Abstract: A media application obtains transcribed text from audio associated with a video communication session. The media application provides, to a text-generation machine-learning model, the transcribed text. The text-generation machine-learning model outputs a text prompt based on the transcribed text, where the text prompt includes an entity in the transcribed text. The media application provides the text prompt to an image-generation machine-learning model. The image-generation machine-learning model outputs a generated image that is responsive to the text prompt, where the generated image includes a depiction of the entity in the transcribed text. The media application causes the generated image to be displayed in the video communication session.

Abstract: Systems and methods for virtual meeting background freeze may include determining that a background of a video stream of a first client device of a participant of a virtual meeting is to be modified; identifying a first frame of the video stream as a candidate for the background of the video stream; and for each of one or more second frames of the video stream, generating a composite image by superimposing an image of a participant depicted in a respective second frame of the one or more second frames of the video stream on the background of the first frame using a location and a size of the image of the participant with respect to the respective second frame, and causing the composite image to be presented in a virtual meeting user interface (UI) on a second client device in place of the respective second frame.

Abstract: Systems and methods for providing visual indicators of improvement actions performed during a virtual meeting. A virtual meeting user interface (UI) is provided for presentation during a virtual meeting for presentation on a user device of a user participating in the virtual meeting. An artificial intelligence (AI)-based action performed to improve audio quality for the user device during the virtual meeting is identified. Upon identifying the AI-based action, the virtual meeting UI of the user device is caused to be modified during the virtual meeting to include a UI feature notifying the user of the AI-based action.

Abstract: A method for providing an unobtrusive self-view to participants of a virtual conference is provided. The method includes receiving a self-view video stream including a self-view of a user participating in a virtual meeting. The video stream is being acquired by a camera of the client device. The method includes causing the self-view video stream to be presented in a first self-view portion incorporated into a graphical user interface (GUI) control panel of a GUI displayed on the client device of the user. The GUI control panel can include a first control element to control the camera. The method can further include receiving a switch self-view command of the user, and responsive to receiving the switch self-view command, causing the self-view video stream to be presented in a second self-view portion located outside of the GUI control panel of the GUI displayed on the client device of the user.

Abstract: A method for identifying a virtual meeting for absent user participation includes identifying, by a calendar application of a first user and based on one or more calendar event criteria, a calendar event that corresponds to a virtual meeting. The first user of the calendar application may be invited to attend the virtual meeting. The method includes causing a calendar application UI to be presented to the first user. The calendar application UI may include a UI element requesting that virtual meeting information be provided to the first user who is unable to attend the virtual meeting. The method includes, in response to a user activation of the UI element, providing a virtual meeting information request of the first user to a virtual meeting application.

Abstract: Aspects of the disclosure are directed to automatic note taking and summary generation based on meeting discussions. Media streams that are generated by participants of a virtual meeting can be provided as input data to an artificial intelligence (AI) model. The AI model can use the received input data to take notes on the portion of the virtual meeting that is captured in the input data and to generate a summary of the portion of the virtual meeting that is captured in the input data. The meeting summaries can be provided for presentation to the participants of the virtual meeting at predetermined time intervals.

Abstract: Aspects of the disclosure are directed to querying an artificial intelligence chatbot based on meeting discussions. Media streams that are generated by participants of a virtual meeting can be provided as input data to an artificial intelligence (AI) model. The AI model can generate one or more summaries of one or more portions of the virtual meeting based on the input data. The AI model can receive, via an AI chatbot, user queries pertaining to the virtual meeting. The AI model can generate responses to user queries based on the information within the one or more summaries and/or relevant corpus data.

Abstract: A method includes obtaining input of a first user that has been invited to participate in a virtual meeting. The input indicates the first user is requesting attendance of the virtual meeting by proxy. The input provides first data to be discussed during the virtual meeting. The method includes causing a virtual meeting UI presented during the virtual meeting to include a first region corresponding to the first user. The first region includes at least a portion of the first data. The method includes, during a discussion of the first data during the virtual meeting, detecting an indication of a task to be performed and generating a prompt identifying the task as input to a generative AI model. The method includes causing second data to be presented in the virtual meeting UI. The second data may be based on an output of the generative AI model.

