Patents by Inventor Chen-Yu Lee

Chen-Yu Lee 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: 20250036886
    Abstract: Using a large language model to comply with a user request. The large language model receives tool documentation for each of one or more tools, and analyzes the tool documentation for each of the one or more tools to determine, for each tool, one or more tasks that the tool is operable to perform. Upon receiving a request from a user, the large language model generates a plan for complying with the request by using one or more of the tools, the plan including performance of one or more of the tasks.
    Type: Application
    Filed: July 9, 2024
    Publication date: January 30, 2025
    Inventors: Chen-Yu Lee, Alexander Ratner, Tomas Pfister, Chun-Liang Li, Yasuhisa Fujii, Ranjay Krishna, Cheng-Yu Hsieh, Si-An Chen
  • Publication number: 20240354504
    Abstract: Systems and methods for providing a structure-aware sequence model that can interpret a document's text without first inferring the proper reading order of the document. In some examples, the model may use a graph convolutional network to generate contextualized “supertoken” embeddings for each token, which are then fed to a transformer that employs a sparse attention paradigm in which attention weights for at least some supertokens are modified based on differences between predicted and actual values of the order and distance between the attender and attendee supertokens.
    Type: Application
    Filed: August 25, 2021
    Publication date: October 24, 2024
    Inventors: Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, Tomas Pfister
  • Publication number: 20240337012
    Abstract: Semiconductor processing apparatuses and methods are provided in which a pre-clean chamber receives a semiconductor wafer from a metal gate layer deposition chamber and at least partially removes an oxide layer on a metal gate layer. In some embodiments, a semiconductor processing apparatus includes a plurality of metal gate layer deposition chambers. Each of the metal gate layer deposition chambers is configured to form a metal gate layer on a semiconductor wafer. At least one pre-clean chamber of the apparatus is configured to receive the semiconductor wafer from one of the metal gate layer deposition chamber and at least partially remove an oxide layer on the metal gate layer.
    Type: Application
    Filed: June 18, 2024
    Publication date: October 10, 2024
    Inventors: Chen-Yu LEE, Yen-Yu CHEN
  • Patent number: 12054823
    Abstract: Semiconductor processing apparatuses and methods are provided in which a pre-clean chamber receives a semiconductor wafer from a metal gate layer deposition chamber and at least partially removes an oxide layer on a metal gate layer. In some embodiments, a semiconductor processing apparatus includes a plurality of metal gate layer deposition chambers. Each of the metal gate layer deposition chambers is configured to form a metal gate layer on a semiconductor wafer. At least one pre-clean chamber of the apparatus is configured to receive the semiconductor wafer from one of the metal gate layer deposition chamber and at least partially remove an oxide layer on the metal gate layer.
    Type: Grant
    Filed: March 3, 2021
    Date of Patent: August 6, 2024
    Assignee: Taiwan Semiconductor Manufacturing Co., Ltd.
    Inventors: Chen-Yu Lee, Yen-Yu Chen
  • Publication number: 20240153297
    Abstract: A method for extracting entities comprises obtaining a document that includes a series of textual fields that includes a plurality of entities. Each entity represents information associated with a predefined category. The method includes generating, using the document, a series of tokens representing the series of textual fields. The method includes generating an entity prompt that includes the series of tokens and one of the plurality of entities and generating a schema prompt that includes a schema associated with the document. The method includes generating a model query that includes the entity prompt and the schema prompt and determining, using an entity extraction model and the model query, a location of the one of the plurality of entities among the series of tokens. The method includes extracting, from the document, the one of the plurality of entities using the location of the one of the plurality of entities.
    Type: Application
    Filed: November 3, 2023
    Publication date: May 9, 2024
    Applicant: Google LLC
    Inventors: Zizhao Zhang, Zifeng Wang, Vincent Perot, Jacob Devlin, Chen-Yu Lee, Guolong Su, Hao Zhang, Tomas Jon Pfister
  • Patent number: 11853894
    Abstract: Methods and systems for meta-learning are described for automating learning of child tasks with a single neural network. The order in which tasks are learned by the neural network can affect performance of the network, and the meta-learning approach can use a task-level curriculum for multi-task training. The task-level curriculum can be learned by monitoring a trajectory of loss functions during training. The meta-learning approach can learn to adapt task loss balancing weights in the course of training to get improved performance on multiple tasks on real world datasets. Advantageously, learning to dynamically balance weights among different task losses can lead to superior performance over the use of static weights determined by expensive random searches or heuristics. Embodiments of the meta-learning approach can be used for computer vision tasks or natural language processing tasks, and the trained neural networks can be used by augmented or virtual reality devices.
    Type: Grant
    Filed: June 10, 2021
    Date of Patent: December 26, 2023
    Assignee: Magic Leap, Inc.
