Patents by Inventor Iaroslav Ganin

Iaroslav Ganin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20240119261
    Abstract: 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 generating, by using the diffusion model, a final latent representation of the sequence of discrete tokens that includes a determined value for each of a plurality of latent variables; applying a de-embedding matrix to the final latent representation of the output sequence of discrete tokens to generate a de-embedded final latent representation that includes, for each of the plurality of latent variables, a respective numeric score for each discrete token in a vocabulary of multiple discrete tokens; selecting, for each of the plurality of latent variables, a discrete token from among the multiple discrete tokens in the vocabulary that has a highest numeric score; and generating the output sequence of discrete tokens that includes the selected discrete tokens.
    Type: Application
    Filed: September 28, 2023
    Publication date: April 11, 2024
    Inventors: Robin Strudel, Rémi Leblond, Laurent Sifre, Sander Etienne Lea Dieleman, Nikolay Savinov, Will S. Grathwohl, Corentin Tallec, Florent Altché, Iaroslav Ganin, Arthur Mensch, Yilin Du
  • Publication number: 20230076437
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating data specifying a three-dimensional mesh of an object using an auto-regressive neural network.
    Type: Application
    Filed: February 8, 2021
    Publication date: March 9, 2023
    Inventors: Charlie Thomas Curtis Nash, Iaroslav Ganin, Seyed Mohammadali Eslami, Peter William Battaglia
  • Publication number: 20210271968
    Abstract: A generative adversarial neural network system to provide a sequence of actions for performing a task. The system comprises a reinforcement learning neural network subsystem coupled to a simulator and a discriminator neural network. The reinforcement learning neural network subsystem includes a policy recurrent neural network to, at each of a sequence of time steps, select one or more actions to be performed according to an action selection policy, each action comprising one or more control commands for a simulator. The simulator is configured to implement the control commands for the time steps to generate a simulator output. The discriminator neural network is configured to discriminate between the simulator output and training data, to provide a reward signal for the reinforcement learning. The simulator may be non-differentiable simulator, for example a computer program to produce an image or audio waveform or a program to control a robot or vehicle.
    Type: Application
    Filed: February 11, 2019
    Publication date: September 2, 2021
    Inventors: Iaroslav Ganin, Tejas Dattatraya Kulkarni, Oriol Vinyals, Seyed Mohammadali Eslami