公开(公告)号：US12231563B2

公开(公告)日：2025-02-18

申请号：US18297339

申请日：2023-04-07

Applicant: Lemon Inc.

Inventor： Haohao Qian ,  Jian Du ,  Qiang Yan

IPC: H04L9/30 ,  G06F16/2455 ,  G06F16/25

Abstract: Methods and systems for secure computation and communication are provided. The method includes transforming identifications of a first dataset using a first transforming scheme, and transforming attributes of the first dataset using a second transforming scheme. The method also includes dispatching the transformed first dataset, receiving a second dataset, transforming identifications of the received second dataset, dispatching the identifications of the transformed received second dataset, and receiving a set of identifications. The method further includes generating a first intersection of the received set of identifications and the transformed received second dataset, generating a first share based on the first intersection, receiving a second share, and constructing a result based on the first share and the second share.

公开(公告)号：US20250054271A1

公开(公告)日：2025-02-13

申请号：US18723150

申请日：2022-12-22

Applicant: Lemon Inc.

Inventor： Yichun SHI ,  Xiao YANG ,  Xiaohui SHEN

IPC: G06V10/44 ,  G06T3/4007 ,  G06V10/74

Abstract: The present disclosure provides a video generation method and device. The video generation method includes: extracting a first image feature from a first image; obtaining a plurality of intermediate image features by means of nonlinear interpolation according to the first image feature and a second image feature, wherein the second image feature is an image feature of a second image; and performing image reconstruction by means of an image generation model based on the first image feature, the second image feature, and the plurality of intermediate image features, so as to generate a target video, wherein the target video is used for presenting a process of a gradual change from the first image to the second image.

公开(公告)号：US20250053390A1

公开(公告)日：2025-02-13

申请号：US18447734

申请日：2023-08-10

Applicant: Lemon Inc.

Inventor： Lakshminarayanan VIJAYARAGHAVAN

IPC: G06F8/35

Abstract: Described are examples for creating elements in an effect creation tool, including receiving, via a user interface provided for the effect creation tool, a natural language string requesting creation of an element in the effect creation tool, providing, to a model, an input including at least a portion of the natural language string, receiving, from the model and based on the input, an output string, in an expected syntax, corresponding to creating the element, mapping the output string to one or more commands of a format for creating the element in the effect creation tool, and providing the one or more commands to the effect creation tool to cause creation of the element in the effect creation tool.

公开(公告)号：US20250046054A1

公开(公告)日：2025-02-06

申请号：US18717239

申请日：2023-03-17

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Chong WANG ,  Lin ZHENG

IPC: G06V10/48 ,  G06F17/18

Abstract: The disclosure relates to a method, an apparatus, a storage medium, an electronic device, a computer program product, and a computer program for feature extraction, device. The method includes: determining target data for a feature to be extracted, and determining, based on the target data, a plurality of query vectors, a plurality of key vectors, and a plurality of value vectors; determining a plurality of key-value pair information corresponding to each of the query vectors; and performing, for each of the query vectors, a random mapping based on the query vector and the plurality of data samples, to obtain a plurality of random query vectors, and determining feature information corresponding to the query vector based on the plurality of random query vectors and the plurality of key-value pair information.

公开(公告)号：US20250045929A1

公开(公告)日：2025-02-06

申请号：US18365060

申请日：2023-08-03

Applicant: Lemon Inc.

Inventor： Qihang Yu ,  Ju He ,  Xueqing Deng ,  Xiaohui Shen ,  Liang-Chieh Chen

IPC: G06T7/12 ,  G06T3/40 ,  G06V10/44 ,  G06V10/764 ,  G06V10/771

Abstract: Single-stage frameworks for open-vocabulary panoptic segmentation are provided. One aspect provides a computing system comprising a processor and memory storing instructions that, when executed by the processor, cause the processor to: receive an image; extract a plurality of feature maps from the image using a convolutional neural network-based vision-language model; generate a plurality of pixel features from the plurality of feature maps; generate a plurality of mask predictions from the plurality of pixel features; generate a plurality of in-vocabulary class predictions corresponding to the plurality of mask predictions using the plurality of pixel features; generate a plurality of out-of-vocabulary class predictions using the plurality of feature maps; perform geometric ensembling on the plurality of in-vocabulary class predictions and the plurality of out-of-vocabulary class predictions to generate a plurality of final class predictions; and output the plurality of mask predictions and the plurality of final class predictions.

