Abstract: Methods and apparatus for scalable processing. Conventional image sensors read image data in a sequential row-by-row manner. However, image data may be more efficiently processed at different scales. For example, computer vision processing at a first scale may be used to determine whether subsequent processing with more resolution is helpful. Various embodiments of the present disclosure readout image data according to different scales; scaled readouts may be processed using scale specific computer vision algorithms to determine next steps. In addition to scaled readouts of image data, some variants may also provide commonly used data and/or implement pre-processing steps.

Abstract: Systems, apparatus, and methods for augmenting vision with region-of-interest based processing. In one specific example, smart glasses may use an eye-tracking camera to monitor the user's gaze and determine the user's gaze point. When triggered, the camera assembly captures a high-resolution image. The high-resolution image may be cropped to a much smaller region-of-interest (ROI) image based on computer-vision analysis of the user's gaze point. For example, if the smart glasses detect a human face at the gaze point, then the ROI is cropped to the human face. In this manner, the smart glasses may leverage specific capabilities of the smart glasses to augment the user experience; for example, telephoto lenses provide long distance vision, or computer-assisted search may direct the user to interesting activity. Other aspects may include e.g., external database assisted operation and/or ongoing cataloging throughout the day.

Abstract: Systems, apparatus, and methods for a gesture-based augmented reality and/or extended reality (AR/XR) user interface. Conventional image processing scales quadratically based on image resolution. Processing complexity directly corresponds to memory size, power consumption, and heat dissipation. As a result, existing smart glasses solutions have short run-times (<1 hr) and may have battery weight and heat dissipation issues that are uncomfortable for continuous wear. The disclosed solution provides a system and method for low-power image processing via the use of scalable processing. In one specific implementation, gesture detection is divided into multiple stages. Each stage conditionally enables subsequent stages for more complex processing. By scaling processing complexity at each stage, high complexity processing can be performed on an “as-needed” basis.

Abstract: Methods and apparatus for scalable processing. Conventional image sensors read image data in a sequential row-by-row manner. However, image data may be more efficiently processed at different scales. For example, computer vision processing at a first scale may be used to determine whether subsequent processing with more resolution is helpful. Various embodiments of the present disclosure readout image data according to different scales; scaled readouts may be processed using scale specific computer vision algorithms to determine next steps. In addition to scaled readouts of image data, some variants may also provide commonly used data and/or implement pre-processing steps.

Abstract: Systems, apparatus, and methods for a gesture-based augmented reality and/or extended reality (AR/XR) user interface. Conventional image processing scales quadratically based on image resolution. Processing complexity directly corresponds to memory size, power consumption, and heat dissipation. As a result, existing smart glasses solutions have short run-times (<1 hr) and may have battery weight and heat dissipation issues that are uncomfortable for continuous wear. The disclosed solution provides a system and method for low-power image processing via the use of scalable processing. In one specific implementation, gesture detection is divided into multiple stages. Each stage conditionally enables subsequent stages for more complex processing. By scaling processing complexity at each stage, high complexity processing can be performed on an “as-needed” basis.

Abstract: Systems, computer programs, devices, and methods that enable LLM-based user interfaces within real-time and/or embedded devices. Providing user-specific context to a generically trained LLM may enable a variety of new usages and scenarios. For example, adaptive prompt augmentation may enable a user device to augment user-generated prompts with additional user context in the form of machine-generated prompts. In some variants, machine-generated prompts may be further refined to accommodate e.g., foundation model constraints, etc. APIs for user-specific data structures can be used to e.g., optimize for habitual behaviors, user idiosyncrasies, etc. Agentic query construction may enable a user device to operate with autonomy and decision-making capabilities, beyond prompt-response interactions. Stitching (or dreaming) may be used to identify pattern-based associations within high dimensional space (embedding vectors).

Abstract: Systems, computer programs, devices, and methods that enable LLM-based user interfaces within real-time and/or embedded devices. Providing user-specific context to a generically trained LLM may enable a variety of new usages and scenarios. For example, adaptive prompt augmentation may enable a user device to augment user-generated prompts with additional user context in the form of machine-generated prompts. In some variants, machine-generated prompts may be further refined to accommodate e.g., foundation model constraints, etc. APIs for user-specific data structures can be used to e.g., optimize for habitual behaviors, user idiosyncrasies, etc. Agentic query construction may enable a user device to operate with autonomy and decision-making capabilities, beyond prompt-response interactions. Stitching (or dreaming) may be used to identify pattern-based associations within high dimensional space (embedding vectors).