    Inventors: Andrew Rabinovich, Vijay Badrinarayanan, Srivignesh Rajendran, Chen-Yu Lee
  • Publication number: 20230394315
    Abstract: Systems and methods for estimating a layout of a room are disclosed. The room layout can comprise the location of a floor, one or more walls, and a ceiling. In one aspect, a neural network can analyze an image of a portion of a room to determine the room layout. The neural network can comprise a convolutional neural network having an encoder sub-network, a decoder sub-network, and a side sub-network. The neural network can determine a three-dimensional room layout using two-dimensional ordered keypoints associated with a room type. The room layout can be used in applications such as augmented or mixed reality, robotics, autonomous indoor navigation, etc.
    Type: Application
    Filed: August 23, 2023
    Publication date: December 7, 2023
    Inventors: Chen-Yu Lee, Vijay Badrinarayanan, Tomasz Jan Malisiewicz, Andrew Rabinovich
  • Patent number: 11793851
    Abstract: The present invention relates to a method for treating a side effect caused by bacillus Calmette-Guérin (BCG) perfusion therapy for bladder cancer. The method includes: administering a Chinese medicine composition to a subject in need thereof; wherein the Chinese medicine composition is an extract of a first mixture comprising Gentiana scabra, Scutellariae Radix, Gardeniae Fructus, Angelicae Sinensis Radix, Rehmanniae radix, Akebiae Caulis, Bupleurum chinense, Plantaginis Semen, Atractylodes lancea, Rhizoma alismatis, and Glycyrrhiza uralensis.
    Type: Grant
    Filed: September 3, 2020
    Date of Patent: October 24, 2023
    Inventor: Chen-Yu Lee
  • Patent number: 11783552
    Abstract: In one implementation, a method of including a person in a CGR experience or excluding the person from the CGR experience is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes, while presenting a CGR experience, capturing an image of scene; detecting, in the image of the scene, a person; and determining an identity of the person. The method includes determining, based on the identity of the person, whether to include the person in the CGR experience or exclude the person from the CGR experience. The method includes presenting the CGR experience based on the determination.
    Type: Grant
    Filed: December 21, 2021
    Date of Patent: October 10, 2023
    Assignee: APPLE INC.
    Inventors: Daniel Ulbricht, Amit Kumar K C, Angela Blechschmidt, Chen-Yu Lee, Eshan Verma, Mohammad Haris Baig, Tanmay Batra
  • Patent number: 11775835
    Abstract: Systems and methods for estimating a layout of a room are disclosed. The room layout can comprise the location of a floor, one or more walls, and a ceiling. In one aspect, a neural network can analyze an image of a portion of a room to determine the room layout. The neural network can comprise a convolutional neural network having an encoder sub-network, a decoder sub-network, and a side sub-network. The neural network can determine a three-dimensional room layout using two-dimensional ordered keypoints associated with a room type. The room layout can be used in applications such as augmented or mixed reality, robotics, autonomous indoor navigation, etc.
    Type: Grant
    Filed: April 9, 2020
    Date of Patent: October 3, 2023
    Assignee: MAGIC LEAP, INC.
    Inventors: Chen-Yu Lee, Vijay Badrinarayanan, Tomasz Jan Malisiewicz, Andrew Rabinovich
  • Publication number: 20230274143
    Abstract: A method for rehearsal-free continual learning includes obtaining a set of training samples where training sample in the set of training samples is associated with a respective task of a plurality of different tasks. The method includes obtaining a task-invariant prompt representative of learned knowledge common to each respective task of the plurality of different tasks. The method includes, for each respective task of the plurality of different tasks, obtaining a respective task-specific prompt representative of learned knowledge specific to the respective task. The method includes, during each of one or more training iterations, for each respective training sample in the set of training samples, selecting the respective task-specific prompt representative of the respective task of the respective training sample and training a model using the task-invariant prompt and the selected respective task-specific prompt.
    Type: Application
    Filed: February 24, 2023
    Publication date: August 31, 2023
    Applicant: Google LLC
    Inventors: Zizhao Zhang, Zifeng Wang, Chen-Yu Lee, Ruoxi Sun, Sayna Ebrahimi, Xiaoqi Ren, Guolong Su, Vincent Perot, Tomas Pfister, Han Zhang
  • Patent number: 11730787
    Abstract: The present invention relates to a method for treating HIV/AIDS complications including administering a first Chinese herbal medicine composition to a subject in need; wherein the first Chinese herbal medicine composition is an extract of a first mixture including Polygonatum sibiricum, Astragalus membranaceus, Panax ginseng, Liriope spicata, Schisandra chinensis, Ziziphus zizyphus, Cornus officinalis, Fallopia multiflora, and Salvia miltiorrhiza.
    Type: Grant
    Filed: November 8, 2021
    Date of Patent: August 22, 2023
    Inventors: Ying-Chieh Huang, Chen-Yu Lee
  • Patent number: 11710283
    Abstract: Various implementations disclosed herein include devices, systems, and methods that enable faster and more efficient real-time physical object recognition, information retrieval, and updating of a CGR environment. In some implementations, the CGR environment is provided at a first device based on a classification of the physical object, image or video data including the physical object is transmitted by the first device to a second device, and the CGR environment is updated by the first device based on a response associated with the physical object received from the second device.
