MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202617080058 A) filed by Gdm Holding LLC on June 29, 2026, for Computer Code Generation From Task Descriptions Using Neural Networks.
Inventors include Leblond, Rmi; Saade, Alaa; Tallec, Corentin; Gimeno Gil, Felix Axel; Altch, Florent; Grill, Jean-Bastien Franois Laurent; Lochbrunner, Matthias Heinz; Caron, Paul; Ruddock, Anton; Powell, George; Mathieu, Michael Fabien Serge; and Mikula, Maciej.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating computer code using neural networks. One of the methods includes receiving description data describing a computer programming task; generating a plurality of candidate computer programs by sampling a plurality of output sequences from a set of one or more generative neural networks; clustering the plurality of candidate computer programs to generate a plurality of clusters; for each cluster in a set of one or more of the clusters: processing each of the respective plurality of candidate computer programs in the cluster using a correctness estimation neural network to generate a correctness score for the candidate computer program that estimates a likelihood that the candidate computer program accurately performs the computer programming task; and selecting a representative computer program for the cluster using the correctness scores for the respective plurality of candidate computer programs in the cluster; and selecting one or more of the representative computer programs for the clusters as synthesized computer programs for performing the computer programming task.
Disclaimer: Curated by HT Syndication.
