Patents by Inventor Arun Mallya

Arun Mallya 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: 20250111222
    Abstract: Performance of a neural network is usually a function of the capacity, or complexity, of the neural network, including the depth of the neural network (i.e. the number of layers in the neural network) and/or the width of the neural network (i.e. the number of hidden channels). However, improving performance of a neural network by simply increasing its capacity has drawbacks, the most notable being the increased computational cost of a higher-capacity neural network. Since modern neural networks are configured such that the same neural network is evaluated regardless of the input, a higher capacity neural network means a higher computational cost incurred per input processed. The present disclosure provides for a multi-layer neural network that allows for dynamic path selection through the neural network when processing an input, which in turn can allow for increased neural network capacity without incurring the typical increased computation cost associated therewith.
    Type: Application
    Filed: September 29, 2023
    Publication date: April 3, 2025
    Inventors: Zekun Hao, Ming-Yu Liu, Arun Mallya
  • Publication number: 20240397077
    Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.
    Type: Application
    Filed: July 22, 2024
    Publication date: November 28, 2024
    Inventors: Aurobinda Maharana, Arun Mallya, Ming-Yu Liu, Abhijit Patait
  • Patent number: 12047595
    Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.
    Type: Grant
    Filed: September 29, 2022
    Date of Patent: July 23, 2024
    Assignee: Nvidia Corporation
    Inventors: Aurobinda Maharana, Arun Mallya, Ming-Yu Liu, Abhijit Patait
  • Publication number: 20240144568
    Abstract: Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate video information based at least in part upon voice information and a combination of image features and facial landmarks corresponding to one or more images of a person.
    Type: Application
    Filed: September 6, 2022
    Publication date: May 2, 2024
    Inventors: Siddharth Gururani, Arun Mallya, Ting-Chun Wang, Jose Rafael Valle da Costa, Ming-Yu Liu
  • Publication number: 20240114162
    Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.
    Type: Application
    Filed: September 29, 2022
    Publication date: April 4, 2024
    Inventors: Aurobinda Maharana, Arun Mallya, Ming-Yu Liu, Abhijit Patait
  • Patent number: 11934959
    Abstract: Apparatuses, systems, and techniques are presented to synthesize consistent images or video. In at least one embodiment, one or more neural networks are used to generate one or more second images based, at least in part, on one or more point cloud representations of one or more first images.
    Type: Grant
    Filed: June 1, 2020
    Date of Patent: March 19, 2024
    Assignee: NVIDIA CORPORATION
    Inventors: Arun Mallya, Ting-Chun Wang, Ming-Yu Liu, Karan Sapra
  • Publication number: 20230186077
    Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes computing a first set of halting scores for a first set of tokens that has been input into a first layer of the transformer neural network. The technique also includes determining that a first halting score included in the first set of halting scores exceeds a threshold value. The technique further includes in response to the first halting score exceeding the threshold value, causing a first token that is included in the first set of tokens and is associated with the first halting score not to be processed by one or more layers within the transformer neural network that are subsequent to the first layer.
    Type: Application
    Filed: June 15, 2022
    Publication date: June 15, 2023
    Inventors: Hongxu YIN, Jan KAUTZ, Jose Manuel ALVAREZ LOPEZ, Arun MALLYA, Pavlo MOLCHANOV, Arash VAHDAT
  • Publication number: 20230045076
    Abstract: Apparatuses, systems, and techniques are presented to generate one or more images. In at least one embodiment, one or more neural networks are used to generate one or more images based, at least in part, upon one or more input types.
    Type: Application
    Filed: July 29, 2021
    Publication date: February 9, 2023
    Inventors: Xun Huang, Arun Mallya, Ting Wang, Ming-Yu Liu
  • Publication number: 20230035306
    Abstract: Apparatuses, systems, and techniques are presented to generate media content.
    Type: Application
    Filed: July 21, 2021
    Publication date: February 2, 2023
    Inventors: Ming-Yu Liu, Koki Nagano, Yeongho Seol, Jose Rafael Valle Gomes da Costa, Jaewoo Seo, Ting-Chun Wang, Arun Mallya, Sameh Khamis, Wei Ping, Rohan Badlani, Kevin Jonathan Shih, Bryan Catanzaro, Simon Yuen, Jan Kautz
  • Publication number: 20220374637
    Abstract: Apparatuses, systems, and techniques are presented to reduce an amount of data to be transmitted for media content. In at least one embodiment, one or more neural networks are used to generate video and audio information corresponding to one or more people based, at least in part, on at least one image and voice information corresponding to the one or more people.
    Type: Application
    Filed: May 20, 2021
    Publication date: November 24, 2022
    Inventors: Ming-Yu LIU, Ting-Chun WANG, Arun MALLYA
  • Publication number: 20220284232
    Abstract: Apparatuses, systems, and techniques to identify one or more images used to train one or more neural networks. In at least one embodiment, one or more images used to train one or more neural networks are identified, based on, for example, one or more labels of one or more objects within the one or more images.
    Type: Application
    Filed: March 1, 2021
    Publication date: September 8, 2022
    Inventors: Hongxu Yin, Arun Mallya, Arash Vahdat, Jose Manuel Alvarez Lopez, Jan Kautz, Pavlo Molchanov
  • Publication number: 20210374552
    Abstract: Apparatuses, systems, and techniques are presented to synthesize consistent images or video. In at least one embodiment, one or more neural networks are used to generate one or more second images based, at least in part, on one or more point cloud representations of one or more first images.
    Type: Application
    Filed: June 1, 2020
    Publication date: December 2, 2021
    Inventors: Arun Mallya, Ting-Chun Wang, Ming-Yu Liu, Karan Spara
  • Publication number: 20210142177
    Abstract: Apparatuses, systems, and techniques are presented to generate data useful for further training of a neural network. In at least one embodiment, one or more neural networks can be re-trained based, at least in part, on data generated by the one or more neural networks including data used to previously train the one or more neural networks.
    Type: Application
    Filed: November 13, 2019
    Publication date: May 13, 2021
    Inventors: Arun Mallya, Jan Kautz, Zhizhong Li, Pavlo Molchanov, Hongxu Danny Yin