Samsung Electronics Co., Ltd.

Intermolecular, Inc.

Gopro, Inc.

Beijing Voyager Technology Co., Ltd.

Xerox Corporation

Palo Alto Research Center Inc.

Guardian Industries Corporation

Beijing Didi Infinity Technology and Development Co., Ltd.

Chemocentryx, Inc.

Ambarella International LP

Nvidia Corporation

Yahoo Assets LLC

Google Inc.

Meta Platforms, Inc.

Guardian Glass, LLC

Yu Wang

Guowen Ding

Minh Le

Fengmin Gong

Xiaoyong Yi

Leslie D Kohn

Brent Boyce

Zhi-Wen Sun

Qi Chen

Jiang Zhang

Christopher L Chua

Guizhen Zhang

Pei Zheng

Yongli Xu

Hongxia Jin

Muhammad Imran

Mohd Fadzli Anwar Hassan

Jeremy Cheng

Daniel Schweigert

Yilin Shen

Penglie Zhang

Qian Wang

I-Hsuan Yang

Rajinder Paul Singh

Elliot N Linzer

Eugene Michael Chow

Patrick Yasuo Maeda

Sreenivas Punna

Thai Cheng Chua

Venkat Reddy Mali

Ju Yang

Viengkham Malathong

Darren J McMurtrie

Christopher W Lange

Jeffrey P McMahon

Zhiyun Li

Kostas Tsioutsiouliklis

Minh Anh Nguyen

Howard S Roth

Donghyun Kim

Rao Shen

Guy Rapaport

Yufeng Ma

Abhishek Bajpayee

Fatemeh Nazly Pirmoradi

Yongzuan Wu

David Kalman Biegelsen

Ping Mei

Jurgen Hans Daniel

Yibin Zeng

Joerg Martini

Tuna Toksoz

Wei Wei

Alex N Hegyi

Jose Ferreira

Jingyu Lao

Zhihong Yang

James B Boyce

Jackson H Ho

Hae-Jong Seo

Hien Minh Huu Le

Jinghao Yan

Yue Deng

Liuqing Li

Joanne Tan

Kathleen Dore Boyce, Legal Representative

Karen Ebsworth

Igor Tryndin

Wei Fang

Xiangyu Zeng

Pei Huang

Yue Guo

Sagar Sanjay Chordia

Shlok Vaidya

Yu Pang

Manish Singhal

Connor Foody

Manav Kedia

Dylan Doblar

Arjun Gupta

Keerthi Raj Nagaraja

Caitlin King Stanton

Thomas Benjamin Jablin

Sai Krishnan Chandrasekar

Kivanc Temel

Jeffrey Mcmahon

Rachel Lau

Minh Huu Le

Muhammed Imran

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling workloads on computing resources using a high priority queue and a low priority queue. The high priority queue maintains pending high priority workloads to be scheduled for execution, and the low priority queue maintains pending low priority workloads to be scheduled for execution. The computing system as described in this specification schedules the pending low priority workloads for execution by utilizing computing resources provided by the system only when the high priority queue is empty.

Workload scheduling using queues with different priorities

Methods, systems, and non-transitory computer-readable media are configured to perform operations comprising determining a symmetric scenario for a scenario; training a first machine learning model for the scenario based on first training data generated from second training data for the symmetric scenario; and generating a prediction for the scenario based on the first machine learning model.

Intention prediction in symmetric scenarios

Focusing optics can include optical elements disposed and bonded in a linear arrangement (linear array) in at least two rows. A transparent bonding agent can secure alignment of the at least two rows of the optical elements. Scattering elements can also be disposed in the transparent polymer to cause light diffusion. Diffused or un-diffused light from a semiconductor laser array can then be caused to pass through the optical element and illuminate a target substrate such as an imaging member in a printing system.

Focusing optics for use with semiconductor lasers for imaging applications

This application is directed to predicting vehicle actions according to a hierarchy of interconnected vehicle actions. The hierarchy of interconnected vehicle actions includes a plurality of predefined vehicle actions that are organized to define a plurality of vehicle action sequences. A first vehicle obtains one or more images of a road and a second vehicle, and predicts a sequence of vehicle actions of the second vehicle through the hierarchy of interconnected vehicle actions using the one or more images. The first vehicle is controlled to drive at least partially autonomously based on the predicted sequence of vehicle actions of the second vehicle. In some embodiments, the hierarchy of interconnected vehicle actions includes a first action level that is defined according to a stage of a trip and corresponds to three predefined vehicle actions of: 'start a trip,' “move in a trip,” and “complete a trip.”

Hierarchical vehicle action prediction

A microspring includes a film stack having a base disposed on a build plane and a spring member extending from the base. The film stack includes a compressive layer, a substantially stress-free layer, and a tensile layer. The film stack is formed of one or more materials that become superconducting below 140 K. A stress gradient in the film stack causes the spring member to curl away from the build plane of the base.

