公开(公告)号：US20200213378A1

公开(公告)日：2020-07-02

申请号：US16811820

申请日：2020-03-06

Applicant: GOOGLE LLC

Inventor： Chuo-Ling Chang ,  Ping-Hao Wu

IPC: H04L29/06 ,  H04L12/26 ,  H04N21/414 ,  H04N21/6377 ,  H04N21/61 ,  H04N21/81 ,  G06F9/451

Abstract: In a streaming application environment, input generated in a remote device may be synchronized with rendered content generated by a virtual streaming application in the streaming application environment in part by using frame refresh events passed between the remote device and the streaming application environment to enable the streaming application environment to effectively track a frame refresh rate of the remote device such that input events received from the remote device may be injected into the virtual streaming application at appropriate frame intervals.

公开(公告)号：US20240412334A1

公开(公告)日：2024-12-12

申请号：US18735050

申请日：2024-06-05

Applicant: Google LLC

Inventor： Raman Sarokin ,  Yu-Hui Chen ,  Juhyun Lee ,  Jiuqiang Tang ,  Chuo-Ling Chang ,  Andrei Kulik ,  Matthias Grundmann

IPC: G06T5/60 ,  G06T1/20 ,  G06T5/70

Abstract: Systems, methods, devices, and related techniques for accelerating execution of diffusion models or of other neural networks that involve similar operations. Some aspects include accelerating inference computations in neural networks, including inference computations utilized in denoising (also referred to as “diffusion”) neural networks.

公开(公告)号：US20240370717A1

公开(公告)日：2024-11-07

申请号：US18313189

申请日：2023-05-05

Applicant: Google LLC

Inventor： Qifei Wang ,  Yicheng Fan ,  Wei Xu ,  Jiayu Ye ,  Lu Wang ,  Chuo-Ling Chang ,  Dana Alon ,  Erik Nathan Vee ,  Hongkun Yu ,  Matthias Grundmann ,  Shanmugasundaram Ravikumar ,  Andrew Stephen Tomkins

IPC: G06N3/08

Abstract: A method for a cross-platform distillation framework includes obtaining a plurality of training samples. The method includes generating, using a student neural network model executing on a first processing unit, a first output based on a first training sample. The method also includes generating, using a teacher neural network model executing on a second processing unit, a second output based on the first training sample. The method includes determining, based on the first output and the second output, a first loss. The method further includes adjusting, based on the first loss, one or more parameters of the student neural network model. The method includes repeating the above steps for each training sample of the plurality of training samples.

公开(公告)号：US20220308747A1

公开(公告)日：2022-09-29

申请号：US17833469

申请日：2022-06-06

Applicant: GOOGLE LLC

Inventor： Chuo-Ling Chang ,  Peter Tan

IPC: G06F3/04883 ,  G06F9/451 ,  G06F3/038 ,  H04L65/612 ,  H04N21/422

Abstract: In a streaming application environment coupled to a remote device over a packet-switching network, correction events may be synthesized from input events received from the remote device and injected into a virtual streaming application to account for lost or delayed input events. In addition, trailing events may be reissued by a remote device in frames during which no new input events are generated.

公开(公告)号：US20240111572A1

公开(公告)日：2024-04-04

申请号：US17935709

申请日：2022-09-27

Applicant: Google LLC

Inventor： Jamie Menjay Lin ,  Chuo-Ling Chang

IPC: G06F9/48 ,  G06F9/46

CPC classification number: G06F9/4881 ,  G06F9/463

Abstract: A method including processing a stream of data in a sequence of tasks. The processing including receiving a first block of data of the stream of data, determining features associated with the first block of data, selecting, based on the features, one of a first a task to process the first block of data or a second task to process the first block of data and if the second task is selected, shift an output of the second task in time to align the output of the second task with a predicted output of the first task processing a second block of data of the stream of data.

公开(公告)号：US11303687B2

公开(公告)日：2022-04-12

申请号：US16811820

申请日：2020-03-06

Applicant: GOOGLE LLC

Inventor： Chuo-Ling Chang ,  Ping-Hao Wu

IPC: G06F15/16 ,  H04L29/08 ,  G06F3/14 ,  H04L65/60 ,  H04N21/61 ,  G06F9/451 ,  H04N21/81 ,  H04N21/6377 ,  H04N21/414 ,  H04L43/087

Abstract: In a streaming application environment, input generated in a remote device may be synchronized with rendered content generated by a virtual streaming application in the streaming application environment in part by using frame refresh events passed between the remote device and the streaming application environment to enable the streaming application environment to effectively track a frame refresh rate of the remote device such that input events received from the remote device may be injected into the virtual streaming application at appropriate frame intervals.

公开(公告)号：US10404771B2

公开(公告)日：2019-09-03

申请号：US15711077

申请日：2017-09-21

Applicant: Google LLC

Inventor： Chuo-Ling Chang

IPC: G06F15/16 ,  H04L29/06 ,  G06F9/451 ,  H04N21/238 ,  H04N21/6336 ,  H04N19/50 ,  G06F3/14

Abstract: Systems and methods for pre-fetched encoding for application streaming. In some implementations, an indication at a server computer system that a client device has a plurality of representations of template frames may be received. Multiple image frames, provided to a client device by the server computer system, where the processing of each image frame includes determining whether the image frame satisfies a threshold similarity to one of the template frames, may be processed. The operations performed for each image frame that satisfies the threshold similarity to one of the template frames may include, generating a representation of a difference between the image frame and the template frame with which the image frame satisfies the threshold similarity, generating an instruction for rendering the image frame, and providing the instruction to the client device.