Abstract: Systems, computer programs, devices, and methods that enable LLM-based user interfaces within real-time and/or embedded devices. Providing user-specific context to a generically trained LLM may enable a variety of new usages and scenarios. For example, adaptive prompt augmentation may enable a user device to augment user-generated prompts with additional user context in the form of machine-generated prompts. In some variants, machine-generated prompts may be further refined to accommodate e.g., foundation model constraints, etc. APIs for user-specific data structures can be used to e.g., optimize for habitual behaviors, user idiosyncrasies, etc. Agentic query construction may enable a user device to operate with autonomy and decision-making capabilities, beyond prompt-response interactions. Stitching (or dreaming) may be used to identify pattern-based associations within high dimensional space (embedding vectors).

Abstract: Systems, computer programs, devices, and methods that enable LLM-based user interfaces within real-time and/or embedded devices. Providing user-specific context to a generically trained LLM may enable a variety of new usages and scenarios. For example, adaptive prompt augmentation may enable a user device to augment user-generated prompts with additional user context in the form of machine-generated prompts. In some variants, machine-generated prompts may be further refined to accommodate e.g., foundation model constraints, etc. APIs for user-specific data structures can be used to e.g., optimize for habitual behaviors, user idiosyncrasies, etc. Agentic query construction may enable a user device to operate with autonomy and decision-making capabilities, beyond prompt-response interactions. Stitching (or dreaming) may be used to identify pattern-based associations within high dimensional space (embedding vectors).

Abstract: Systems, computer programs, devices, and methods that enable ML-based vision processing for low-power, embedded, and/or real-time applications. In one exemplary embodiment, smart glasses use classifiers that are based on machine-learned (ML) patch relationships. The ML patch features are determined during an offline training process. The ML patch features are grouped into weak classifiers, strong classifiers, and detectors to progressively improve prediction accuracy. An object detection architecture uses triggering logic, search management, and a classification neural network to enable event-based searching, interest-based searching, and/or dynamic search control. In some cases, pre-processing may also be used to minimize the neural network complexity (e.g., pre-processing for scaling, rotations, translations, etc.).

Abstract: Systems, computer programs, devices, and methods that enable ML-based vision processing for low-power, embedded, and/or real-time applications. In one exemplary embodiment, smart glasses use classifiers that are based on machine-learned (ML) patch relationships. The ML patch features are determined during an offline training process. The ML patch features are grouped into weak classifiers, strong classifiers, and detectors to progressively improve prediction accuracy. An object detection architecture uses triggering logic, search management, and a classification neural network to enable event-based searching, interest-based searching, and/or dynamic search control. In some cases, pre-processing may also be used to minimize the neural network complexity (e.g., pre-processing for scaling, rotations, translations, etc.).

Abstract: Systems, computer programs, devices, and methods that enable ML-based vision processing for low-power, embedded, and/or real-time applications. In one exemplary embodiment, smart glasses use classifiers that are based on machine-learned (ML) patch relationships. The ML patch features are determined during an offline training process. The ML patch features are grouped into weak classifiers, strong classifiers, and detectors to progressively improve prediction accuracy. An object detection architecture uses triggering logic, search management, and a classification neural network to enable event-based searching, interest-based searching, and/or dynamic search control. In some cases, pre-processing may also be used to minimize the neural network complexity (e.g., pre-processing for scaling, rotations, translations, etc.).

Abstract: Systems, computer programs, devices, and methods that enable ML-based vision processing for low-power, embedded, and/or real-time applications. In one exemplary embodiment, smart glasses use classifiers that are based on machine-learned (ML) patch relationships. The ML patch features are determined during an offline training process. The ML patch features are grouped into weak classifiers, strong classifiers, and detectors to progressively improve prediction accuracy. An object detection architecture uses triggering logic, search management, and a classification neural network to enable event-based searching, interest-based searching, and/or dynamic search control. In some cases, pre-processing may also be used to minimize the neural network complexity (e.g., pre-processing for scaling, rotations, translations, etc.).