Stress engineered microspring for cryogenic superconducting circuits

The present disclosure relates to determining a first illumination level corresponding to an area based at least on a first illumination detection obtained using a first illumination detector corresponding to a machine. A second illumination level corresponding to the area may be determined based at least on a second illumination detection obtained using a second illumination detector corresponding to the machine. Based at least on the first illumination level and the second illumination level, a scene illumination state of the area may be determined. Based at least on the scene illumination state, one or more lights of the machine may be controlled.

Scene illumination detection for autonomous systems and applications

One or more computing devices, systems, and/or methods for debiasing training data based upon information seeking behaviors are provided. Users associated with a set of training data are segmented into information seeking behavior groups corresponding to varying degrees of information seeking behaviors of the users. Biases for the information seeking behavior groups may be estimated based upon information seeking behaviors of users within the information seeking behavior groups. The training set of data is debiased using the biases to generate a debiased training set of data. A model may be trained to perform a task based upon the debiased training set of data.

Debiasing training data based upon information seeking behaviors

In various examples, contrast values corresponding to pixels of one or more images generated using one or more sensors of a vehicle may be computed to detect and identify objects that trigger glare mitigating operations. Pixel luminance values are determined and used to compute a contrast value based on comparing the pixel luminance values to a reference luminance value that is based on a set of the pixels and the corresponding luminance values. A contrast threshold may be applied to the computed contrast values to identify glare in the image data to trigger glare mitigating operations so that the vehicle may modify the configuration of one or more illumination sources so as to reduce glare experienced by occupants and/or sensors of the vehicle.

Glare mitigation using image contrast analysis for autonomous systems and applications

A method includes obtaining, using at least one processor of an electronic device, an image-query understanding model. The method also includes obtaining, using the at least one processor, an image and a user query associated with the image, where the image includes a target image area and the user query includes a target phrase. The method further includes retraining, using the at least one processor, the image-query understanding model using a correlation between the target image area and the target phrase to obtain a retrained image-query understanding model.

System and method for robust image-query understanding based on contextual features

An electronic assembly and methods of making the assembly are disclosed. The electronic assembly includes a substrate with an elastic member having an intrinsic stress profile. The elastic member has an anchor portion on the surface of the substrate; and a free end biased away from the substrate via the intrinsic stress profile to form an out of plane structure. The substrate includes one or more spacers on the substrate. The electronic assembly includes a chip comprising contact pads. The out of plane structure on the substrate touches corresponding contact pads on the chip, and the spacers on the substrate touch the chip forming a gap between the substrate and the chip.

Spacers formed on a substrate with etched micro-springs

Disclosed are techniques for securing electronic control units (ECUs) in a vehicle. A security platform for a vehicle includes a key distribution center (KDC) for the vehicle. The KDC is configured to verify that a digital certificate associated with a first electronic control unit (ECU) on the vehicle is a valid certificate, where the digital certificate indicates a first security level of the first ECU. The KDC is configured to generate, based on the first security level of the first ECU, one or more security keys for secure communication between the first ECU and a set of ECUs on the vehicle, and provision the one or more security keys to the first ECU and the set of ECUs. In some embodiments, the KDC uses the provisioned keys to authenticate each ECU when the vehicle is powered up.

Trusted platform protection in an autonomous vehicle

Compounds are provided that are useful as immunomodulators. The compounds have the following Formula (I): including stereoisomers and pharmaceutically acceptable salts thereof, wherein Z, L, R, R, R, R, R, R, R, R, R, R, R, R, m and n are as defined herein. Methods associated with preparation and use of such compounds, as well as pharmaceutical compositions comprising such compounds, are also disclosed.

Immunomodulator compounds

This application is directed to predicting vehicle actions according to a hierarchy of interconnected vehicle actions. The hierarchy of interconnected vehicle actions includes a plurality of predefined vehicle actions that are organized to define a plurality of vehicle action sequences. A first vehicle obtains one or more images of a road and a second vehicle, and predicts a sequence of vehicle actions of the second vehicle through the hierarchy of interconnected vehicle actions using the one or more images. The first vehicle is controlled to drive at least partially autonomously based on the predicted sequence of vehicle actions of the second vehicle. In some embodiments, the hierarchy of interconnected vehicle actions includes a first action level that is defined according to a stage of a trip and corresponds to three predefined vehicle actions of: 'start a trip,' 'move in a trip,' and &#x201c;complete a trip.&#x201d;

Intent determination based on one or more multi-model structures can include generating an output from each of a plurality of domain-specific models in response to a received input. The domain-specific models can comprise simultaneously trained machine learning models that are trained using a corresponding local loss metric for each domain-specific model and a global loss metric for the plurality of domain-specific models. The presence or absence of an intent corresponding to one or more domain-specific models can be determined by classifying the output of each domain-specific model.

Multi-model structures for classification and intent determination

Growing community of inventors

San Jose, CA, United States of America

Yu Wang