Abstract: In one embodiment, a method includes receiving a first user request from a first user for generating a media montage from a client system during a dialog session with the first user, generating an initial media montage during the dialog session based on media collections associated with the first user, sending instructions for presenting the initial media montage to the client system during the dialog session, receiving a second user request from the first user from the client system during the dialog session for editing the initial media montage, generating an edited media montage from the initial media montage during the dialog session based on the second user request and a memory graph associated with the first user, and sending instructions for presenting the edited media montage to the client system during the dialog session.

Abstract: The disclosed computer-implemented method may include systems and methods for embedding specific data into a call stack associated with an application session. For example, the systems and methods described herein can initialize a program thread that sequentially executes specialized application functions based on characters of a unique identifier to embed the unique identifier within a call stack of the application session. The systems and methods further provide the unique identifier in connection with other data sources associated with the application session such that further analysis of all data associated with the application session may be cross-referenced according to the unique identifier. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: In one embodiment, a method includes accessing a decoded hypothesis corresponding to an utterance, computing a predicted probability of observing each token in the decoded hypothesis by having a local first machine-learning model process the decoded hypothesis, computing a confidence score for each token in the decoded hypothesis by having a second machine-learning model process the decoded hypothesis, where the confidence score indicates a degree of confidence for the token to be observed at its position, calculating a loss for the computed predicted probabilities of observing tokens in the decoded hypothesis based on the computed confidence scores, and updating parameters of the local first machine-learning model based on the calculated loss.

Abstract: An image processing system enables a user wearing a head-mounted display to experience a virtual environment combined with a representation of a real-world object. The image processing system receives a captured scene of a real-world environment that includes a target object. The image processing system identifies the target object in the captured scene and generates a representation of the target object. In some cases, the image processing system may include a graphical overlay with the representation of the target object. The image processing system can generate a combined scene that includes the target object and the virtual environment. The combined scene is presented to the user, thereby allowing the user to interact with the real-world target object (or a representation thereof) in combination with the virtual environment.

Abstract: In one embodiment, a method includes by a client system associated with a user, receiving, at the client system, a user input from the user, parsing, by the client system, the first user input to identify a request to execute a function to be performed by an assistant system of several assistant systems associated with the client system, determining whether the user is authorized to access the assistant system by comparing a voiceprint of the user to several voiceprints stored on the client system, sending, from the client system to the assistant system in response to determining the user is authorized to access the assistant system, a request to set an assistant xbot of the assistant system into a listening mode, and receiving, at the client system from the assistant system, an indication that the assistant xbot is in listening mode.

Abstract: In one embodiment, a method includes receiving a first user input from a first user, wherein the first user input comprises a partial request, presenting one or more suggested intent auto-completions corresponding to the partial request, receiving a selection by the first user of a first suggested intent auto-completion of the suggested intent auto-completions and a second user input, presenting one or more suggested slot auto-completions corresponding to one or more candidate slot-hypotheses corresponding to the second user input, respectively, wherein each of the candidate slot-hypotheses comprise a slot-suggestion, and wherein each suggested slot auto-completion comprises the second user input and the corresponding candidate slot-hypothesis, receiving a selection by the first user of a first suggested slot auto-completion of the suggested slot auto-completions, and presenting execution results of one or more tasks corresponding to the first suggested intent auto-completion and the first suggested slot auto

Abstract: In one embodiment, a method includes receiving a first user input comprising a wake word associated with an assistant xbot from a first client system, setting the assistant xbot into a listening mode, wherein a continuous non-visual feedback is provided via the first client system while the assistant xbot is in the listening mode, receiving a second user input comprising a user utterance from the first client system while the assistant xbot is in the listening mode, determining the second user input has ended based on a completion of the user utterance, and setting the assistant xbot into an inactive mode, wherein the non-visual feedback is discontinued via the first client system while the assistant xbot is in the inactive mode.