    Type: Grant
    Filed: October 22, 2021
    Date of Patent: July 25, 2023
    Assignee: Apple Inc.
    Inventors: Eshan Verma, Daniel Ulbricht, Angela Blechschmidt, Mohammad Haris Baig, Chen-Yu Lee, Tanmay Batra
  • Publication number: 20230153980
    Abstract: A computer-implemented method includes receiving an anomaly clustering request that requests data processing hardware to assign each image of a plurality of images into one of a plurality of groups. The method also includes obtaining a plurality of images. For each respective image, the method includes extracting a respective set of patch embeddings from the respective image, determining a distance between the respective set of patch embeddings and each other set of patch embeddings, and assigning the respective image into one of the plurality of groups using the distances between the respective set of patch embeddings and each other set of patch embeddings.
    Type: Application
    Filed: November 10, 2022
    Publication date: May 18, 2023
    Applicant: Google LLC
    Inventors: Kihyuk Sohn, Jinsung Yoon, Chun-Liang Li, Tomas Jon Pfister, Chen-Yu Lee
  • Publication number: 20230141424
    Abstract: The present invention relates to a method for treating HIV/AIDS complications including administering a first Chinese herbal medicine composition to a subject in need; wherein the first Chinese herbal medicine composition is an extract of a first mixture including Polygonatum sibiricum, Astragalus membranaceus, Panax ginseng, Liriope spicata, Schisandra chinensis, Ziziphus zizyphus, Cornus officinalis, Fallopia multiflora, and Salvia miltiorrhiza.
    Type: Application
    Filed: November 8, 2021
    Publication date: May 11, 2023
    Inventors: Ying-Chieh HUANG, Chen-Yu LEE
  • Patent number: 11510953
    Abstract: The present invention relates to a method for treating T cell lymphomas. The method includes: administering a Chinese medicine composition to a subject in need thereof; wherein, the Chinese medicine composition is an extract of a first mixture comprising Ephedrae herba, Armeniacae semen amarum, Coicis semen, Glycyrrhiza uralensis, Gleditsiae spina, and Liquidambaris fructus.
    Type: Grant
    Filed: September 14, 2020
    Date of Patent: November 29, 2022
    Inventor: Chen-Yu Lee
  • Patent number: 11510958
    Abstract: The present invention relates to a method for treating psoriasis including: administering a Chinese medicine composition to a subject in need thereof; wherein the Chinese medicine composition is an extract of a first mixture including Pimenta officinalis, Paeonia veitchii, Anastatica hierochuntica, Zingiber officinale, Scutellaria baicalensis, and Ziziphus jujube.
    Type: Grant
    Filed: November 6, 2020
    Date of Patent: November 29, 2022
    Inventor: Chen-Yu Lee
  • Publication number: 20220143127
    Abstract: The present invention relates to a method for treating psoriasis including: administering a Chinese medicine composition to a subject in need thereof; wherein the Chinese medicine composition is an extract of a first mixture including Pimenta officinalis, Paeonia veitchii, Anastatica hierochuntica, Zingiber officinale, Scutellaria baicalensis, and Ziziphus jujube.
    Type: Application
    Filed: November 6, 2020
    Publication date: May 12, 2022
    Inventor: Chen-Yu LEE
  • Patent number: 11315278
    Abstract: In one implementation, a method of estimating the orientation of an object in an image is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes obtaining an image of a scene including a plurality of pixels at a respective plurality of pixel locations and having a respective plurality of pixel values. The method includes determining a first set of pixels locations corresponding to a 2D boundary surrounding an object represented in the image and determining, based on the first set of pixel locations, a second set of pixel locations corresponding to a 3D boundary surrounding the object.
    Type: Grant
    Filed: September 24, 2019
    Date of Patent: April 26, 2022
    Assignee: APPLE INC.
    Inventors: Daniel Ulbricht, Amit Kumar K C, Angela Blechschmidt, Chen-Yu Lee, Eshan Verma, Mohammad Haris Baig, Tanmay Batra
  • Publication number: 20220114796
    Abstract: In one implementation, a method of including a person in a CGR experience or excluding the person from the CGR experience is performed by a device including one or more processors, non-transitory memory, and a scene camera. The method includes, while presenting a CGR experience, capturing an image of scene; detecting, in the image of the scene, a person; and determining an identity of the person. The method includes determining, based on the identity of the person, whether to include the person in the CGR experience or exclude the person from the CGR experience. The method includes presenting the CGR experience based on the determination.
    Type: Application
    Filed: December 21, 2021
    Publication date: April 14, 2022
    Inventors: Daniel Ulbricht, Amit Kumar K C, Angela Blechschmidt, Chen-Yu Lee, Eshan Verma, Mohammad Haris Baig, Tanmay Batra