Patents by Inventor Ye Yuan

Ye Yuan 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: 20250239036
    Abstract: Apparatuses, systems, and techniques to generate 3D models. In at least one embodiment, a 3D model, generated by a second neural network, is refined by a first neural network. In at least one embodiment, the first neural network is adjusted based on a determination made by the first neural network.
    Type: Application
    Filed: January 22, 2024
    Publication date: July 24, 2025
    Inventors: Ye Yuan, Umar Iqbal, Jiaming Song, Arash Vahdat, Jan Kautz
  • Publication number: 20250232504
    Abstract: In various examples, systems and methods are disclosed relating to receive at least one of a text prompt or a kinematic constraint and determine first human motion data using a motion model by applying the at least one of the text prompt or the kinematic constraint to the motion model. The motion model is updated by generating, using the motion model, second human motion data by applying motion capture (mocap) data and video reconstruction data as inputs to the motion model, receiving user feedback information for the second human motion data, and updating the motion model based on the user feedback information. The video reconstruction data is generated by reconstructing human motions from a plurality of videos. Physically implausible artifacts are filtered from the video reconstruction data using a motion imitation controller. The motion imitation controller is updated using at least one of Reinforced Learning (RL) or physics-based character simulations.
    Type: Application
    Filed: January 16, 2024
    Publication date: July 17, 2025
    Applicant: NVIDIA Corporation
    Inventors: Jason PENG, Ye YUAN, Davis Winston REMPE, Umar IQBAL, Or LITANY, Tingwu WANG, Chen TESSLER, Jan KAUTZ, Sanja FIDLER, Michael BUTTNER
  • Publication number: 20250232505
    Abstract: Systems and methods are disclosed relating to receiving at least one of a text prompt or a kinematic constraint, generating, by a motion model including a first model and a second model, human motion data of a human character by applying a random noise and the at least one of the text prompt or the kinematic constraint into the motion model. Generating the human motion data includes, for each iteration of diffusion determining, using the first model, global root motion by applying noisy global root motion and noisy local joint motion as inputs into the first model and determining, using the second model, local joint motion by applying the noisy local joint motion and local root motion as inputs into the second model. The local root motion is determined based on the global root motion. The human motion data includes the local joint motion and the global root motion.
    Type: Application
    Filed: January 16, 2024
    Publication date: July 17, 2025
    Applicant: NVIDIA Corporation
    Inventors: Jason PENG, Ye YUAN, Davis Winston REMPE, Umar IQBAL, Or LITANY, Tingwu WANG, Chen TESSLER, Jan KAUTZ, Sanja FIDLER, Michael BUTTNER
  • Patent number: 12346778
    Abstract: The disclosure discloses an AI-based condition classification system for patients with novel coronavirus, which includes: a classification model acquisition module for training one or more binary classification models that classify patient conditions according to patient data, and obtain the most accurate binary classification model as the target model, and determine the interpretable features in the patient data; a preprocessing module is configured to extract the interpretable features in the patient data to be classified, and then perform preprocessing on the extracted features to fill in the missing values and replace the abnormal values in the data, so as to obtain the features to be classified after the preprocessing is completed; a condition classification module is configured to use the features to be classified as the input for the target model, and the target model is used to complete condition classification for the patients to be classified.
    Type: Grant
    Filed: July 29, 2020
    Date of Patent: July 1, 2025
    Assignee: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Ye Yuan, Chuan Sun, Li Yan, Hui Xu, Maolin Wang, Yuqi Guo, Xiuchuan Tang, Haitao Zhang, Yang Xiao
  • Publication number: 20250111592
    Abstract: Virtual reality and augmented reality bring increasing demand for 3D content creation. In an effort to automate the generation of 3D content, artificial intelligence-based processes have been developed. However, these processes are limited in terms of the quality of their output because they typically involve a model trained on limited 3D data thereby resulting in a model that does not generalize well to unseen objects, or a model trained on 2D data thereby resulting in a model that suffers from poor geometry due to ignorance of 3D information. The present disclosure jointly uses both 2D and 3D data to train a machine learning model to be able to generate 3D content from a single 2D image.
