中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.02 seconds)

    INTEGRATING EVOLUTIONARY ALGORITHMS AND REINFORCEMENT LEARNING
    1.
    发明申请
    INTEGRATING EVOLUTIONARY ALGORITHMS AND REINFORCEMENT LEARNING 有权

    公开(公告)号：US20250053826A1

    公开(公告)日：2025-02-13

    申请号：US18754007

    申请日：2024-06-25

    Applicant: NVIDIA Corporation

    Inventor： Eli Alexander Meirom ,  Piotr Sielski ,  Gal Chechik ,  Alexandre Fender ,  Shie Mannor

    IPC: G06N3/126 ,  G06N3/092

    Abstract: A technique for solving combinatorial problems, such as vehicle routing for multiple vehicles integrates evolutionary algorithms and reinforcement learning. A genetic algorithm maintains a set of solutions for the problem and improves the solutions using mutation (modify a solution) and crossover (combine two solutions). The best solution is selected from the improved set of solutions. A system that integrates evolutionary algorithms, such as a genetic algorithm, and reinforcement learning comprises two components. A first component is a beam search technique for generating solutions using a reinforcement learning model. A second component augments a genetic algorithm using learning-based solutions that are generated by the reinforcement learning model. The learning-based solutions improve the diversity of the set which, in turn, improves the quality of the solutions computed by the genetic algorithm.

    GENERATION OF 3D OBJECTS USING POINT CLOUDS AND TEXT
    2.
    发明公开
    GENERATION OF 3D OBJECTS USING POINT CLOUDS AND TEXT 审中-公开

    公开(公告)号：US20240331280A1

    公开(公告)日：2024-10-03

    申请号：US18442756

    申请日：2024-02-15

    Applicant: NVIDIA Corporation

    Inventor： Yehonatan Kasten ,  Gal Chechik

    IPC: G06T17/00 ,  H04N13/279

    CPC classification number: G06T17/00 ,  H04N13/279

    Abstract: Embodiments of the present disclosure relate to controlling generation of 3D objects using point clouds and text. Systems and methods are disclosed that leverage a pre-trained text-to-image diffusion model to reconstruct a complete 3D model of an object from a sensor-captured incomplete point cloud for the object and a textual description of the object. The complete 3D model of the object may be represented as a neural surface (signed distance function), polygonal mesh, radiance field (neural surface and volumetric coloring function), and the like. The signed distance function (SDF) measures the distance of any 3D point from the nearest surface point, where positive or negative signs indicate that the point is outside or inside the object respectively. The SDF enables use of the incomplete point cloud for constraining the surface location by simply encouraging the signed distance function to be zero in the point cloud locations.

    FEEDBACK BASED CONTENT GENERATION IN GRAPHICAL INTERFACES
    3.
    发明申请
    FEEDBACK BASED CONTENT GENERATION IN GRAPHICAL INTERFACES 有权

    公开(公告)号：US20250053284A1

    公开(公告)日：2025-02-13

    申请号：US18232016

    申请日：2023-08-09

    Applicant: NVIDIA Corporation

    Inventor： Shie Mannor ,  Gal Chechik

    IPC: G06F3/04845 ,  G06F3/04815

    Abstract: Apparatuses, systems, and techniques to identify one or more modifications to objects within an environment. In at least one embodiment, objects are identified in an image, based on extracted feedback information, using one or more machine learning models, for example, using direct and/or implicit feedback of user interaction with one or more objects in an environment.

    TEXT-TO-IMAGE DIFFUSION MODEL WITH COMPONENT LOCKING AND RANK-ONE EDITING
    4.
    发明公开
    TEXT-TO-IMAGE DIFFUSION MODEL WITH COMPONENT LOCKING AND RANK-ONE EDITING 审中-公开

    公开(公告)号：US20240249446A1

    公开(公告)日：2024-07-25

    申请号：US18385840

    申请日：2023-10-31

    Applicant: NVIDIA Corporation

    Inventor： Yuval Atzmon ,  Yoad Tewel ,  Rinon Gal ,  Gal Chechik

    IPC: G06T11/00 ,  G06T7/10 ,  G06V10/24

    CPC classification number: G06T11/00 ,  G06T7/10 ,  G06V10/24

    Abstract: A text-to-image machine learning model takes a user input text and generates an image matching the given description. While text-to-image models currently exist, there is a desire to personalize these models on a per-user basis, including to configure the models to generate images of specific, unique user-provided concepts (via images of specific objects or styles) while allowing the user to use free text “prompts” to modify their appearance or compose them in new roles and novel scenes. Current personalization solutions either generate images with only coarse-grained resemblance to the provided concept(s) or require fine tuning of the entire model which is costly and can adversely affect the model. The present description employs component locking and/or rank-one editing for personalization of text-to-image diffusion models, which can improve the fine-grained details of the concepts in the generated images, reduce the memory footprint update of the underlying model instead of full fine-tuning, and reduce adverse effects to the model.

