MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202647124311 A) filed by Qualcomm Incorporated on October 16, 2026, for Sparse High Rank Adapters And Their Hardware-Software Co-Design.
Inventors include Bhardwaj, Kartikeya; Pandey, Nilesh Prasad; Priyadarshi, Sweta; Borse, Shubhankar Mangesh; Kadambi, Shreya; Esteves, Rafael Xavier; Ganapathy, Viswanath; Garrepalli, Risheek; Whatmough, Paul Nicholas; Van Baalen, Marinus Willem; and Nagel, Markus.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: A processor-implemented method includes receiving an artificial neural network having a number of pre-trained weights. The method also includes training a subset of the number of pre-trained weights to obtain trained sparse adapter weights for obtaining a fine-tuned version of the artificial neural network. The subset of the number of pre-trained weights includes base model weights of a base model for the artificial neural network. The subset of the number of pre-trained weights is selected with a sparse mask of a sparse adapter. The method may also include replacing the subset of the number of pre-trained weights with the trained sparse adapter weights.
Disclaimer: Curated by HT Syndication.
