Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a message from a network entity indicating a set of machine learning models, a set of parameter sets, or both and one or more usage conditions associated with the machine learning models and parameter sets. Based on a usage condition being satisfied, the UE may select a machine learning model, a parameter set, or both for generating a machine learning inference. For example, the UE may select the machine learning model or the parameter set based on a priority, whether sufficient input data is provided, or based on other usage conditions. The UE may generate the machine learning inference using the selected machine learning model or the selected parameter set, and the UE may transmit a report indicating an output of the machine learning inference to the network entity.

Abstract: Aspects presented herein may enable a network entity (e.g., a consumer network entity) to request data and/or analytics (e.g., AI/ML analytics, AI/ML inference, etc.) from another network entity (e.g., a RAN) via a core network or a function associated with the network (e.g., an NWDAF of the core network). In one aspect, a core network entity receives, from a first network entity, an analytics request. The core network entity transmits, to a second network entity, a data collection request based at least in part on the analytics request. The core network entity receives, from the second network entity, a data collection response based on the data collection request. The core network entity transmits, to the first network entity, an analytics response based at least in part on the data collection response.

Abstract: This disclosure provides methods, components, devices and systems for wireless communications. A user equipment (UE) may receive first control signaling including a set of configuration identifiers corresponding to a set of configurations for inclusion in an applicability report and including one or more indicators indicating whether respective configurations of the set of configurations are for an applicability report. The UE may transmit the applicability report for one or more configurations in accordance with the one or more indicators and based on whether the one or more configurations are applicable for the inference procedures. The UE may receive second control signaling indicating at least one configuration to be used for the inference procedures, where the one or more indicators previously indicated the at least one configuration for the applicability report.

Abstract: There is provided a system for modulating a graphical user interface (GUI). The system comprising a user device and a system controller in communication therewith. The user device comprises a device controller and a display interface for displaying the GUI. Execution of processor executable code stored in the system controller or provided for storage in the user device by the system controller or by the device controller or by the combination thereof synergistically provides for the system controller or the device controller or the combination thereof with performing computer-implementable steps. The computer implementable steps comprise splitting the GUI into two or more sub-GUI portions positioned within the GUI frame boundary and providing for the two or more sub-GUI portions to display respective content stored within the user device and/or hosted by the system controller and/or a same or different remote host controllers in communication with the user device.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communications. An example method includes obtaining one or more configurations comprising one or more of: an indication of one or more frequencies for measurement prediction for at least a first feature; or an indication of one or more cell identifiers for measurement prediction for at least the first feature; sending an applicability report comprising one or more of: an indication of at least one frequency, of the one or more frequencies, selected for measurement prediction for at least the first feature; or an indication of at least one cell identifier, of the one or more cell identifiers, selected for measurement prediction for at least the first feature; obtaining a measurement configuration comprising an indication of one or more measurement objects for at least the first feature; and sending a measurement report based on the measurement configuration.

Abstract: Methods, systems, and devices for wireless communications are described. An access and mobility management function (AMF) may register a configuration of one or more RAN entities to a network repository function (NRF). The AMF may register information associated with a device with a UDM. A network data analytics function (NWDAF) may perform RAN discovery via the NRF, the UDM, or both. The NWDAF may receive an analytics request from a device, and the NWDAF may query the NRF, the UDM, or both for information about one or more targets of the analytics request, and the NWDAF may receive such information from the NRF, the UDM, or both. The NWDAF may transmit a data collection request to the RAN and the NWDAF may receive data back from the RAN.

Abstract: Certain aspects of the present disclosure provide techniques for reporting applicability reporting for artificial intelligence (AI) and/or machine learning (ML) inference scenarios. An example method, performed at a user equipment (UE), generally includes obtaining first signaling configuring the UE with a machine learning (ML) model associated with a use case, outputting a reference report with first information indicating a first set of one or more functionalities that are available to be applied by the UE for inference related to the use case, and outputting a subsequent report with updated information that indicates one or more changes relative to the first set.