    LEARNING DIRECTABLE VIRTUAL AGENTS THROUGH CONDITIONAL ADVERSARIAL LATENT MODELS
    5.
    发明公开
    LEARNING DIRECTABLE VIRTUAL AGENTS THROUGH CONDITIONAL ADVERSARIAL LATENT MODELS 审中-公开

    公开(公告)号：US20240249458A1

    公开(公告)日：2024-07-25

    申请号：US18364982

    申请日：2023-08-03

    Applicant: NVIDIA Corporation

    Inventor： Chen Tessler ,  Gal Chechik ,  Yoni Kasten ,  Shie Mannor ,  Jason Peng

    IPC: G06T13/40 ,  G06N3/08 ,  G06T13/80

    CPC classification number: G06T13/40 ,  G06N3/08 ,  G06T13/80

    Abstract: A conditional adversarial latent model (CALM) process can be used to generate reference motions from a set of original reference movements to create a library of new movements for an agent. The agent can be a virtual representation various types of characters, animals, or objects. The CALM process can receive a set of reference movements and a requested movement. An encoder can be used to map the requested movement onto a latent space. A low-level policy can be employed to produce a series of latent space joint movements for the agent. A conditional discriminator can be used to provide feedback to the low-level policy to produce stationary distributions over the states of the agent. A high-level policy can be employed to provide a macro movement control over the low-level policy movements, such as providing direction in the environment. The high-level policy can utilize a reward or a finite-state machine function.

    ADAPTIVE LOOKAHEAD FOR PLANNING AND LEARNING
    6.
    发明公开
    ADAPTIVE LOOKAHEAD FOR PLANNING AND LEARNING 审中-公开

    公开(公告)号：US20230237342A1

    公开(公告)日：2023-07-27

    申请号：US18158920

    申请日：2023-01-24

    Applicant: NVIDIA Corporation

    Inventor： Shie Mannor ,  Gal Chechik ,  Gal Dalal ,  Assaf Joseph Hallak ,  Aviv Rosenberg

    IPC: G06N3/092

    CPC classification number: G06N3/092

    Abstract: A method is performed by an agent operating in an environment. The method comprises computing a first value associated with each state of a number of states in the environment, determining a lookahead horizon for each state of the number of states in the environment based on the computed first value for each state of the number of states, applying a first policy to compute a second value associated with each state of at least one state in the number of states in the environment for the at least one state in the number of states based on the determined lookahead horizons for the number of states, and determining a second policy based on the first policy and the second value for each state of the number of states in the environment.

    METHOD FOR FAST AND BETTER TREE SEARCH FOR REINFORCEMENT LEARNING
    8.
    发明申请
    METHOD FOR FAST AND BETTER TREE SEARCH FOR REINFORCEMENT LEARNING 有权

    公开(公告)号：US20220398283A1

    公开(公告)日：2022-12-15

    申请号：US17824680

    申请日：2022-05-25

    Applicant: NVIDIA Corporation

    Inventor： Shie Mannor ,  Assaf Joseph Hallak ,  Gal Dalal ,  Steven Tarence Dalton ,  Iuri Frosio ,  Gal Chechik

    IPC: G06F16/903 ,  G06F16/901

    Abstract: A method for performing a Tree-Search (TS) on an environment is provided. The method comprises generating a tree for a current state of the environment based on a TS policy, determining a corrected TS policy, and determining an action to apply to the environment based on the corrected TS policy. The tree comprises a plurality of nodes including a root node among the plurality of nodes corresponding to the current state of the environment. Each node other than the root node among the plurality of nodes corresponding to an estimated future state of the environment. The plurality of nodes in the tree are connected by a plurality of edges. Each edge among the plurality of edges is associated with an action causing a transition from a first state to a different sate of the environment.

Patent Agency Ranking