Abstract: Implementations described herein generally relate to generating a modification selectable element that may be provided for presentation to a user in a smart dictation session with an automated assistant. The modification selectable element may, when selected, cause a transcription, that includes textual data generated based on processing audio data that captures a spoken utterance and that is automatically arranged, to be modified. The transcription may be automatically arranged to include spacing, punctuation, capitalization, indentations, paragraph breaks, and/or other arrangement operations that are not specified by the user in providing the spoken utterance. Accordingly, a subsequent selection of the modification selectable element may cause these automatic arrangement operation(s), and/or the textual data locationally proximate to these automatic arrangement operation(s), to be modified.

Abstract: Example aspects of the present disclosure are directed to systems and methods that learn a compressed representation of a machine-learned model (e.g., neural network) via representation of the model parameters within a reparameterization space during training of the model. In particular, the present disclosure describes an end-to-end model weight compression approach that employs a latent-variable data compression method. The model parameters (e.g., weights and biases) are represented in a “latent” or “reparameterization” space, amounting to a reparameterization. In some implementations, this space can be equipped with a learned probability model, which is used first to impose an entropy penalty on the parameter representation during training, and second to compress the representation using arithmetic coding after training. The proposed approach can thus maximize accuracy and model compressibility jointly, in an end-to-end fashion, with the rate-error trade-off specified by a hyperparameter.

Abstract: Disclosed is the technology for computer-based “Daily Brief” service, which includes methods and corresponding systems for proactively providing push notifications for users of chat information systems. The push notifications are dynamically generated and presented to the user based on identification of one or more triggering events, which may include predetermined time/date, current geographical location, activity of peers and friends in social media associated with the user, scheduled events, appointments, meetings, emails, instant messages, and many more. The described technology improves the interaction interface between the user and chat information system.

Abstract: A computer-implemented method for compressing computer-readable data having improved efficiency can include obtaining, by a computing system including one or more computing devices, input data associated with the computing system; and encoding, by the computing system, the input data and added noise from a noisy channel to produce encoded data based at least in part on an encoder model, wherein encoding the input data and added noise includes additively combining the added noise and the input data to obtain noisy input data and rounding the noisy input data by a soft rounding function, the soft rounding function having a sharpness, to produce the encoded data, wherein the machine-learned encoder model is trained on training data, wherein the training data is encoded with the added noise from the noisy channel.

Abstract: Implementations set forth herein relate to interactions, between vehicle computing devices and mobile computing devices, that reduce duplicative processes from occurring at either device. Reduction of such processes can be performed, in some instances, via communications between a vehicle computing device and a mobile computing device in order to determine, for example, how to uniquely render content at an interface of each respective computing device while the user is driving the vehicle. These communications can occur before a user has entered a vehicle, while the user is in the vehicle, and/or after a user has left the vehicle. For instance, just before a user enters a vehicle, a vehicle computing device can be primed for certain automated assistant interactions between the user and their mobile computing device. Alternatively, or additionally, the user can authorize the vehicle computing device to perform certain processes immediately after leaving the vehicle.

Abstract: The technology relates to a navigation system that provides one or more routes from a starting location to a destination location, including a candidate parking location at or near the destination location. The starting location may be the current location of a user or the parking location from a previous navigation session. In some examples, the current location of the user may be the same location as the parking location from the previous navigation session. Each route suggestion may include one or more segments. For example, a route may include a first segment from the location of the user to the candidate parking spot and a second segment may be from the candidate parking location to the destination location. In some examples, there may be a third segment from the user's current location to the parking location from the previous navigation session.

Abstract: Methods, systems and apparatus for simulating a physical system described by an electronic structure Hamiltonian expressed in an orthonormal basis. In one aspect, a method includes decomposing the electronic structure Hamiltonian into a sum of sub-Hamiltonians, wherein each sub-Hamiltonian in the sum of sub-Hamiltonians is expressed in one of multiple bases; simulating evolution of the physical system using the decomposed electronic structure Hamiltonian; and using the simulated evolution of the physical system using the decomposed electronic structure Hamiltonian to determine properties of the physical system.

Abstract: Systems and methods are provided for multimodal input collection. More particularly, the present disclosure relates to efficient and intuitive multimodal input collection for mobile devices. As an example, a mobile computing system (e.g., a smartphone, a tablet, a wearable device, etc.) can display a lock screen interface at a display device associated with the mobile computing system (e.g., an initial interface that requests interaction and/or authentication from the user before granting access to applications, etc.).

