Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an image embedding model and a text embedding model. In one aspect, a method comprises: processing data from a historical query log of a search system to generate a candidate set of training examples, wherein each training example comprises: (i) a search query comprising a sequence of one or more words, (ii) an image, and (iii) selection data characterizing how often users selected the image in response to the image being identified by a search result for the search query; selecting a plurality of training examples from the candidate set of training examples; and using the training data to jointly train the image embedding model and the text embedding model.

Abstract: The present disclosure provides a complex of general formula (I), wherein M is tetravalent platinum; L is independently a neutral ligand or an anionic ligand when appearing each time; x is an integer of 1-5; P is a precursor ligand, the precursor ligand being a ligand of a tetravalent platinum ion which can be released from the complex after irradiation and converted into a functional molecule D to achieve functions such as medicine, fluorescence detection, or a functional material.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching an autonomous vehicle sensor data repository. One of the methods includes maintaining a collection of sensor samples and, for each sensor sample, an embedding of the sensor sample; receiving a request specifying a query sensor sample, wherein the query sensor sample characterizes a query environment region; and identifying, from the collection of sensor samples, a plurality of relevant sensor samples that characterize similar environment regions to the query environment region, comprising: processing the query sensor sample through the embedding neural network to generate a query embedding; and identifying, from sensor samples in a subset of the sensor samples in the collection, a plurality of sensor samples that have embeddings that are closest to the query embedding.

Abstract: The described aspects and implementations enable efficient calibration of a sensing system of a vehicle. In one implementation, disclosed is a method and a system to perform the method of obtaining a plurality of target outputs generated by processing a training input using a respective teacher machine learning model (MLM) of a plurality of teacher MLMs. The training input includes a representation of one or more objects, and each of the plurality of target outputs includes a classification of the objects among a respective set of classes of a plurality of sets of classes. The method further includes using the training input and the plurality of target outputs to train a student MLM to classify the one or more objects among each of the plurality of sets of classes.

Abstract: The invention provides a parameters tuning method of energy storage system and the energy storage system, and the method comprises the following steps: using PID control module to construct a closed-loop control subsystem of energy dispatching; acquiring PID initial parameters according to the energy dispatching model of the energy storage system; setting an adaptive model in the PID control module, and processing the PID initial parameters through the adaptive model to obtain PID adjusted and modified parameters; using the PID adjusted and modified parameters to modify the PID parameters and get the PID tuning parameters. What's more, the system comprises a battery module, a bidirectional converter device, an energy dispatching subsystem and a closed-loop control subsystem; and the closed-loop control subsystem is provided with a PID control module, and the PID control module is provided with an adaptive model for realizing the parameters tuning method of the energy storage system.

Abstract: A backlight module includes a front frame (1), a screen (3), and a flexible buffer layer (2) located between the front frame (1) and the screen (3). In a direction from the front frame (1) to the screen (3), a gap between the front frame (1) and the screen (3) is filled with the flexible buffer layer (2); and the flexible buffer layer (2) is in an elastic compression state.

Abstract: The invention provides a parameters tuning method of energy storage system and the energy storage system, and the method comprises the following steps: using PID control module to construct a closed-loop control subsystem of energy dispatching; acquiring PID initial parameters according to the energy dispatching model of the energy storage system; setting an adaptive model in the PID control module, and processing the PID initial parameters through the adaptive model to obtain PID adjusted and modified parameters; using the PID adjusted and modified parameters to modify the PID parameters and get the PID tuning parameters. What's more, the system comprises a battery module, a bidirectional converter device, an energy dispatching subsystem and a closed-loop control subsystem; and the closed-loop control subsystem is provided with a PID control module, and the PID control module is provided with an adaptive model for realizing the parameters tuning method of the energy storage system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.

Abstract: The invention provides a thermal management device for energy storage system, a method for controlling the thermal management device for energy storage system, and an energy storage system, wherein the thermal management device for energy storage system comprises a heat dissipation system, a temperature transducer, a data acquisition module, a management module and a data interaction module; the heat dissipation system comprises refrigerant circulating heat exchange components for heat dissipation of energy storage system, wherein the refrigerant circulating heat exchange components perform heat exchange through phase change of refrigerant; the data acquisition module is connected with the temperature transducer, and is used for acquiring the external environment temperature and the working environment temperature of energy storage system; the management module is used for conducting heating value analysis of energy storage system, and then performing heat dissipation control and management according to the h

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a spatio-temporal embedding of a sequence of point clouds. One of the methods includes obtaining a temporal sequence comprising a respective point cloud input corresponding to each of a plurality of time points, each point cloud input comprising point cloud data generated from sensor data captured by one or more sensors of a vehicle at the respective time point; processing each point cloud input using a first neural network to generate a respective spatial embedding that characterizes the point cloud input; and processing the spatial embeddings of the point cloud inputs using a second neural network to generate a spatio-temporal embedding that characterizes the point cloud inputs in the temporal sequence.

