Search papers, labs, and topics across Lattice.
2
0
4
Ditching caches for compiler-managed data streams, Li Auto's M100 architecture achieves higher utilization than GPUs on autonomous driving tasks, hinting at a new path for efficient AI inference.
Forget intractable quantum linear algebra: this distributed algorithm and circuit compression technique slashes circuit complexity by 256x while preserving solution fidelity, opening the door to practical quantum advantage on near-term hardware.
