Abstract: Systems and methods are disclosed for modifying content items based on eye tracking data, which may be indicative of saccadic suppression of a user. A plurality of content items is displayed on a device, including a first content item displayed at a first region. In an example, based on eye tracking data of the user, the onset of a saccade of the user is detected. An end location and duration of the saccade may be predicted based at least in part on the eye tracking data. A saccadic suppression window is identified based on the predicted duration. Based at least in part on the predicted end location, the display of the first content item is modified at a time that is within the saccadic suppression window.

Abstract: Systems and methods are disclosed for modifying content items based on eye tracking data, which may be indicative of saccadic suppression of a user. A plurality of content items is displayed on a device, including a first content item displayed at a first region. In an example, based on eye tracking data of the user, the onset of a saccade of the user is detected. An end location and duration of the saccade may be predicted based at least in part on the eye tracking data. A saccadic suppression window is identified based on the predicted duration. Based at least in part on the predicted end location, the display of the first content item is modified at a time that is within the saccadic suppression window.

Abstract: The present disclosure is directed to systems and methods to enhance the process of creating an artificial intelligence (AI) generated content or content items, such as images, text, video, sounds, etc., using a text or other suitable prompt, such as via voice input. In an embodiment the systems and methods receive a text prompt describing a content item to be generated, and generate a text embedding vector representing the received text prompt. The systems and methods further process the text embedding vector using a trained parameter classifier and determine, based on an output of the trained parameter classifier, a suggested generative AI model and a suggested sampling algorithm corresponding to the text prompt. The systems and methods further configure a generation interface to generate the content item using the suggested generative AI model and the suggested sampling algorithm.

Abstract: Systems and methods are provided for customizing a profile page. A first user profile and a second user profile are accessed by a computing device. First and second pluralities of content items associated with the first and second user are identified. Based on the first and second user profiles, first and second subsets of content items of the first and second plurality of content items are selected. For each content item of the first subset of content items, an image associated with the content item is identified. For each content item of the second subset of content items, an image associated with the content item is identified. Based on the identified images, first and second image collages are generated for the first and second user profiles. The first and second image collages and first and second indicators corresponding to the first and second user profiles are generated for display.

Abstract: Methods and systems, implemented by a device e.g., a server or computing device, for enabling the improved output of multiple content items are provided so as to e.g., limit communication network bandwidth resources requested to deliver, from the server to the computing device, portions of the multiple content items. A content item comprising at least a plurality of portions is received at a computing device. A first complexity score associated with the plurality of portions is determined. It is identified that the first complexity score is below a threshold complexity score. A length of the plurality of portions is above a threshold length. And a portion of the plurality of portions of the content item is generated for simultaneous output.

Abstract: Systems and methods for automatically calibrating sound in real-time based on changes in the environment that exceed a threshold are described. An initial calibration of sound is performed to establish a baseline for a space and recorded in a spatial sound map. The space is automatically monitored to detect any changes in the environment that exceed a threshold. If change that exceeds a threshold is detected, then recalibration is performed automatically using data from the spatial sound map. The recalibration performed factors in the changes that took place in the environment, including any changes to the listening position, to deliver optimal sound quality to the listening position. Systems and methods also describe monitoring sound characteristics in a live event. Upon receiving feedback from users in the event, auto-calibrating sound based on the feedback and/or notifying the performers to perform the sound adjustments.

Abstract: Systems and methods for automatically calibrating sound in real-time based on changes in the environment that exceed a threshold are described. An initial calibration of sound is performed to establish a baseline for a space and recorded in a spatial sound map. The space is automatically monitored to detect any changes in the environment that exceed a threshold. If change that exceeds a threshold is detected, then recalibration is performed automatically using data from the spatial sound map. The recalibration performed factors in the changes that took place in the environment, including any changes to the listening position, to deliver optimal sound quality to the listening position. Systems and methods also describe monitoring sound characteristics in a live event. Upon receiving feedback from users in the event, auto-calibrating sound based on the feedback and/or notifying the performers to perform the sound adjustments.

Abstract: Systems and methods are provided for generating a content item banner for display based on a session type and a content item type. A user profile is accessed at a computing device, and a session type associated with consumption of at least a content item of a plurality of content items is determined based on the user profile. A content item type associated with the plurality of content items is determined, and a content item banner for a subsequent content item of the plurality of content items is identified based on the session type and the content item type. The content item banner is generated for display.

Abstract: Systems and methods are described for monitoring chat activity in a live streaming session and automatically presenting prompts that include information of a supplemental content item that is related to the topic of the chat for presentation during the streaming session. The system receives and analyzes a chat message to determine its topic(s). A determination is made whether the topic is prominent and if a supplemental content item that is supported by the presenter relates to the topic of the chat. Upon a positive determination, a prompt is dynamically populated and displayed to the presenter. The presenter may verbally present the content of the prompt, or the supplemental content item may be displayed in other formats, during the streaming session. Presentation metrics and user engagement metrics may be obtained and provided to the supplemental content item provider.

Abstract: The present disclosure is directed to systems and methods to enhance the process of creating an artificial intelligence (AI) generated content or content items, such as images, text, video, sounds, etc., using a text or other suitable prompt, such as via voice input. The systems and methods disclosed provide streamlined content generation with, e.g., reduced processing power and computing time. In an embodiment the systems and methods receive a prompt for generating a first content item using a generative artificial intelligence (AI) model and retrieve, based on the prompt, a collection of matching content items. The systems and methods may then receive input selecting one of the content items from the collection and identify a prompt used to generate the selected content item. The systems and methods may then merge using a trained natural language processing model, the received prompt with the prompt of the selected content item to create a third prompt.

