中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.015 seconds)

    EFFICIENT ON-DEVICE TRANSFORMER ARCHITECTURE FOR IMAGE PROCESSING
    1.
    发明申请
    EFFICIENT ON-DEVICE TRANSFORMER ARCHITECTURE FOR IMAGE PROCESSING 有权

    公开(公告)号：US20240414448A1

    公开(公告)日：2024-12-12

    申请号：US18515732

    申请日：2023-11-21

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Karim AHMED ,  Yi WEI ,  Vasili RAMANISHKA ,  Yilin SHEN ,  Hongxia JIN

    IPC: H04N23/84 ,  G06T3/4015 ,  G06T5/60 ,  G06T5/70

    Abstract: Provided is a U-shaped network for image restoration. The U-shaped network is lightweight based on a transformer block and is suitable to be deployed on-device, such as in a smartphone. The U-shaped network uses the transformer block to implement encoder, decoder and bottleneck functions. Decoders are connected to respective encoders using skip connections based on element-wise addition, which avoids dimension expansion of concatenation. The transformer block uses a configuration of scaling and pool mixing to process input image data without the need for self-attention computations which permits reduction in memory, reduction in latency, reduction in computational demand, all while maintaining good output image quality.

    METHOD AND SYSTEM FOR WEIGHTED KNOWLEDGE DISTILLATION BETWEEN NEURAL NETWORK MODELS
    2.
    发明申请
    METHOD AND SYSTEM FOR WEIGHTED KNOWLEDGE DISTILLATION BETWEEN NEURAL NETWORK MODELS 有权

    公开(公告)号：US20220398459A1

    公开(公告)日：2022-12-15

    申请号：US17835457

    申请日：2022-06-08

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Yen-Chang HSU ,  Yilin SHEN ,  Hongxia JIN

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A method of training a student model includes providing an input to a teacher model that is larger than the student model, where a layer of the teacher model outputs a first output vector, providing the input to the student model, where a layer of the student model outputs a second output vector, determining an importance value associated with each dimension of the first output vector based on gradients from the teacher model and updating at least one parameter of the student model to minimize a difference between the second output vector and the first output vector based on the importance values.

    PARAPHRASE AND AGGREGATE WITH LARGE LANGUAGE MODELS FOR IMPROVED DECISIONS
    6.
    发明申请
    PARAPHRASE AND AGGREGATE WITH LARGE LANGUAGE MODELS FOR IMPROVED DECISIONS 有权

    公开(公告)号：US20250037710A1

    公开(公告)日：2025-01-30

    申请号：US18781617

    申请日：2024-07-23

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Vikas YADAV ,  Zheng TANG ,  Vijay SRINIVASAN ,  Hongxia JIN

    IPC: G10L15/18

    Abstract: A method of interpreting a verbal input, may include: assigning a meaning classification to the verbal input, and a confidence score to the meaning classification; and based on the confidence score corresponding to the meaning classification of the verbal input being less than or equal to a threshold, generating at least one paraphrase of the verbal input using at least one large language model (LLM); assigning the meaning classification to the at least one paraphrase, and the confidence score to the meaning classification; and concatenating the verbal input, the at least one paraphrase, the meaning classification, and the confidence score to generate a concatenated input; inputting the concatenated input into the at least one LLM.

    ENABLING DEVICE CONTROL PLANNING CAPABILITIES OF SMALL LANGUAGE MODEL
    8.
    发明申请
    ENABLING DEVICE CONTROL PLANNING CAPABILITIES OF SMALL LANGUAGE MODEL 有权

    公开(公告)号：US20250094820A1

    公开(公告)日：2025-03-20

    申请号：US18824166

    申请日：2024-09-04

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Sudipta PAUL ,  Lingyu ZHANG ,  Yilin SHEN ,  Hongxia JIN

    IPC: G06N3/096

    Abstract: A method for enabling an improved device control capability of a small language model (SLM) transferrable to a hub device configured to be operable by a user in an environment, is disclosed. The method includes performing a fine-tuning the SLM based on a data set including base plans and contrastive plans; generating computer codes corresponding to the fine-tuned SLM; and transferring the generated computer codes to the hub device to be connected with a group of the electronic devices in the environment.

    IMAGE SUPER-RESOLUTION WITH REFERENCE IMAGES FROM ONE OR MORE CAMERAS
    9.
    发明申请
    IMAGE SUPER-RESOLUTION WITH REFERENCE IMAGES FROM ONE OR MORE CAMERAS 有权

    公开(公告)号：US20220368829A1

    公开(公告)日：2022-11-17

    申请号：US17493268

    申请日：2021-10-04

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jing ZHU ,  Wenbo LI ,  Hongxia JIN

    IPC: H04N5/232 ,  G06T5/00 ,  G06T5/50 ,  G06T5/20

    Abstract: A super resolution is produced using multiple reference images. Reference images are upsampled and blurred as needed for comparison between images of different resolution. Patches in blurred images are searched to find those patches which can be assembled into vectors for improving feature content over multiple resolution levels. The searches are based on similarity maps. The assembled vectors are concatenated with one or more other vectors, up-converted and then passed through convolutional layers to obtain new feature vectors. A final feature vector is passed through a convolutional layer to obtain the super resolution image.

    METHOD AND SYSTEM FOR DETECTING UNSUPPORTED UTTERANCES IN NATURAL LANGUAGE UNDERSTANDING
    10.
    发明申请
    METHOD AND SYSTEM FOR DETECTING UNSUPPORTED UTTERANCES IN NATURAL LANGUAGE UNDERSTANDING 有权

    公开(公告)号：US20220199070A1

    公开(公告)日：2022-06-23

    申请号：US17402045

    申请日：2021-08-13

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Yen-Chang Hsu ,  Yilin Shen ,  Avik Ray ,  Hongxia JIN

    IPC: G10L15/02 ,  G10L15/18

    Abstract: An apparatus for detecting unsupported utterances in natural language understanding, includes a memory storing instructions, and at least one processor configured to execute the instructions to classify a feature that is extracted from an input utterance of a user, as one of in-domain and out-of-domain (OOD) for a response to the input utterance, obtain an OOD score of the extracted feature, and identify whether the feature is classified as OOD. The at least one processor is further configured to executed the instructions to, based on the feature being identified to be classified as in-domain, identify whether the obtained OOD score is greater than a predefined threshold, and based on the OOD score being identified to be greater than the predefined threshold, re-classify the feature as OOD.

Patent Agency Ranking