Abstract: In one embodiment, a method includes receiving a request for a games tab on a messaging application running on a client system of a first user; identifying one or more games played by the first user; identifying, for each identified game, one or more message threads associated with the first user and the respective game; ranking the identified games based on one or more first criteria; ranking the one or more message threads associated with each identified game based on one or more second criteria; and sending instructions for presenting the games tab on the messaging application. The games tab may comprise a list of one or more of the identified games presented in ranked order, and, for each game, one or more message threads associated with the respective game presented in ranked order.

Abstract: A composite optical element includes a first optical component and a second optical component. The first optical component includes a first front surface, a first back surface, and a first junction surface. The second optical component that includes an end surface, a second front surface, a second back surface, and a second junction surface. The first front surface and the second front surface together form a first surface of the composite optical element, and the first back surface and the second back surface together form a second surface of the composite optical element. The second junction surface is coupled to the first junction surface to form a beam splitter that transmits light in a first band and reflects light in a second band toward the end surface.

Abstract: A hand tracking system includes a wearable device configured to be worn on a user's wrist. The wearable device includes one or more transmitters, at least one receiver, and a controller. The transmitters generate an electric field that is altered by movement of a hand, fingers, and/or wrist of the user. The wearable device may also include one or more microphones that are configured to detect taps and so forth by one or more fingers of the hand. In some embodiments, the microphones are positioned such that they detect the taping my monitoring acoustic waves propagating through the tissue of the hand. The controller uses information captured by the receivers and/or the microphones and a model (e.g., machine learning model) to recognize a hand gesture.

Abstract: An exemplary method of generating content for a user of a social networking service includes, in an application of a social networking service, receiving a classification model from a server system associated with the social networking service. The method further includes detecting content items stored on the client device independently of the application. The method further includes generating content for a user of the social networking service that includes a set of content items from the detected content items, based at least in part on metadata for the set of content items. The metadata is stored at the client device. The method further includes, in accordance with a determination that the generated content for the user satisfies a criterion included in the classification model, presenting the content to the user in the application.

Abstract: The disclosed method for performing content-based transcoding of images may include determining an image, calculating an extraction-feature set based on content of the image, calculating a distance measure based on the extraction-feature set according to an image recognition model, determining an image type for the image based on the distance measure, and storing the image according to the image type. When the image type of the image is a first image type, the disclosed computer-implemented method may generate a transcoded image from the image, store the transcoded image at a content-provider computing system, and refrain from storing the image at the content-provider computing system. Alternatively, when the image type of the image is a second image type, the disclosed computer-implemented method may refrain from generating the transcoded image from the image and store the image at the content-provider computing system. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for manufacturing a display element comprising a plurality of pixels, each comprising a plurality of sub-pixels. The method comprises undertaking, using a pick up tool, a first placement cycle (1908) comprising picking up a plurality of first, untested LED dies and placing them on a display substrate at locations corresponding to the plurality of pixels, testing (1912) the first LED emitters on the display substrate to determine one or more locations of non-functional first LED emitters, selecting one or more second tested LED dies based on a result of the test, configuring the selected one or more second LED dies to enable their pick up and placement on the display substrate and undertaking, using the PUT, a second placement cycle (2008) comprising picking up the selected one or more second LED dies and placing them on the display substrate at the determined locations of the non-functional first LED emitters.

Abstract: Exemplary embodiments relate to techniques for identifying messaging robots, or bots, to surface in response to a request. For example, in order to facilitate increased interaction between a user and a bot, a list of candidate bots that the user is likely to be interested in may be surfaced to the user in response to a search for a bot or a request that a bot perform a particular task. Identifying the bots may be accomplished by generating a list of candidate bots and filtering the list based on filtering metrics. Then, the remaining bots may be ranked based on ranking metrics, and the top bots in the ranking may be returned. In some embodiments, two sets of ranks may calculated: one for retention rate, and another rank for the number of messages sent and received by the bots.

Abstract: This disclosure covers methods, non-transitory computer readable media, and systems that receive a direct digital message for delivery to a recipient and then generate a relevance score representing the direct digital message's relevance to the recipient. The relevance score accounts for either or both of crowdsourced information and social-network signals. Based on the relevance score, the methods, non-transitory computer readable media, and systems either provide the direct digital message to the recipient's client device for display within a received-messages preview or provide the message to the recipient's client device for sequestration within a sequestration folder.

Abstract: Embodiments relate to a head-mounted display including an eye tracking system. The eye tracking system includes a source assembly, a camera, and a controller. In some embodiments, the source assembly is a plurality of sources and are positioned to illuminate at least a peripheral area of a cornea of an eye. In some embodiments, the sources are masked to be a particular shape. The peripheral region is a location on the eye where the cornea transitions to the sclera. In some embodiments, the camera can detect a polarization of the reflected light, and uses polarization to disambiguate possible reflection locations. Similarly, time of flight may also be used to disambiguate potential reflection locations. The controller uses information from the detector to track positions of the user's eyes.

Abstract: A method for generating an individualized audio output response for a headset based on a representation of a user's ear. One or more images of a portion of a user's head including at least the user's ear are received. A representation of the user's ear is generated based in part on the one or more images. A simulation of sound propagation from an audio source to the user's ear is performed based on the representation. An individualized audio output response is generated for the user based on the simulation, the individualized audio output response configured to adjust one or more acoustic parameters of audio content provided to the user by the headset.