    Type: Application
    Filed: September 20, 2024
    Publication date: April 3, 2025
    Inventors: Dejia Xu, Morteza Mardani, Jiaming Song, Sifei Liu, Ye Yuan, Arash Vahdat
  • Patent number: 12258651
    Abstract: A method for extracting germanium based on acid decomposition is provided, including acid decomposition and post-treatment steps, and specifically including: adding an acid to a coal ash for conditioning to obtain a material a; heating the material a to 350° C. to 800° C., and keeping the material a at this temperature for 10 min to 10 h to obtain an acid-decomposed material b; milling the acid-decomposed material b until more than 60% of a milled material has a particle size of less than 200 mesh to obtain a material c; subjecting the material c to distillation to obtain a residual slurry d and a distillation fraction e; and hydrolyzing the distillation fraction e with a dilute hydrochloric acid solution, and then oven-drying to obtain GeO2.
    Type: Grant
    Filed: September 27, 2024
    Date of Patent: March 25, 2025
    Assignee: KUNMING METALLURGICAL RESEARCH INSTITUTE CO., LTD.
    Inventors: Xiaocai He, Huixian Shi, Jiuyang Ren, Na Xu, Ye Yuan, Qingxin Xu, Yina Li, Qiugu He, Ting Ren, Yuan Xu, Weizhi Diao, Sen Yan, Hui Zhang
  • Publication number: 20250019795
    Abstract: A method for extracting germanium based on acid decomposition is provided, including acid decomposition and post-treatment steps, and specifically including: adding an acid to a coal ash for conditioning to obtain a material a; heating the material a to 350° C. to 800° C., and keeping the material a at this temperature for 10 min to 10 h to obtain an acid-decomposed material b; milling the acid-decomposed material b until more than 60% of a milled material has a particle size of less than 200 mesh to obtain a material c; subjecting the material c to distillation to obtain a residual slurry d and a distillation fraction e; and hydrolyzing the distillation fraction e with a dilute hydrochloric acid solution, and then oven-drying to obtain GeO2.
    Type: Application
    Filed: September 27, 2024
    Publication date: January 16, 2025
    Applicant: KUNMING METALLURGICAL RESEARCH INSTITUTE CO., LTD.
    Inventors: Xiaocai HE, Huixian SHI, Jiuyang REN, Na XU, Ye YUAN, Qingxin XU, Yina LI, Qiugu HE, Ting REN, Yuan XU, Weizhi DIAO, Sen YAN, Hui ZHANG
  • Publication number: 20250008479
    Abstract: Provided are an action execution method and apparatus, a distance determination method and apparatus, a device, and a storage medium, relating to the technical field of wireless communications. The action execution method is applied to a transmitting device. The action execution method includes: determining transmitting power of each target channel according to a signal distance range of each target channel; transmitting a broadcast signal on the basis of the transmitting power of each target channel; establishing a communication connection to a receiving device in response to a communication request of the receiving device; sending the signal distance range of each target channel to the receiving device; and executing a response action according to a received signal distance range at which the receiving device is currently located.
    Type: Application
    Filed: January 31, 2024
    Publication date: January 2, 2025
    Applicant: Chongqing Changan Automobile Co Ltd
    Inventors: Bin YANG, Liang SUN, Ye YUAN, Xiansheng QU, Tengyu YANG
  • Publication number: 20240419311
    Abstract: The present application provides a method and system, a device, and a medium. The method for information processing includes: obtaining an information processing state, wherein the information processing state is used for characterizing a processing state for target information, and the target information is generated according to input information on a dialogue page of a digital assistant; determining, according to the information processing state, display content matched with the information processing state; and displaying, on the dialogue page of the digital assistant, the display content matched with the information processing state. The method reduces the interaction complexity of users in a human-computer dialogue process and improve the operation experience of users.
