知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.011 seconds)

    IMITATION LEARNING SYSTEM
    1.
    发明申请
    IMITATION LEARNING SYSTEM 有权

    公开(公告)号：US20210081752A1

    公开(公告)日：2021-03-18

    申请号：US16931211

    申请日：2020-07-16

    Applicant: NVIDIA Corporation

    Inventor： Yu-Wei Chao ,  De-An Huang ,  Christopher Jason Paxton ,  Animesh Garg ,  Dieter Fox

    IPC: G06N3/00 ,  G06N20/00

    Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

    FAIRNESS-BASED NEURAL NETWORK MODEL TRAINING USING REAL AND GENERATED DATA
    2.
    发明公开
    FAIRNESS-BASED NEURAL NETWORK MODEL TRAINING USING REAL AND GENERATED DATA 审中-公开

    公开(公告)号：US20240144000A1

    公开(公告)日：2024-05-02

    申请号：US18307227

    申请日：2023-04-26

    Applicant: NVIDIA Corporation

    Inventor： Yuji Roh ,  Weili Nie ,  De-An Huang ,  Arash Vahdat ,  Animashree Anandkumar

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: A neural network model is trained for fairness and accuracy using both real and synthesized training data, such as images. During training a first sampling ratio between the real and synthesized training data is optimized. The first sampling ratio may comprise a value for each group (or attribute), where each value is optimized. A second sampling ratio defines relative amounts of training data that are used for each one of the groups. Furthermore, a neural network model accuracy and a fairness metric are both used for updating the first and second sampling ratios during training iterations. The neural network model may be trained using different classes of training data. The second sampling ratio may vary for each class.

    Imitation learning system
    3.
    发明授权
    Imitation learning system 有权

    公开(公告)号：US11893468B2

    公开(公告)日：2024-02-06

    申请号：US16931211

    申请日：2020-07-16

    Applicant: NVIDIA Corporation

    Inventor： Yu-Wei Chao ,  De-An Huang ,  Christopher Jason Paxton ,  Animesh Garg ,  Dieter Fox

    IPC: G06N3/008 ,  G06N20/00

    CPC classification number: G06N3/008 ,  G06N20/00

    Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

    CONDITIONAL DIFFUSION MODEL FOR DATA-TO-DATA TRANSLATION
    4.
    发明公开
    CONDITIONAL DIFFUSION MODEL FOR DATA-TO-DATA TRANSLATION 审中-公开

    公开(公告)号：US20240273682A1

    公开(公告)日：2024-08-15

    申请号：US18431527

    申请日：2024-02-02

    Applicant: NVIDIA Corporation

    Inventor： Weili Nie ,  Guan-Horng Liu ,  Arash Vahdat ,  De-An Huang ,  Anima Anandkumar

    IPC: G06T5/60 ,  G06T5/50

    CPC classification number: G06T5/60 ,  G06T5/50

    Abstract: Image restoration generally involves recovering a target clean image from a given image having noise, blurring, or other degraded features. Current image restoration solutions typically include a diffusion model that is trained for image restoration by a forward process that progressively diffuses data to noise, and then by learning in a reverse process to generate the data from the noise. However, the forward process relies on Gaussian noise to diffuse the original data, which has little or no structural information corresponding to the original data versus learning from the degraded image itself which is much more structurally informative compared to the random Gaussian noise. Similar problems also exist for other data-to-data translation tasks. The present disclosure trains a data translation conditional diffusion model from diffusion bridge(s) computed between a first version of the data and a second version of the data, which can yield a model that can provide interpretable generation, sampling efficiency, and reduced processing time.

    SYSTEM AND METHOD FOR EFFICIENT TEXT-GUIDED GENERATION OF HIGH-RESOLUTION VIDEOS
    6.
    发明申请
    SYSTEM AND METHOD FOR EFFICIENT TEXT-GUIDED GENERATION OF HIGH-RESOLUTION VIDEOS 有权

    公开(公告)号：US20250111552A1

    公开(公告)日：2025-04-03

    申请号：US18819064

    申请日：2024-08-29

    Applicant: NVIDIA Corporation

    Inventor： Sihyun Yu ,  Weili Nie ,  De-An Huang ,  Boyi Li ,  Animashree Anandkumar

    IPC: G06T11/00 ,  G06N3/0455 ,  G06T9/00

    Abstract: Systems and methods are disclosed that train a content frame-motion latent diffusion model (CDM) and use the CDM to generate requested videos. The CMD may be a two-stage framework that first compresses videos to a succinct latent space and then learns the video distribution in this latent space. For instance, the CMD may include an autoencoder and two diffusion models. In a first stage, using the autoencoder, a low-dimensional latent decomposition into a content frame and latent motion representation is learned. In the second stage, without adding any new parameters, the content frame distribution may be fine-tuned by using a pretrained image diffusion model, which allows the CMD to leverage the rich visual knowledge in pretrained image diffusion models. In addition, a new lightweight diffusion model may be used to generate motion latent representations that are conditioned on the given content frame.

    TRAJECTORY STITCHING FOR ACCELERATING DIFFUSION MODELS
    8.
    发明申请
    TRAJECTORY STITCHING FOR ACCELERATING DIFFUSION MODELS 有权

    公开(公告)号：US20250103968A1

    公开(公告)日：2025-03-27

    申请号：US18821611

    申请日：2024-08-30

    Applicant: NVIDIA Corporation

    Inventor： Zizheng Pan ,  De-An Huang ,  Weili Nie ,  Zhiding Yu ,  Chaowei Xiao ,  Anima Anandkumar

    IPC: G06N20/20

    Abstract: Diffusion models are machine learning algorithms that are uniquely trained to generate high-quality data from an input lower-quality data. Diffusion probabilistic models use discrete-time random processes or continuous-time stochastic differential equations (SDEs) that learn to gradually remove the noise added to the data points. With diffusion probabilistic models, high quality output currently requires sampling from a large diffusion probabilistic model which corners at a high computational cost. The present disclosure stitches together the trajectory of two or more inferior diffusion probabilistic models during a denoising process, which can in turn accelerate the denoising process by avoiding use of only a single large diffusion probabilistic model.

Patent Agency Ranking