Abstract: Systems, methods, and non-transitory computer readable media are configured to determine an interaction between a first entity and a first item. A second entity can be determined. The first entity can have formed a connection with the second entity on a social networking system. A belief that the second entity will interact with the first item can then be generated.

Abstract: Systems, methods, and non-transitory computer-readable media can be configured to determine an issue associated with a media broadcast during the media broadcast. A copy of a portion of the media broadcast associated with the issue can be stored. A stored media broadcast associated with the media broadcast can be repaired based on the copy of the portion of the media broadcast.

Abstract: An online system receives digital content and determines whether the digital content includes malicious content, such as obfuscated text, before presenting the digital content to a user. To determine whether the digital content contains malicious content, the online system renders the digital content. The online system performs optical character recognition on the content. The online system uses an obfuscation machine learning model to identify obfuscated text. The online system may deobfuscate the obfuscated text. The online system may prevent presentation of the digital content in response to detecting obfuscated text.

Abstract: A model visualizer visualizes a neural network model at a neuron level. The model visualizer receives a plurality of instances comprising a plurality of features, and receives a neural network model comprising a plurality of layers, each layer comprising a plurality of neurons. For each neuron of each layer, the model visualizer selects a group of instances that highly activate that neuron to generate a summary feature vector, calculates an average feature value of the summary feature vector, compares each feature value of the summary feature vector with the average feature value, and assigns an attribute to each element of the summary feature vector based on the comparison. The model visualizer visualizes the received neural network model based on the assignment to each neuron.

Abstract: A social networking system obtains financial transaction activity for its users and allows its users to obtain reports of their spending compared to various benchmarks. The benchmarks may be for various demographic groups, networks to which the user belongs, groups of users connected to a user, or any other suitable grouping of users. The social networking system may also forecast a user's spending on a category based on the spending of other users who have similar spending profiles in other categories.

Abstract: One or more embodiments of the disclosure include methods and systems that allows for improved user navigation within a group of content items. For example, a content navigation system can identify a content item within a group of content items to provide to a user in response to a user interaction. In some embodiments, the content navigation system can identify a content item to provide to the user based on one or more factors, such as a characteristic of a user interaction and a relevance of a content item. In addition, the content navigation system can strategically provide advertisement content items to a user by adjusting one or more factors with respect to advertisement content items.

Abstract: In one embodiment, a computing system may receive input data from several artificial-reality systems used by participants to participate in a virtual meeting. The input data may include audio data and sensor data corresponding to the participants while they are in the virtual meeting. The computing system may determine meeting characteristics based on input data. The meeting characteristics may include individual behavioral characteristics for each participant and communal characteristics associated with the participants as a group. The computing system may determine an action to improve a meeting characteristic according to a predetermined criteria and generate an instruction for performing the action. The computing system may send the instruction to one or more of the artificial-reality systems used by the participants. The instructions may be configured to cause an application running on each of the artificial-reality systems that receives the instruction to perform the action.

Abstract: One or more embodiments described herein include methods and systems of capturing and sending multimedia content items as electronic message. More specifically, systems and methods described herein provide users the ability to easily and effectively capture multimedia content items for inclusion in a communication session without navigating away from the communication session. Additionally, systems and methods described herein allow a multimedia content item to be sent to one or more co-users immediately following the capture of the multimedia content item without further user interaction. In other words, the system and methods can capture and automatically send a multimedia content item in response to a single user interaction.

Abstract: An online system provides a feed of content including organic content items and sponsored content items that are positioned relative to each other to maximize user interaction with the feed of content. To reduce latency of providing the feed of content to a user without impairing positioning of organic content items and sponsored content items relative to each other, the online system generates the feed of content including organic content items and sends the feed of content to a client device while selecting sponsored content items for the feed of content. The online system transmits selected sponsored content items to the client device, which modifies the feed of content to include the sponsored content items and presents the modified feed of content.

Abstract: A device (e.g., an integrated circuit chip) includes a dot product processing component, a data alignment component, and an accumulator. The dot product processing component is configured to calculate a dot product of a first group of elements stored in a first storage unit with a second group of elements, wherein: each element of the first group of elements is represented using a first number of bits, each value of a group of values stored in the first storage unit is represented using a second number of bits greater than the first number of bits, and each value of the group of values is stored as split segments across more than one element of the elements of the first group of elements. The data alignment component is configured to receive results of the dot product processing component and modify one or more of the results of the dot product processing component. The accumulator is configured to sum outputs of the data alignment component to at least in part determine a sum of the group of values.