    Type: Application
    Filed: August 29, 2024
    Publication date: December 19, 2024
    Inventors: Yizhe Yang, Jiahe Ma, Quan Chen, Ang Zhang, Chong Niu, Zhenghua Hao, Yong Li, Eryou Hao, Penglin Li, Ye Yuan
  • Patent number: 12166607
    Abstract: A digital isolator can include: an encoding circuit configured to receive and encode an input digital signal, in order to generate an encoded signal, wherein a rising edge of the input digital signal is encoded as a first pulse sequence, and a falling edge of the input digital signal is encoded as a second pulse sequence; an isolation element coupled to the encoding circuit, and being configured to transmit the encoded signal in an electrically isolated manner; and a decoding circuit configured to receive the encoded signal through the isolation element, and to decode the encoded signal, in order to generate an output digital signal consistent with the input digital signal.
    Type: Grant
    Filed: January 13, 2023
    Date of Patent: December 10, 2024
    Assignee: Silergy Semiconductor Technology (Hangzhou) LTD
    Inventors: Yufei Dong, Xiaodong Huang, Ye Yuan, Chen Zhao
  • Publication number: 20240402710
    Abstract: Systems and methods for evaluating and deploying fleets of autonomous in operational domains are described. A computing system may obtain data indicative of one or more capabilities of at least one autonomous vehicle, data indicative of vehicle service dynamics in an operational domain over a period of time, and determining a plurality of resource performance parameters respectively for a plurality of autonomous vehicle fleets associated with potential deployment in the operational domain. Each autonomous vehicle fleet can be associated with a different number of autonomous vehicles The resource performance parameter for each autonomous vehicle fleet can be based at least in part on the one or more capabilities of the at least one autonomous vehicle and the vehicle service dynamics in the operational domain. The computing system can initiate an action associated with the operational domain based at least in part on the plurality of resource performance parameters.
    Type: Application
    Filed: August 8, 2024
    Publication date: December 5, 2024
    Inventors: Valerie Nina Chadha, Ye Yuan, Neil Stegall, Brent Justin Goldman, Kane Sweeney, Rei Chiang
  • Patent number: 12153789
    Abstract: Video-based interaction and video processing methods, an apparatus, a device, and a storage medium are provided. The video-based interaction method includes: in response to a target video being played back to a target image frame, displaying a mask comprising an interactive control on a video playback interface corresponding to the target image frame, the position of the display area of the interactive control on the mask having a correspondence with the display area of a target element on the target image frame, and the display image on the interactive control having a correspondence with the target element. When a trigger operation for the interactive control is received, a target page is displayed.
    Type: Grant
    Filed: December 28, 2022
    Date of Patent: November 26, 2024
    Assignees: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD., BEIJING YOUZHUJU NETWORK TECHNOLOGY CO. LTD.
    Inventors: Ye Yuan, Pengfei Ji, Yuchen Wang, Zhaoyiding Mai, Jiayi Shi, Ting Nie, Jingyu Zhang
  • Publication number: 20240357498
    Abstract: This disclosure describes a power save mechanism for devices in a neighbor awareness networking (NAN) network. In some aspects, a NAN device is able to enter into a power save mode during a window agreed to between the NAN device and a NAN peer device. A NAN device transmits, to a NAN peer device, an indication that the wireless communication device is to enter a power save mode. For example, the NAN device may transmit a MAC packet with a more data (MD) bit set to 0. The NAN peer device may indicate that the NAN device is allowed to enter the power save mode by transmitting a MAC packet with the MD bit set to 0, or the NAN peer device may indicate that the wireless communication device is not to enter the power save mode by transmitting a MAC packet with the MD bit set to 1.
