Abstract: Various embodiments include methods, and computing devices that perform the methods, of improving execution of a generative artificial intelligence model. Embodiment methods may include receiving an input prompt that is tokenized into a sequence of input tokens and converted into input embedding vectors. These input embedding vectors may be processed through a collection of i self-attention-based transformer layers extending from a first layer to a transition layer index (i), and a transitional output from the transition layer index (i) may be stored. The transitional output may be applied to a collection of (N?i) cross-attention-based transformer layers extending from the transition layer index (i+1) to the number of layers (N), and output tokens may be generated based on the final cross-attention based hidden state output from the final layer in the number of layers (N).

Abstract: Systems and techniques are provided for conditioning virtual representatives. For example, a method can include obtaining, by a conditioning engine, a baseline model for a virtual representative; obtaining, by the conditioning engine, one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative; generating, based on the baseline model and the one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative, a conditioned model for the virtual representative; and outputting the conditioned model for the virtual representative.

Abstract: Systems and methods are provided for detecting a driving action that mitigates risk.

Abstract: Methods, systems, and media for providing automated review of incoming messages in a group messaging service are provided.

Abstract: Systems and techniques are provided for conditioning virtual representatives. For example, a method can include obtaining, by a conditioning engine, a baseline model for a virtual representative; obtaining, by the conditioning engine, one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative; generating, based on the baseline model and the one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative, a conditioned model for the virtual representative; and outputting the conditioned model for the virtual representative.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for machine learning. In an example method, a feature map comprising a set of tokens is accessed for a pooling operation in a machine learning model, the feature map indicating correlation among a set of tensors. A polarized pooling operation is applied to the feature map to generate a pooled output, comprising, for each respective patch of a set of patches in the feature map, selecting a token, in the respective patch, having a highest absolute value. The pooled output is output.

Abstract: An apparatus has one or more memories and one or more processors coupled to the memory. The processor(s) is configured to receive a text input to a generative artificial intelligence/machine learning (AI/ML) model. The processor(s) is also configured to generate, with the generative AI/ML model, a text output based on the text input. The processor(s) is further configured to determine an advertisement related to the text input and/or the text output. The processor(s) is still further configured to modify the text input and/or the text output with the advertisement. The processor(s) is also configured to display the advertisement while receiving the text input and/or while generating the text output by generating the advertisement for selected text of the text input and/or the text output.

Abstract: An apparatus has one or more memories and one or more processors coupled to the one or more memories. The one or more processors is configured to receive an input to a generative artificial intelligence/machine learning (AI/ML) model. The one or more processors is also configured to generate, with the generative AI/ML model, an output based on the input, the output comprising a generated image. The one or more processors is further configured to determine an advertisement related to at least one of the input or the output. The one or more processors is still further configured to display the advertisement and the output of the generative AI/ML model by displaying the advertisement and the output.

Abstract: Systems and methods are provided for detecting a driving action that mitigates risk.

Abstract: A device includes a memory configured to store a first model and a second model. The first model is configured to perform inference based on a first set of parameters corresponding to a first context. The device includes one or more processors configured to process, using the second model, the first set of parameters and input corresponding to a second context to generate an output of the second model. The one or more processors are also configured to update the first model to perform inference using an updated set of parameters based on the output of the second model.

Abstract: Methods, systems, and media for providing automated review of incoming messages in a group messaging service are provided.

Abstract: Various embodiments include systems and methods for improving the user experience with LXMs. A computing device may be configured to receive a user prompt, observe user responses to an output received from a LXM in response to a prompt that is at least partially based on the user's prompt, and take an action to improve the user's experience with the LXM based on the observed user response.

Abstract: Various embodiments include systems and methods for generating a prompt for a generative artificial intelligence (AI) models. A processing system including at least one processor may be configured to recognize a user of the computing device, obtain user context information from a source of physical context information in the computing device, receive a user prompt for the large generative AI model (LXM), select a user profile from among a plurality of user profiles based on the user, the user context information and the user prompt, generate an enhanced prompt based on the user prompt and information included in the selected user profile, and submit the enhanced prompt to the LXM.

Abstract: Methods, systems, and media for providing contextual information associated with webpages are provided.

Abstract: Systems and techniques are provided for conditioning virtual representatives. For example, a method can include obtaining, by a conditioning engine, a baseline model for a virtual representative; obtaining, by the conditioning engine, one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative; generating, based on the baseline model and the one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative, a conditioned model for the virtual representative; and outputting the conditioned model for the virtual representative.

Abstract: Systems and techniques are provided for coordinating multi-user experiences. For example, a process can include obtaining a plurality of settings associated with a plurality of multi-user experience participants. The plurality of settings includes one or more arbitrated settings and one or more non-arbitrated settings. The process can include arbitrating, by a settings arbitration engine, the one or more arbitrated settings to generate one or more adjusted settings for each arbitrated setting. The process can include generating, by an experience adaptation engine, an adapted multi-user experience, wherein the adapted multi-user experience is configured to enforce the one or more adjusted settings for each arbitrated setting.

Abstract: Systems and techniques are provided for adapting digital content. For example, a process can include obtaining a digital content comprising a default configuration for outputting the digital content to a device; outputting, by the device, the digital content based on the default configuration for outputting the digital content. The process can include obtaining, from a monitoring engine, content interaction information associated with outputting, by the device, the digital content based on the default configuration for outputting the digital content. The monitoring engine is configured to monitor one or more interactions between one or more users of the device and the digital content. The process can include generating, based on the content interaction information, a content adaptation for the digital content. The process can include outputting, by the device, the content adaptation for the digital content.

Abstract: Embodiment systems and methods for dynamically rendering elements in a virtual environment rendered by the computing device may include monitoring interactions of participants in a virtual environment related to an element or elements presented in the virtual environment, identifying an agreement about the element or elements between at least two of the participants based on the interactions, and altering a presentation of the element or elements in the virtual environment based on the agreement by at least two of the participants.

Abstract: Techniques and systems are provided for displaying content by an extended reality apparatus. For instance, a process can include receiving content for display, wherein the content is associated with a first object and a first transition, the first transition indicating a change to apply to the content based on a trigger condition; outputting the content for display in association with the first object; determining that the trigger condition has been satisfied; in response to a determination that the trigger condition has been satisfied, modifying the content for presentation based on the first transition; and outputting the modified content for display.

Abstract: Methods, systems, and media for providing content providers with contextual information associated with dynamic content are provided.