Abstract: Systems, methods, and instrumentalities are disclosed for measuring and adjusting extended reality (XR) roundtrip delays. A device may determine a first time associated with a start of a scene graph update. The device may determine a second time associated with an end of the scene graph update and a start of a rendering process. The device may determine a third time associated with an end of the rendering process. The device may calculate a first latency associated with the scene graph update based on the first time and the second time. The device may calculate a second latency associated with the rendering process based on the second time and the third time. The device may adjust a first parameter associated with user experience quality based, at least in part, on the first latency.

Abstract: In one implementation, a manifest application server provides to a UE a description text file, called “manifest.” which indicates several network communication paths to download or update a particular AI/ML model adapted to the target UE capabilities. The AI/ML model is supposed to be split into chunks. The manifest file is centralized and controlled by the manifest application server for delivering the best overall network efficiency with respect to different types of UEs in the system. The manifest file includes device to device communication paths and relevant information (bandwidth, chunk IDs, etc.) provided by the UE themselves. The manifest application server publishes a set of different manifests describing different network communication paths and related expected network limitations for downloading particular model chunks.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products comprising: sending, by a first Wireless Transmit/Receive Unit (WTRU) to a network entity, a subscription request for downloading an AI/ML model, the AI/ML model comprising a first model portion, and one or more further model portions; determining a second WTRU storing at least the first model portion of the AI/ML model; sending, to the network entity, first information comprising an indication of the second WTRU; receiving, from the network entity, second information indicating a schedule for downloading at least the first model portion of the AI/ML model from the second WTRU; and downloading, from the second WTRU via a device-to-device communication between the first WTRU and the second WTRU, at least the first model portion of the AI/ML model at a scheduled time using the second information.

Abstract: Some embodiments of a method may include configuring a metadata structure to manage processing of received inter-actions with respect to an MR scene, the metadata structure comprising a series of time information determinations in processing the received interaction; receiving a user action and initiating processing of an interaction request based on the user action; determining a first time information at a first stage of the processing of the interaction request; updating the interaction information with the first time information at the first stage; sending the interaction request to the server with the updated interaction information; receiving a response to the interaction request, the response comprising further interaction information that comprises the updated interaction information and further time information from the server in accordance with the metadata structure; and determining one or more Quality of Experience (QoE) metrics based at least in part on the updated further interaction information

Abstract: Methods, apparatuses, systems, etc., directed to quality of experience (QoE) data analytics for multiple wireless transmit and receive units (WTRUs) in 5G networks are disclosed herein. In an embodiment, a method may comprise receiving a request message requesting a quality of service (QoS) configuration related to at least one WTRU involved in an application for obtaining a target QoE of the application. The first method may further comprise transmitting the QoS configuration obtained based on the target QoE. In an embodiment, a method may comprise transmitting a first request signal for subscribing to a service data from an application and receiving a first response signal comprising at least one identifier of at least one WTRU involved in the application, the first response signal may comprise at least one indication of at least one individual contribution of the at least one WTRU to a QoE of the application.

Abstract: In an embodiment, a method may be implemented in a WTRU. The WTRU may send, to a first network element, request information indicating a request to perform a replication policy of information associated with a first flow and a second flow, wherein the first flow and the second flow may be co-dependent. The WTRU may send, to a first network element, first information in the first flow and may receive, from the first network element, replicated first information from the second flow, wherein the first flow and the second flow may be co-dependent. The WTRU may determine one or more co-dependent flows characteristics associated with the first flow and the second flow based on the first information and the replicated first information. The WTRU may send second information associated with the one or more co-dependent flows characteristics.

Abstract: The disclosure pertains to procedures, methods, architectures, apparatus, systems, devices, and computer program products for, and/or directed to distributing adaptive Artificial Intelligence (AI) models in a wireless network. For example, a wireless transmit/receive unit (WTRU) is configured to: transmit, to a network node, information indicating one or more capabilities of the WTRU for running an AI model; receive, from the network node, based on a comparison of the one or more capabilities of the WTRU and a first accuracy level, a first AI model subset of an adaptive AI model, wherein the adaptive AI model comprises a plurality of AI model subsets, each subset being associated with an accuracy level; and run the first AI model subset of the adaptive AI model.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for the distribution of Artificial Intelligence (AI) models from a network to a Wireless Transmit/Receive Unit (WTRU) in the network.

Abstract: Procedures, methods, apparatuses, systems, devices, and computer program products are provided for achieving dynamic quality of service (QoS) adaptation. Wireless transmit/receive unit (WTRU) methods and systems include storing configuration information indicating a plurality of QoS index values (QIDs) each associated with a set of QoS parameters. The methods and systems further include receiving a data unit and selecting a QID of the plurality of QIDs for the data unit based on an association between data units or a data flow corresponding to the data unit. The methods and systems further include transmitting the data unit to a wireless network based on the set of QoS parameters associated with the selected QID.