Abstract: An online system provides group recommendations by applying a set of sourcing rules to identify a plurality of candidate groups and then generating scores for the candidate groups. The sourcing rules can be configured to identify a relatively small subset of the groups maintained by the online system. After the candidate groups are identified, the online system generates a score for each candidate group, ranks the candidate groups based on the scores, and sends high-ranking candidate groups to the target user to be displayed as recommended groups. As a result, the online system generates a smaller number of scores, which advantageously allows for the online system to provide group recommendations to users in a more computationally efficient manner.

Abstract: In one embodiment, a computing system may access a first image and a second image of at least a common portion of an environment while a light emission with a predetermined emission pattern is projected by a projector. The first and second images are respectively captured by a first and a second detector that are respectively separated from the projector by a first and a second distance. The system may determine that a first portion of the first image corresponds to a second portion of the second image. The system may compute, using triangulation, a first depth value associated with the first portion and a second depth value associated with the second portion. The system may determine that the first and second depth values match in accordance with one or more predetermined criteria, and generate a depth map of the environment based on at least one of the depth values.

Abstract: In one embodiment, a method includes receiving an indication a first user is accessing a game, wherein the first user has a first user identifier (ID); generating, based on the first user ID, a first hashed ID for the first user; providing the first hashed ID to a game bot associated with the game, the game bot being a software agent configured to act automatically on behalf of the game; receiving, from the game bot, a request to initiate a message thread between the game bot and the first user on a messaging application running on a first client system of the first user; and sending instructions for presenting the message thread on the messaging application, the message thread comprising one or more messages referencing in-game actions in the game.

Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first video frame and a second video frame. The first video frame can be processed using a convolutional neural network to output a first set of feature maps. The second video frame can be processed using the convolutional neural network to output a second set of feature maps. The first set of feature maps and the second set of feature maps can be processed using a spatial matching layer of the convolutional neural network to determine an optical flow for at least one pixel.

Abstract: A method of generating respective adaptations of digital content for display by multiple computing devices is recited. In one embodiment, a server determines whether multiple client computing devices are in physical proximity to one another. If multiple computing devices are in physical proximity to one another, respective adaptations of digital content are generated. Each respective content adaptation presents a different content view which is configured for a specific one of the computing devices. Each content adaptation is configured for synchronous presentation on the computing devices with the other content adaptations. The content adaptations are then sent to the computing devices.

Abstract: A head mounted display (HMD) comprises an eye tracking system configured to enable eye-tracking using light. The eye tracking system implements time-multiplexing by configuring a source assembly comprising a plurality of light sources to project at least a first light pattern towards the user's eye over a first time period, and a second light pattern towards the user's eye over a second time period in accordance with a set of emission instructions. A camera assembly is configured to capture images of the user's eye during the first and second time periods in accordance with a set of imaging instructions, the captured images containing one or more glints corresponding to reflections of the first or second light patterns on the cornea of the user's eye. The location of the glints may be used to determine a shape or orientation of the eye.

Abstract: In one embodiment, an interference-management system of a multi-hop wireless network may access an interference map indicating interference among network nodes, each network node comprising sectors that each comprise an array of beamforming antennae. The interference-management system may identify links between network nodes, each link being associated with a transmitting (TX) beamforming weight variable and a receiving (RX) beamforming weight variable. The interference-management system may generate a factor-graph representation of the multi-hop wireless network comprising a first set of vertices corresponding to a second set of vertices, each vertex pair being associated with an identified link, wherein each vertex pair comprises a variable node and a function node, and wherein messages passed between the nodes of a first vertex pair are derived at least in part based on messages previously passed between the nodes of one or more vertex pairs.

Abstract: A method is performed at a virtual-reality system that includes a head-mounted display (HMD) and a hand-held controller. The hand-held controller includes a grip, a user-input surface, and a tracking ring. the user-input surface includes a user-input key that is mounted on the grip, and the user input key includes an analog pressure sensor. The tracking ring is coupled to the user-input surface and the tracking ring includes a plurality of illumination sources on an outer surface of the tracking ring. The method displays an image of a hand on the HMD, and senses pressure applied to the analog pressure sensor by a user holding the hand-held controller and wearing the HMD. The method displays, on the HMD, the degree of closing the image of the hand in proportion to the pressure applied to the analog pressure sensor.

Abstract: In one embodiment, a method includes accessing an image of a physical world scene, detecting a number of straight-line segments in the accessed image, identifying a first vanishing point and a second vanishing point in the image, where each vanishing point corresponds to a sub-set of the number of straight-line segments, and where the first vanishing point and the second vanishing point are orthogonal, identifying a planar region in the accessed image represented by one or more straight-line segments associated with the first vanishing point and one or more straight-line segments associated with the second vanishing point, transforming a virtual object associated with the planar region based on one or more properties associated with the planar region, and displaying the transformed virtual object over the image.

Abstract: A method for performing client-side content inference may include (1) receiving a request to upload, from a client-side device to a server-side device, a content item that includes a first sequence of bytes and a second sequence of bytes, (2) identifying a model configured to output a classification for sequences of bytes, (3) using, at the client-side device, the model to derive a first classification for the first sequence, (4) using, at the client-side device, the model to derive a second classification for the second sequence, and (5) uploading, in response to the request, the content item to the server-side device by (a) uploading the first sequence, (b) uploading the first classification substantially contemporaneous with uploading the first sequence, (c) uploading the second sequence, and (d) uploading the second classification substantially contemporaneous with uploading the second sequence. Various other methods, systems, and computer-readable media are also disclosed.