Abstract: In one embodiment, a method includes accessing visual signals comprising images portraying textual content in a real-world environment associated with a first user from a client system associated with the first user, recognizing the textual content based on machine-learning models and the visual signals, determining a context associated with the first user with respect to the real-world environment based on the visual signals, executing tasks determined based on the textual content and the determined context for the first user, and sending instructions for presenting execution results of the tasks to the first user to the client system.

Abstract: Systems, apparatuses and methods provide technology that compresses first data based on a first compression scheme to generate second data, where the first data is associated with a first machine learning model. The technology stores the second data into a memory, adjusts a first entry of a lookup table to correspond to the first compression scheme based on the first data being compressed based on the first compression scheme, provide the second data from the memory to processing elements of a processing array during execution of the first machine learning model, and decompresses, at the processing array, the second data based on the lookup table to obtain the first data.

Abstract: One variation of a method for selectively advertising items in an image includes: loading an image to a social feed; receiving a first tag and a second tag including identification of a first item and a second item visible in the image, respectively; based on the first tag and the second tag, correlating the first item with a first product and the second item with the second product; based on the first product and the second product, sourcing a first link to a first electronic storefront and a second link to a second electronic storefront that facilitate purchase of the first product and the second product, respectively; and selectively displaying a first visual cue of the first link and a second visual cue of the second link to a first user and to a second user, respectively, according to demographics of the first user and the second user.

Abstract: One or more embodiments of the disclosure include systems and methods that generate and utilize digital visual codes. In particular, in one or more embodiments, the disclosed systems and methods generate digital visual codes comprising a plurality of digital visual code points arranged in concentric circles, a plurality of anchor points, and an orientation anchor surrounding a digital media item. In addition, the disclosed systems and methods embed information in the digital visual code points regarding an account of a first user of a networking system. In one or more embodiments, the disclosed systems and methods display the digital visual codes via a computing device of the first user, scan the digital visual codes via a second computing device, and provide privileges to the second computing device in relation to the account of the first user in the networking system based on the scanned digital visual code.

Abstract: In one embodiment, a method includes accessing from a client system associated with a first user sensor signals captured by sensors of the client system, wherein the client system comprises a plurality of sensors, and wherein the sensors signals are accessed from the sensors based on cascading model policies, wherein each cascading model policy utilizes one or more of a respective cost or relevance associated with each sensor, detecting a change in a context of the first user associated with an activity of the first user based on machine-learning models and the sensor signals, wherein the change in the context of the first user satisfies a trigger condition associated with the activity, and responsive to the detected change in the context of the first user automatically capturing visual data by cameras of the client system.

Abstract: In one embodiment, a method includes receiving one or more voice inputs from a first user, determining a first language register associated with the first user based on the one or more voice inputs, selecting a second language register for a voice response based on the one or more voice inputs, generating the voice response based on the second language register, and providing the voice response in response to the one or more voice inputs.

Abstract: In one embodiment, a method includes receiving touch inputs from a user corresponding to an activation trigger for an assistant system executing on a head-mounted device at the head-mounted device, accessing signals from inertial measurement unit (IMU) sensors of the head-mounted device by the head-mounted device, determining that the user is either donning or doffing the head-mounted device by an on-device don/doff detection model and based only on the signals from the IMU sensors, and overriding the activation trigger to prevent an activation of the assistant system responsive to the received touch inputs.

Abstract: In one embodiment, a method includes receiving, from a client system of a user, a user input comprising a plurality of n-grams, parsing the user input to identify one or more overall intents, hidden intents, and slots associated with the one or more n-grams, wherein at least one of the hidden intents is non-resolvable for being associated with partial slot information corresponding to an n-gram that has not been resolved to a particular entity identifier, wherein the partial slot information is associated with two more entity identifiers of two or more entities, respectively, sending, to the client system, instructions for prompting the user to select one of the entities to be associated with the non-resolvable hidden intent, resolving the non-resolvable hidden intent based on the entity identifier of the entity selected by the user, and generating a response to the user input based on the resolved hidden intent.

Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.