Abstract: Flexible neural architectures for end-to-end compression are used for image or video compression. In one embodiment, a first device is an encoder, and a second device is a decoder. Transmission of compressed features is performed between the first device and the second device. Mapping of probability tables is performed in the first and second devices. In one embodiment, mapping is communicated between the first and second devices by updating a bitstream used to encode features. In another embodiment, inference is split between user equipment and a network.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device receives a representation of at least part of a machine learning model and information representing a plurality of split points, a split point representing a layer at which an intermediate result of execution of the machine learning model may be output to a second device, the intermediate result enabling execution of the machine learning model from the split point, determines a selected split point from the plurality of split points, processes input data using the AI/ML model up to the selected split point to obtain an intermediate result corresponding to the selected split point, and outputs, to the second device, information corresponding to the intermediate result corresponding to the selected split point and information indicating the selected split point.

Abstract: Methods, apparatuses, systems, etc., directed to quality of experience (QoE) data analytics for multiple wireless transmit and receive units (WTRUs) in 5G networks are disclosed herein. In an embodiment, a method may comprise receiving a request message requesting a quality of service (QoS) configuration related to at least one WTRU involved in an application for obtaining a target QoE of the application. The first method may further comprise transmitting the QoS configuration obtained based on the target QoE. In an embodiment, a method may comprise transmitting a first request signal for subscribing to a service data from an application and receiving a first response signal comprising at least one identifier of at least one WTRU involved in the application, the first response signal may comprise at least one indication of at least one individual contribution of the at least one WTRU to a QoE of the application.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device partitions a unit of media data corresponding to a media content item into a plurality of media segments, and, for each media segment, determines a machine learning model, a machine learning part, and whether inference using the machine learning part is to be performed externally to the first device or by an inference unit of the first device, transmits content data corresponding to the media segment and information indicative of the determined machine learning model and machine learning part for inference, and obtains processed data resulting from processing of the content data using at least the machine learning part.

Abstract: A method performed by a wireless transmit/receive unit (WTRU) may comprise: receiving, from a base station, configuration information; receiving, from an application layer, one or more uplink protocol data units (PDUs); determining a buffering delay for transmitting the one or more uplink PDUs in resources associated with configured grant (CG) physical uplink shared channel (PUSCH) occasions; and on a condition that the buffering delay is greater than a delay threshold and that there are no available resources associated with semi-persistent scheduling (SPS) physical downlink shared channel (PDSCH)occasions within a time window, transmitting an indication of a time offset for the time window. The method may further comprise transmitting, to the base station, in a CG PUSCH occasion, the one or more uplink PDUs.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products for distributed Artificial Intelligence, AI. A first device receives from a second device information indicative of a plurality of distributed Artificial Intelligence, AI, models, wherein each model of the plurality of distributed AI models corresponds to a same AI service, transmits, to the second device, a message including information indicative of a selected distributed AI model from among the plurality of distributed AI models, wherein the selected distributed AI model includes a plurality of model subsets making up the AI service, receives information corresponding to a model subset of the selected distributed AI model, and runs the model subset of the selected distributed AI model based on the information corresponding to the model subset.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products of machine learning using a first machine learning (ML) module implementing a first ML model and a second ML module implementing a second ML model, the method comprising: receiving, by the second ML module, first prediction results of the first ML model, the first prediction results being based on input data; generating, by the second ML module, second prediction results using the second ML model based on the input data; determining, by the second ML module, an accuracy metric based on a comparison of the first prediction results of the first ML model and the second prediction results of the second ML model; and sending, by the second ML module, the determined accuracy metric and an accuracy condition.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.

Abstract: Procedures, methods, architectures, apparatuses, systems, devices, and computer program products comprising: sending, by a first Wireless Transmit/Receive Unit (WTRU) to a network entity, a subscription request for downloading an AI/ML model, the AI/ML model comprising a first model portion, and one or more further model portions; determining a second WTRU storing at least the first model portion of the AI/ML model; sending, to the network entity, first information comprising an indication of the second WTRU; receiving, from the network entity, second information indicating a schedule for downloading at least the first model portion of the AI/ML model from the second WTRU; and downloading, from the second WTRU via a device-to-device communication between the first WTRU and the second WTRU, at least the first model portion of the AI/ML model at a scheduled time using the second information.

Abstract: A first network analysis node in a network receives, from a device, a first message comprising information indicative of a subscription, for the device, to network analytics information, and sends, to a second network node, a second message comprising information indicative of a request for a transfer of at least part of the subscription to network analytics information to a second network analysis node.