughput by decomposing them into independently scalable microservices.