Abstract: Systems, apparatus, and methods for a gesture-based augmented reality and/or extended reality (AR/XR) user interface. Conventional image processing scales quadratically based on image resolution. Processing complexity directly corresponds to memory size, power consumption, and heat dissipation. As a result, existing smart glasses solutions have short run-times (<1 hr) and may have battery weight and heat dissipation issues that are uncomfortable for continuous wear. The disclosed solution provides a system and method for low-power image processing via the use of scalable processing. In one specific implementation, gesture detection is divided into multiple stages. Each stage conditionally enables subsequent stages for more complex processing. By scaling processing complexity at each stage, high complexity processing can be performed on an “as-needed” basis.

Abstract: Methods and apparatus for scalable processing. Conventional image sensors read image data in a sequential row-by-row manner. However, image data may be more efficiently processed at different scales. For example, computer vision processing at a first scale may be used to determine whether subsequent processing with more resolution is helpful. Various embodiments of the present disclosure readout image data according to different scales; scaled readouts may be processed using scale specific computer vision algorithms to determine next steps. In addition to scaled readouts of image data, some variants may also provide commonly used data and/or implement pre-processing steps.

Abstract: Systems, apparatus, and methods for a gesture-based augmented reality and/or extended reality (AR/XR) user interface. Conventional image processing scales quadratically based on image resolution. Processing complexity directly corresponds to memory size, power consumption, and heat dissipation. As a result, existing smart glasses solutions have short run-times (<1 hr) and may have battery weight and heat dissipation issues that are uncomfortable for continuous wear. The disclosed solution provides a system and method for low-power image processing via the use of scalable processing. In one specific implementation, gesture detection is divided into multiple stages. Each stage conditionally enables subsequent stages for more complex processing. By scaling processing complexity at each stage, high complexity processing can be performed on an “as-needed” basis.

Abstract: Network infrastructure for user-specific generative intelligence. Providing user-specific context to a generically trained LLM introduces a variety of complications (privacy, resource utilization, training costs, etc.). Various aspects of the present disclosure provide novel user-specific data structures, privacy and access control, layers of data, and session management, within a network infrastructure for generative intelligence. For example, user-specific embedding vectors may be used to provide user context to a generically trained foundation model. In some variants, edge devices capture multiple modalities of user context (images, audio; not just text). Privacy and access control mechanisms also allow a user to control information that is captured and sent to the foundation model. Session management further decouples a user's conversational state from the foundation model's session state. These concepts and others may be used to emulate e.g.

Abstract: Network infrastructure for user-specific generative intelligence. Providing user-specific context to a generically trained LLM introduces a variety of complications (privacy, resource utilization, training costs, etc.). Various aspects of the present disclosure provide novel user-specific data structures, privacy and access control, layers of data, and session management, within a network infrastructure for generative intelligence. For example, user-specific embedding vectors may be used to provide user context to a generically trained foundation model. In some variants, edge devices capture multiple modalities of user context (images, audio; not just text). Privacy and access control mechanisms also allow a user to control information that is captured and sent to the foundation model. Session management further decouples a user's conversational state from the foundation model's session state. These concepts and others may be used to emulate e.g.

Abstract: Network infrastructure for user-specific generative intelligence. Providing user-specific context to a generically trained LLM introduces a variety of complications (privacy, resource utilization, training costs, etc.). Various aspects of the present disclosure provide novel user-specific data structures, privacy and access control, layers of data, and session management, within a network infrastructure for generative intelligence. For example, user-specific embedding vectors may be used to provide user context to a generically trained foundation model. In some variants, edge devices capture multiple modalities of user context (images, audio; not just text). Privacy and access control mechanisms also allow a user to control information that is captured and sent to the foundation model. Session management further decouples a user's conversational state from the foundation model's session state. These concepts and others may be used to emulate e.g.

Abstract: Network infrastructure for user-specific generative intelligence. Providing user-specific context to a generically trained LLM introduces a variety of complications (privacy, resource utilization, training costs, etc.). Various aspects of the present disclosure provide novel user-specific data structures, privacy and access control, layers of data, and session management, within a network infrastructure for generative intelligence. For example, user-specific embedding vectors may be used to provide user context to a generically trained foundation model. In some variants, edge devices capture multiple modalities of user context (images, audio; not just text). Privacy and access control mechanisms also allow a user to control information that is captured and sent to the foundation model. Session management further decouples a user's conversational state from the foundation model's session state. These concepts and others may be used to emulate e.g.