公开(公告)号：US20250037806A1

公开(公告)日：2025-01-30

申请号：US18717362

申请日：2023-04-20

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Xiang GAO ,  Weihao GAO ,  Wenzhi XIAO ,  Zhirui WANG ,  Liang XIANG ,  Chong WANG

IPC: G16C20/70

Abstract: According to implementations of the present disclosure, a method, apparatus, device and medium for managing molecular prediction is provided. In the method, an upstream model is obtained from a portion of network layers in a pretrained model, the pretrained model describing an association between a molecular structure and molecular energy. A downstream model is determined based on a molecular prediction purpose, and an output layer of the downstream model is determined based on the molecular prediction purpose. A molecular prediction model is generated based on the upstream model and the downstream model, the molecular prediction model describing an association between a molecular structure and a molecular prediction purpose associated with the molecular structure. Since the upstream model may have extensive knowledge related to molecules, the amount of training data required to train the molecular prediction model that is generated based on the upstream model and the downstream model may be reduced.

公开(公告)号：US20250030881A1

公开(公告)日：2025-01-23

申请号：US18909092

申请日：2024-10-08

Applicant: Lemon Inc.

Inventor： Yue Li ,  Li Zhang ,  Kai Zhang

IPC: H04N19/436 ,  H04N19/124 ,  H04N19/132 ,  H04N19/157 ,  H04N19/70 ,  H04N19/82

Abstract: A method of processing video data. The method includes determining that a supplemental enhancement information (SEI) message of a bitstream includes indicators specifying one or more neural network (NN) filter model candidates or selections for a video unit or samples within the video unit, and converting between a video media file comprising the video unit and the bitstream based on the indicators. A corresponding video coding apparatus and non-transitory computer readable medium are also disclosed.

公开(公告)号：US12204777B2

公开(公告)日：2025-01-21

申请号：US18187088

申请日：2023-03-21

Applicant: Lemon Inc.

Inventor： Ping Zhou ,  Kan Frankie Fan ,  Chaohong Hu ,  Longxiao Li ,  Hui Zhang ,  Fei Liu

IPC: G06F3/06

Abstract: Systems and methods for space allocation for block device compression are provided. In particular, a computing device may receive an allocation request to write the compressed data, select a range list adequate for serving the allocation request from a plurality of range list, dequeue a range entry from the selected range list to allocate free space for the compressed data, and allocate the free space corresponding to the range entry to the compressed data to serve the allocation request.

公开(公告)号：US20250021891A1

公开(公告)日：2025-01-16

申请号：US18900432

申请日：2024-09-27

Applicant: Beijing Youzhuju Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Yuanshun Yao ,  Hongyi Guo ,  Xiaoying Zhang ,  Yang Liu

IPC: G06N20/00

Abstract: A method is proposed for machine learning (ML) model alignment. In the method, a first number of samples is generated by a target ML model based on samples selected from a set of samples. A sample comprises a question-answer pair. The set of samples is updated by adding at least a portion of the first number of samples to the set of samples. The target ML model is trained with at least a portion of the updated set of samples. In this way, the ML model self-generalization ability is unlocked to perform alignment with near-zero human supervision.

公开(公告)号：US12198673B2

公开(公告)日：2025-01-14

申请号：US17525814

申请日：2021-11-12

Applicant: LEMON INC.

Inventor： Lamtharn Hantrakul ,  Siyuan Shan ,  Jitong Chen ,  Matthew David Avent ,  David Trevelyan

IPC: G10L13/04 ,  G06N20/00 ,  G10H7/10 ,  G10L13/047 ,  G10L13/08 ,  G10L15/04 ,  G10L19/26

Abstract: The present disclosure describes techniques for differentiable wavetable synthesizer. The techniques comprise extracting features from a dataset of sounds, wherein the features comprise at least timbre embedding; input the features to the first machine learning model, wherein the first machine learning model is configured to extract a set of N×L learnable parameters, N represents a number of wavetables, and L represents a wavetable length; outputting a plurality of wavetables, wherein each of plurality of wavetables comprises a waveform associated with a unique timbre, the plurality of wavetables form a dictionary, and the plurality of wavetables are portable to perform audio-related tasks. Finally, the said wavetables are used to initialize another machine learning model so as to help reduce computational complexity of an audio synthesis obtained as output of the another machine learning model.