Abstract: Systems and methods for creating, monitoring, and managing a breakout conference for a conference call are disclosed. The methods determine topics for breakout rooms and their complexity scores. A breakout room is created for the topics, including separate breakout rooms for complex topics. An expertise score based on a plurality of factors for each device associated with a participant is also calculated. Devices are assigned to separate breakout rooms based on either just the expertise score or if the expertise score meets the threshold of the complexity score. Performance within the breakout rooms is displayed in real-time, such as in a graph. A moderator schedule is generated based the performance within the breakout rooms, where priority is given to a breakout room that has a negative performance over a breakout room with a positive performance.

Abstract: Systems and methods are described for monitoring chat activity in a live streaming session and automatically presenting prompts that include information of a supplemental content item that is related to the topic of the chat for presentation during the streaming session. The system receives and analyzes a chat message to determine its topic(s). A determination is made whether the topic is prominent and if a supplemental content item that is supported by the presenter relates to the topic of the chat. Upon a positive determination, a prompt is dynamically populated and displayed to the presenter. The presenter may verbally present the content of the prompt, or the supplemental content item may be displayed in other formats, during the streaming session. Presentation metrics and user engagement metrics may be obtained and provided to the supplemental content item provider.

Abstract: Systems and methods for coordinated output of an visual effect at a live event are described herein. A plurality of devices at a live event are identified. For each device of the plurality of devices, a current position of the device within the venue of the live event is determined. The current position of the device is determined by determining an initial location of the device and tracking, during a time period, a position of the respective device within the venue relative to the initial location using data from one or more sensors (e.g., accelerometers, gyroscopes, or any other suitable sensors). The current position of the device is recalibrated by causing the device to capture an image and analyzing the captured image. Based on the determined current positions of the plurality of devices, signals that are coordinated to form an visual effect are output on the plurality of devices.

Abstract: Systems and methods for providing individualized meeting content to participants in online meetings. Participant preferences may be summarized and displayed for speakers to see and attempt to follow, thus increasing the likelihood that meetings will progress according to the preferences of their attendees. Participants may also have their individual meeting feeds tailored to their preferences, if those preferences can be met in real time, during the meeting. Participants may further receive individual recordings of the meetings afterward, for those preferences that cannot be met in real time. In this manner, meeting participants may experience personalized versions of meetings, tailored to their particular preferences. This may improve participant interest in, and engagement with, online meetings.

Abstract: Systems and methods are presented herein for generating at least one preview of a portion of a content item, wherein the at least one preview is selectable and, when selected, enables a user to change to a playback position of the at least one preview. An input corresponding to a request to generate at least one preview of a portion of a content item is received. At least two key events corresponding to the portion of the content item is identified. In response to identifying the at least two key events, at least one interactive thumbnail corresponding to the at least two key events is generated, wherein the icon corresponds to a preview of the portion of the content item.

Abstract: Systems and methods for providing smart communications in a video game environment are disclosed. A first positional vector of a first user within a video game environment and a second positional vector of a second user within the video game environment are determined. In a first communication between the first user and second user, the first positional information is detected and a first translation vector between the first positional vector of the first user and the second positional vector of the second user is calculated. Based on the first translation vector, the first positional information is corrected, and the corrected positional information is transmitted to the second user.

Abstract: Systems and methods for creating, monitoring, and managing a breakout conference for a conference call are disclosed. The methods determine topics for breakout rooms and their complexity scores. A breakout room is created for the topics, including separate breakout rooms for complex topics. An expertise score based on a plurality of factors for each device associated with a participant is also calculated. Devices are assigned to separate breakout rooms based on either just the expertise score or if the expertise score meets the threshold of the complexity score. Performance within the breakout rooms is displayed in real-time, such as in a graph. A moderator schedule is generated based the performance within the breakout rooms, where priority is given to a breakout room that has a negative performance over a breakout room with a positive performance.

Abstract: Systems and methods for simultaneously being present in multiple extended reality (XR) apps running on the same XR device are disclosed. The methods concurrently run multiple XR apps on the user's XR device and use an avatar to represent the user's presence in each app. The methods determine whether the user is actively present in a first app or a second app. When the user is not actively present in a first app, activity in the first app is monitored, the avatar is configured to provide auto-responses based on artificial intelligence (AI), machine learning (ML), or preprogrammed responses for relevant queries to simulate the user's presence. Notifications and summary of the activities in the first app are provided to the user while they are actively present in the second app. Instead of rendering the first app, back-end simulations of the activities in the first app are processed and made available when rendering is resumed.

Abstract: Systems and methods are described for monitoring chat activity in a live streaming session and automatically presenting prompts that include information of a supplemental content item that is related to the topic of the chat for presentation during the streaming session. The system receives and analyzes a chat message to determine its topic(s). A determination is made whether the topic is prominent and if a supplemental content item that is supported by the presenter relates to the topic of the chat. Upon a positive determination, a prompt is dynamically populated and displayed to the presenter. The presenter may verbally present the content of the prompt, or the supplemental content item may be displayed in other formats, during the streaming session. Presentation metrics and user engagement metrics may be obtained and provided to the supplemental content item provider.

Abstract: Systems and methods for providing individualized meeting content to participants in online meetings. Participant preferences may be summarized and displayed for speakers to see and attempt to follow, thus increasing the likelihood that meetings will progress according to the preferences of their attendees. Participants may also have their individual meeting feeds tailored to their preferences, if those preferences can be met in real time, during the meeting. Participants may further receive individual recordings of the meetings afterward, for those preferences that cannot be met in real time. In this manner, meeting participants may experience personalized versions of meetings, tailored to their particular preferences. This may improve participant interest in, and engagement with, online meetings.