    Type: Application
    Filed: September 28, 2022
    Publication date: October 24, 2024
    Inventors: Shivraj Singh SANDHU, Sudhanshu SINGH, Alireza RAISSINIA, Sandip HOMCHAUDHURI, Sheshu Kumar TULA, Ye YUAN
  • Publication number: 20240346770
    Abstract: A method for simulating a solid body animation of a subject includes retrieving a first frame that includes a body image of a subject. The method also includes selecting, from the first frame, multiple key points within the body image of the subject that define a hull of a body part and multiple joint points that define a joint between two body parts, identifying a geometry, a speed, and a mass of the body part to include in a dynamic model of the subject, based on the key points and the joint points, determining, based on the dynamic model of the subject, a pose of the subject in a second frame after the first frame in a video stream, and providing the video stream to an immersive reality application running on a client device.
    Type: Application
    Filed: June 13, 2024
    Publication date: October 17, 2024
    Inventors: Jason Saragih, Shih-En Wei, Tomas Simon Kreuz, Kris Makoto Kitani, Ye Yuan
  • Publication number: 20240348846
    Abstract: A video generating method includes acquiring video materials from an initial collection which comprises user-related videos, acquiring a target audio material serving as background music, performing image feature extraction on video frames of each video material, and performing segmentation processing according to image feature information corresponding to each video frame to acquire a target video segment corresponding to the video material, and merging the target video segment and the corresponding target audio material to generate a target video. The target video includes video segments which are obtained based on the target video segments respectively, the video segments in the target video are played in order of post time, and time lengths of the video segments are matched with time lengths of corresponding musical phrases in the target audio material.
    Type: Application
    Filed: June 27, 2024
    Publication date: October 17, 2024
    Inventors: Yufan XUE, Jie HE, Ye YUAN, Xiaojie LI, Yue GAO
  • Patent number: 12100113
    Abstract: In order to determine accurate three-dimensional (3D) models for objects within a video, the objects are first identified and tracked within the video, and a pose and shape are estimated for these tracked objects. A translation and global orientation are removed from the tracked objects to determine local motion for the objects, and motion infilling is performed to fill in any missing portions for the object within the video. A global trajectory is then determined for the objects within the video, and the infilled motion and global trajectory are then used to determine infilled global motion for the object within the video. This enables the accurate depiction of each object as a 3D pose sequence for that model that accounts for occlusions and global factors within the video.
    Type: Grant
    Filed: January 25, 2022
    Date of Patent: September 24, 2024
    Assignee: NVIDIA CORPORATION
    Inventors: Ye Yuan, Umar Iqbal, Pavlo Molchanov, Jan Kautz
  • Patent number: 12085957
    Abstract: Systems and methods for evaluating and deploying fleets of autonomous in operational domains are described. A computing system may obtain data indicative of one or more capabilities of at least one autonomous vehicle, data indicative of vehicle service dynamics in an operational domain over a period of time, and determining a plurality of resource performance parameters respectively for a plurality of autonomous vehicle fleets associated with potential deployment in the operational domain. Each autonomous vehicle fleet can be associated with a different number of autonomous vehicles The resource performance parameter for each autonomous vehicle fleet can be based at least in part on the one or more capabilities of the at least one autonomous vehicle and the vehicle service dynamics in the operational domain. The computing system can initiate an action associated with the operational domain based at least in part on the plurality of resource performance parameters.
    Type: Grant
    Filed: November 17, 2022
    Date of Patent: September 10, 2024
    Assignee: Uber Technologies, Inc.
    Inventors: Valerie Nina Chadha, Ye Yuan, Neil Stegall, Brent Justin Goldman, Kane Sweeney, Rei Chiang
  • Patent number: D1047886
    Type: Grant
    Filed: August 22, 2023
    Date of Patent: October 22, 2024
    Inventors: Ye Yuan, Jia Li, Zequn Yu, Songlin Yang, Yue Ma
  • Patent number: D1057658
    Type: Grant
    Filed: August 22, 2023
    Date of Patent: January 14, 2025
    Inventors: Ye Yuan, Jia Li, Zequn Yu, Songlin Yang, Yue Ma
  • Patent number: D1057662
    Type: Grant
    Filed: August 22, 2023
    Date of Patent: January 14, 2025
    Inventors: Ye Yuan, Jia Li, Zequn Yu, Songlin Yang, Yue Ma