Abstract: Techniques are described herein for segmenting source code into syntactically coherent sequences of tokens that satisfy constraints inherent in sequence-to-sequence networks. In various implementations, source code may be processed to generate one or more graphs representing the source code. One or more of the graphs may then be traversed to identify one or more sequences of tokens within the source code that satisfy an input constraint of a sequence-to-sequence network. The source code may be segmented into the identified one or more sequences of tokens. The one or more sequences of tokens may then be processed using the sequence-to-sequence network.

Abstract: A device automatically segments an image into different regions and automatically adjusts perceived exposure-levels or other characteristics associated with each of the different regions, to produce pictures that exceed expectations for the type of optics and camera equipment being used and in some cases, the pictures even resemble other high-quality photography created using professional equipment and photo editing software. A machine-learned model is trained to automatically segment an image into distinct regions. The model outputs one or more masks that define the distinct regions. The mask(s) are refined using a guided filter or other technique to ensure that edges of the mask(s) conform to edges of objects depicted in the image. By applying the mask(s) to the image, the device can individually adjust respective characteristics of each of the different regions to produce a higher-quality picture of a scene.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a packet from a client, the packet having header information including a destination Internet Protocol (IP) address, a destination port, a source IP address, and a source port, and wherein the source IP address and source port are associated with the client; selecting a destination virtual machine based on the destination port; modifying the packet by replacing the destination IP address in the header information with an IP address of the selected destination virtual machine; and sending the modified packet to the destination virtual machine.

Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.

Abstract: A method of updating a playlist for a first user includes identifying a client device associated with the first user of a content sharing platform that comprises a plurality of media items, identifying a first playlist of the first user, the first playlist including a first subset of media items, identifying a second subset of media items of the second user, detecting an action performed by the first user with respect to at least one media item of the second subset of media items of the second user, the action performed by the first user indicates interest of the first user in the at least one media item of the second user, and automatically adding the at least one media item of the second user to the first playlist of the first user.

Abstract: A method for unifying transformers with document signals includes obtaining a training sequence of tokens from a web page. The training sequence of tokens may represent text and the web page is associated with one or more web page signals. Each web page signal includes information relevant to the entire training sequence of tokens. The method includes determining, using the training sequence of tokens, an attention matrix. The attention matrix includes a plurality of weights and the plurality of weights direct focus of a machine learning model on inputs provided to the machine learning model. The method includes adjusting the attention matrix using the one or more web page signals and providing, to the machine learning model, an inference sequence of tokens. The method includes generating, by the machine learning model, a prediction based on the inference sequence of tokens and the adjusted attention matrix.

Abstract: A method for docking a tablet computer to a tablet computer case includes magnetically coupling a first pivot magnet of the tablet computer case to a second pivot magnet of the tablet computer, pivoting the tablet computer toward the tablet computer case, and magnetically coupling a first plurality of docking magnets of the tablet computer case to a second plurality of docking magnets of the tablet computer. The first pivot magnet magnetically couples to the second pivot magnet prior to the first plurality of docking magnets magnetically coupling to the second plurality of docking magnets. A tablet computer case system includes a tablet computer case including a first portion and a second portion. The tablet computer case includes a first plurality of docking magnets arranged on the first portion and a first pivot magnet arranged along a perimeter of the first portion opposite the hinge.

Abstract: Various arrangements for using a short-range wireless communication link are presented herein. A wireless communication device can transmit data using an asynchronous connection-oriented logical transport (ACL) of the short-range wireless communication link. Monitoring for a high throughput event on the ACL of the short-range wireless communication link can be performed. Based on detecting the high throughput event on the ACL, a first physical layer (PHY) symbol rate of the ACL can be increased to a second PHY symbol rate.

Abstract: The present document describes a video-recording doorbell. In aspects, the video-recording doorbell provides a compact, space-efficient, electronic-doorbell camera device. Thermal control is enhanced by dividing the heat sink into separate sections for different heat-dissipating subassemblies. The video-recording doorbell includes a robust waterproofing system that enables mechanical movement of the button when a user presses the button to initiate a chime event. For an enhanced user experience, the video-recording doorbell also includes a mounting system that is easy to install and provides added security against theft.

Abstract: Methods, systems, and apparatus are described for processing mutations for a remote database. In one aspect, a method includes receiving a log of database mutations from a client device, the log of database mutations indicating changes previously made to a client version of a database stored on the client device, and each database mutation specifying: an entity included in the database; an operation for the entity; and a client version number for the entity; identifying, in the log of database mutations, two or more database mutations that each specify a same client version number for a same entity; determining, based on a conflict resolution policy, that the two or more database mutations are eligible for collapsing; and collapsing the two or more database mutations into a single database mutation.