Abstract: Compounds are provided having inter alia good duration of action, high potency and/or convenient dosing regimens including once weekly administration. The compounds are engineered polypeptides which incorporate an albumin binding domain in combination with one or more biologically active polypeptides. Also provided are pharmaceutical compositions and methods of treatment for diseases and disorders including lipodystrophy, dyslipidemia, hyperlipidemia, overweight, obesity, hypothalamic amenorrhea, Alzheimer's disease, leptin deficiency, fatty liver disease or diabetes (including type I and type II). Additional diseases and disorders which can be treated by the compounds and methods described herein include nonalcoholic steatohepatitis (NASH) and nonalcoholic fatty liver disease (NAFLD), metabolic syndrome X and Huntington's Disease.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting the intent of an agent in an environment. One of the methods includes obtaining context data characterizing an environment, the context data comprising data characterizing a plurality of agents in the environment; and generating, based on processing the context data using a neural network having a plurality of network parameters, a respective predicted stationary state classification over a plurality of categories for each of one or more target agents of the plurality of agents in the environment, the categories including one or more categories that indicate that the target agent is a stationary non-participant of traffic in the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for open vehicle doors prediction using a neural network model. One of the methods includes: obtaining sensor data (i) that includes a portion of a point cloud generated by a laser sensor of an autonomous vehicle and (ii) that characterizes a vehicle that is in a vicinity of the autonomous vehicle in an environment; and processing the sensor data using an open door prediction neural network to generate an open door prediction that predicts a likelihood score that the vehicle has an open door.

Abstract: The present disclosure relates to the technical field of display devices, in particular, to a rear housing assembly and a display device. The rear housing assembly includes: a rear housing, a back plate, and a connecting assembly. The back plate and the rear housing are disposed oppositely in a thickness direction of the display device. The connecting assembly includes a first connecting part and a second connecting part. One of the first connecting part and the second connecting part is coupled to the rear housing, and the other is coupled to the back plate. The first connecting part includes a limiting cavity extending in the thickness direction, the second connecting part includes a limiting engaging portion, the limiting engaging portion extends into the limiting cavity, and the limiting engaging portion is engaged with the first connecting part.

Abstract: A backlight module includes a front frame (1), a screen (3), and a flexible buffer layer (2) located between the front frame (1) and the screen (3). In a direction from the front frame (1) to the screen (3), a gap between the front frame (1) and the screen (3) is filled with the flexible buffer layer (2); and the flexible buffer layer (2) is in an elastic compression state.

Abstract: Compounds are provided having inter alia good duration of action, high potency and/or convenient dosing regimens including once weekly administration. The compounds are engineered polypeptides which incorporate an albumin binding domain in combination with one or more biologically active polypeptides. Also provided are pharmaceutical compositions and methods of treatment for diseases and disorders including lipodystrophy, dyslipidemia, hyperlipidemia, overweight, obesity, hypothalamic amenorrhea, Alzheimer's disease, leptin deficiency, fatty liver disease or diabetes (including type I and type II). Additional diseases and disorders which can be treated by the compounds and methods described herein include nonalcoholic steatohepatitis (NASH) and nonalcoholic fatty liver disease (NAFLD), metabolic syndrome X and Huntington's Disease.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student machine learning model using a teacher machine learning model that has a pre-trained feature extractor.

Abstract: Aspects of the disclosure provide for the identification of parkable areas. In one instance, observations of parked vehicles may be identified from logged data. The observations may be used to determine whether a sub-portion of an edge of a roadgraph corresponds to a parkable area. In some examples, the edge may define a drivable area in the roadgraph. In addition, map information is generated based on the determination of whether the sub-portion of the edge corresponds to the parkable area.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching an autonomous vehicle sensor data repository. One of the methods includes maintaining a collection of sensor samples and one or more embeddings of each sensor sample. Each sensor sample is generated from sensor data at multiple time steps and characterizes an environment at each of the multiple time steps. Each embedding corresponds to a respective portion of the sensor sample and has been generated by an embedding neural network. A query specifying a query portion of a query sensor sample is received. A query embedding corresponding to the query portion of the query sensor sample is generated through the embedding neural network. A plurality of relevant sensor samples that have embeddings that are closest to the query embedding are identified as characterizing similar scenarios to the query portion of the query sensor sample.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.