Abstract: Aspects of the disclosure are directed to multi-media summary generation based on meeting discussions. A virtual meeting user interface (UI) can be presented during a virtual meeting between a plurality of participants. A command can be received, via the virtual meeting UI, a from a first participant of the plurality of participants to enable automatic note taking. A meeting summary of the virtual meeting can be generated, wherein the meeting summary includes a plurality of embedded references, wherein each embedded reference of the plurality of embedded references identifies at least one corresponding portion of media streams generated by a plurality of client devices associated with the plurality of participants of the virtual meeting. The meeting summary can be provided to the first participant.

Abstract: A method includes causing a virtual meeting UI to be presented during a virtual meeting between one or more participants. The virtual meeting UI may include one or more first regions each corresponding to a participant of the one or more participants. The virtual meeting UI may include a second region corresponding to a presentation of content by a first participant. The method includes determining, using an AI model and using at least a first portion of a transcript of the virtual meeting as input to the AI model, that a second participant is interested in accessing the content outside of the virtual meeting UI. The method includes causing the content to be accessible to the second participant outside of the virtual meeting UI.

Abstract: A method for participation, in a virtual meeting, of an absent invited virtual meeting user includes receiving input of a first user that has been invited to participate in the virtual meeting. The input of the first user indicates an inability to attend the virtual meeting and provides first data to be discussed during the virtual meeting. The method includes causing a virtual meeting UI to be presented during the virtual meeting between multiple participants. The UI includes a UI element associated with the first data provided by the first user that is not present during the virtual meeting. The method includes generating a summary of the virtual meeting. The summary covers presentation of at least a portion of the first data during the virtual meeting. The method includes causing the summary to be accessible by a client device of the first user.

Abstract: A method for a real-time teleprompter for a virtual meeting includes causing, during a virtual meeting between one or more participants, a first virtual meeting UI to be displayed to a first participant. The first participant is a current presenter. A first audio stream produced by a client device of the first participant pertains to a presentation of the first participant. The first virtual meeting UI includes a first region displaying teleprompter notes for the presentation of the first participant. The method includes identifying, using an AI model and using the first audio stream as input to the AI model, a first portion of the teleprompter notes that corresponds to a first presentation segment currently covered by the first participant. The method includes causing the first region displaying the teleprompter notes to include a first visual indication that is associated with the first portion of the teleprompter notes.

Abstract: Systems and methods for virtual meeting background freeze may include determining that a background of a video stream of a first client device of a participant of a virtual meeting is to be modified; identifying a first frame of the video stream as a candidate for the background of the video stream; and for each of one or more second frames of the video stream, generating a composite image by superimposing an image of a participant depicted in a respective second frame of the one or more second frames of the video stream on the background of the first frame using a location and a size of the image of the participant with respect to the respective second frame, and causing the composite image to be presented in a virtual meeting user interface (UI) on a second client device in place of the respective second frame.

Abstract: A method includes causing presentation of a virtual meeting UI during a virtual meeting. The virtual meeting UI includes one or more regions corresponding to video streams associated with meeting participants. The method includes determining that a background of a first region is to be modified in the virtual meeting UI. The method includes identifying a first frame of the first video stream as a candidate for the background of the first region. The method includes generating, using a first generative AI model and using the first frame as input to the first generative AI model, an enhanced background image. The method includes, for each of one or more second frames of the first video stream, generating a composite image by superimposing an image of the first participant on the enhanced background image and causing the composite image to be presented in the first region of the virtual meeting UI.

Abstract: A method for providing an unobtrusive self-view to participants of a virtual conference is provided. The method includes receiving a self-view video stream including a self-view of a user participating in a virtual meeting. The video stream is being acquired by a camera of the client device. The method includes causing the self-view video stream to be presented in a first self-view portion incorporated into a graphical user interface (GUI) control panel of a GUI displayed on the client device of the user. The GUI control panel can include a first control element to control the camera. The method can further include receiving a switch self-view command of the user, and responsive to receiving the switch self-view command, causing the self-view video stream to be presented in a second self-view portion located outside of the GUI control panel of the GUI displayed on the client device of the user.

Abstract: Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.

Abstract: Systems and methods for signaling deviations in a user position during a video conference are provided. A reference position of a user within a field of view (FOV) of a camera associated with a client device is determined. The user is one of a plurality of participants of a video conference. A video stream generated by the camera associated with the client device is then received. The video stream comprises an image of the user of the client device. From the image, a current position of the user within the FOV is determined. Responsive to determining that a value of a metric reflecting a deviation of the current position from the reference position satisfies a threshold criterion, an alert to the user is generated.

Abstract: Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.

Abstract: Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.

Abstract: Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.