US Patent Issued to Zoox on Jan. 27 for "Efficient relative position-aware attention for transformer-based machine-learned models" (California Inventor)

ALEXANDRIA, Va., Jan. 28 -- United States Patent no. 12,535,780, issued on Jan. 27, was assigned to Zoox Inc. (Foster City, Calif.).

"Efficient relative position-aware attention for transformer-based machine-learned models" was invented by Ethan Miller Pronovost (Redwood City, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A transformer-based machine-learned model may use relative positions between token embeddings to more accurately predict outputs. Example outputs may include an object detection, sensor data segmentation, object state prediction, and/or the like. Efficiently computing relative position-aware attention scores of the transformer-based machine-learned model may comprise utilizing fast ...