Abstract: A content publisher may transfer an impression token value to a user in response to the content publisher displaying an advertisement for a merchant to the user. The content publisher may record the transfer on a zero knowledge blockchain. The merchant may transfer a conversion token value to the user in response to the user making a purchase from the merchant. The merchant may record the transfer on the zero knowledge blockchain. The user may transfer the impression token value and the conversion token value to a measurement company. The measurement company may calculate attribution and lift results for the advertisement.

Abstract: The disclosed method may include (1) detecting, by a communication resource of a communication system, an event indicative of traffic congestion in the communication resource, where the communication resource services one or more traffic flows, and where at least one of the traffic flows causes the event, (2) sampling, by the communication resource, in relation to detecting the event, status data indicating a current status of the communication resource during each of a plurality of time intervals, (3) transmitting, by the communication resource, to a receiving device external to the communication resource to control the communication system, at least one of (a) at least a portion of the status data that is associated with the at least one of the traffic flows or (b) control information for the at least one of the traffic flows based on that status data. Various other methods and systems are also disclosed.

Abstract: Systems, methods, and non-transitory computer readable media configured to receive an initial targeting for an advertisement. The advertisement can promote a group of a social networking system. A refined targeting for the advertisement can be generated. The advertisement based on the refined targeting can be delivered.

Abstract: In one embodiment, a method includes detecting objects in an image. The method includes accessing a mask for each object. The method includes receiving an input in relation to the image. The input corresponds to an input region and an input type. The method includes identifying a region of the image corresponding to the input region of the input. The identified region of the image includes one or more of the masks. The method includes providing feedback regarding the one or objects in the identified region of the image based on the input type.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a plurality of content items to be presented to a user in a content grid user interface, wherein the content grid user interface is divided into a plurality of columns, the plurality of content items are arranged in an order, and each content item of the plurality of content items is associated with an aspect ratio and a span value indicative of the number of columns the content item will occupy within the content grid user interface. A first content item in the plurality of content items is selected based on the order, wherein the first content item is associated with a first span value and a first aspect ratio. A position within the content grid user interface is determined for the first content item based on the first span value and the first aspect ratio.

Abstract: In one embodiment, a mobile-client system may receive user input from a first user to send a message to a plurality of second users. The user input may include an indication of the first user currently being located at a first geographic location, a time period for which the first geographic location of the first user is visible to the plurality of second users, and one or more content items shared by the first user. The mobile-client system may send the message to one or more second users selected from the plurality of second users. The mobile-client system may receive a notification referencing one or more of the selected second users to whom the message was sent. The notification may include an indication of one or more second geographic locations shared by the one or more of the selected second users.

Abstract: Systems and methods for creating automatic digital representations of events may include (1) transmitting a preview segment of a recommended media item to a user's device for presentation within a media consumption interface presented within a display element of the device, (2) receiving, from the device, an indication that the user has selected a user-selectable save element presented in association with the preview segment within the media consumption interface, and (3) in response to receiving the indication, adding a full-length version of the recommended media item to a digital container maintained for the user. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Disclosed is a system for connecting to an online meeting room with multiple people. A first client device of a first user initiates a connection to the online meeting room. After the connection has been initiated, the first client device starts receiving video data and audio data from one or more client devices of one or more other users connected to the online meeting room. While connected to the online meeting room, the first client device displays a video stream based on the received video data from the one or more client device of the one or more other users connected to the online meeting. Upon receiving a request from a second user to start a conversation with the first user, the first client device plays an audio stream based on the audio data received from the client device of the second user.

Abstract: In one embodiment, a method includes accessing visual data from a client system associated with a user, wherein the visual data comprises images portraying one or more objects, receiving, from the client system, a user request, wherein the user request comprises a coreference to a target object, resolving the coreference to the target object from among the one or more objects, resolving the target object to a specific entity, and sending, to the client system, instructions for providing a response to the user request, wherein the response comprises attribute information about the specific entity.

Abstract: A processor system comprises a hardware channel convolution processor unit and dot product processor unit. The channel convolution processor unit is configured to perform depthwise convolution, including by multiplying each data element of a first group of data elements of a convolution data matrix with a corresponding data element of a second group of data elements of a plurality of depthwise convolution weight matrices and summing together, for each specific channel, multiplication results corresponding to the specific channel to determine one corresponding result data element in a corresponding channel convolution result matrix to calculate a portion of depthwise convolution results.