MUMBAI, India, June 13 -- Intellectual Property India has published a patent application (202517039408 A) filed by Deepmind Technologies Limited, London, on April 24, for 'score interpolation diffusion models.'
Inventor(s) include Dieleman, Sander Etienne Lea; Sartran, Laurent Patrice Marc; Savinov, Nikolay; Ganin, Iaroslav; Richemond, Pierre; Doucet, Arnaud; Dyer, Christopher James; Durkan, Conor Michael; Leblond, Remi; Grathwohl, Will S.; Strudel, Robin; and Hawthorne, Curtis Glenn-Macway.
The application for the patent was published on June 13, under issue no. 24/2025.
According to the abstract released by the Intellectual Property India: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of discrete tokens using a diffusion model. In one aspect, a method includes initializing the output sequence by assigning a respective embedding to each of the plurality of output positions; repeatedly performing the following at each of multiple reverse diffusion steps: a current continuous representation of the output sequence; processing a diffusion model input that comprises the current continuous representation using the diffusion model to generate a diffusion model output; processing the respective initial scores using a softmax function to generate, for each of the plurality of output positions, a probability distribution over the plurality of embeddings in the vocabulary of embeddings; and updating the continuous representation of the output sequence using the probability distributions and the vocabulary of embeddings."
The patent application was internationally filed on Nov. 23, 2023, under International application No.PCT/EP2023/082883.
Disclaimer: Curated by HT Syndication.
