MUMBAI, India, June 19 -- Intellectual Property India has published a patent application (202617055242 A) filed by Gdm Holding LLC on April 30, 2026, for Synthetic Data Generation For Training Visual Language Models.
Inventors include Kaplanis, Christos; Mitrovic, Jovana; Erdogan, Goker; Bauer, Matthias Stephan; and Blundell, Charles.
The application for the patent was published on June 05, 2026, under issue no. 23/2026.
Abstract: A method is proposed for generating a visual language model (VLM) neural network trained to perform a multi-modal task on an input dataset comprising an input image to generate a token output which is a text response to the input dataset. The VLM is trained using a training database comprising tuples of sample input datasets and corresponding sample token outputs. The sample input dataset of some of the tuples comprises an image generated from a text description by a text-to-image model, and the corresponding sample token output comprises at least part of the text description.
Disclaimer: Curated by HT Syndication.