Abstract: Some examples of the techniques described herein may relate to data collection for training one or more artificial intelligence or machine learning (AI/ML) models to predict one or more measurements or measurement events. For example, signaling may be utilized for data collection for AI/ML model training. A trained AI/ML model may be utilized for beam management, channel state information (CSI) measurement prediction, CSI feedback prediction for a two-sided model, positioning enhancements, radio resource management (RRM) measurement prediction, or measurement event prediction, among other examples. Some approaches to RRM measurement prediction may include cell-level measurement prediction or beam-level measurement prediction. A user equipment (UE) may be configured by a source gNB with a set of cells to measure, a set of beams on each cell to measure, a set of cells for measurement prediction, or a set of beams on each cell for measurement prediction.

Abstract: Certain aspects of the present disclosure provide techniques for indicating the start of event triggered data collection for artificial intelligence (AI) and/or machine learning (ML) model training scenarios. An example method, performed at a wireless node, generally includes obtaining first signaling configuring the wireless node to perform data collection responsive to detection of one or more events by the wireless node, wherein the first signaling configures the wireless node to perform the data collection according to a first configuration, detecting the one or more events, outputting second signaling indicating the detection, and performing the data collection according to the first configuration, subject to availability of processing resources at the wireless node.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communications. An example method includes receiving a radio resource management (RRM) inference configuration, wherein the RRM inference configuration configures: a set of measurement objects, and a reporting configuration; generating one or more RRM predictions based at least in part on one or more measurements according to the set of measurement objects; and transmitting a report including information associated with the one or more RRM predictions, wherein the report is in accordance with the reporting configuration.

Abstract: Certain aspects of the present disclosure provide techniques for receiving a measurement configuration comprising one or more measurement object indications, the one or more measurement object indications indicating a first measurement object associated with radio resource management (RRM) prediction and a second measurement object associated with performance monitoring for the RRM prediction; transmitting a first report, based on the first measurement object, of a first result of the RRM prediction; and transmitting a second report, based on the second measurement object, of a second result of the performance monitoring, wherein the second report includes or is associated with an indication of the first measurement object associated with the RRM prediction.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communications. An example method includes receiving, from a network entity, information indicating a set of criteria for training or using a model associated with encoding uplink control channel data, wherein the set of criteria includes a criterion associated with an uplink control channel data distribution; and performing one or more operations associated with training or using the model based at least in part on a determination that at least one criterion, of the set of criteria, is satisfied, wherein the at least one criterion includes the criterion associated with the uplink control channel data distribution.

Abstract: A method for wireless communication at a user equipment (UE) and related apparatus are provided. In the method, the UE initiates a random-access channel (RACH) procedure with a network entity; and generate, upon a successful completion of the RACH procedure, a report. The report includes one or more of: an indicator indicating whether a message 1-repetition (MSG1-repetition) feature was utilized for the RACH procedure, a first RACH purpose indicating the RACH procedure is triggered for a link recovery procedure, or a second RACH purpose indicating the RACH procedure is initiated for mobile terminated-small data transfer (MT-SDT). The UE further transmits the report to the network entity.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may report inference parameter sets supported by the UE to a network entity. The network entity may configure channel state information (CSI) reporting configurations for the UE, and may indicate a correspondence between the CSI reporting configurations and supported inference parameter sets. The UE may evaluate and report applicability information for the inference parameter sets and/or the CSI reporting configurations. For example, an inference parameter set may become non-applicable for CSI reporting at a UE based on changing conditions (e.g., channel or spatial conditions have changed as compared to the channel or spatial conditions used to train the relevant artificial intelligence or machine learning model by more than an allowable threshold for accuracy of the artificial intelligence or machine learning model).

Abstract: Methods, systems, and devices for wireless communications are described. The method may include a user equipment (UE) may receive a control signal indicating an event trigger for reporting a performance parameter associated with a machine learning model. Further, the UE may receive one or more signals indicating input data for monitoring a performance of the machine learning model by the UE. Upon detecting the event trigger, the UE may transmit a report comprising the performance parameter.

Abstract: Methods, systems, and devices for wireless communications are described. A radio access network (RAN) node may receive a message including meta information for a machine learning model that is operated by one or more devices within the coverage area of the RAN node (e.g., supported by the RAN node), where the machine learning model may be transparent to the RAN node. The meta information may include applicability information for control and management of the machine learning model by the RAN node. In some examples, the RAN node may receive the meta information from various logical functions. In some other examples, the RAN node may receive the meta information from the one or more devices. In response to receiving the meta information, the RAN node may transmit a model management message instructing a device of the one or more devices to perform a model management operation for the machine learning model.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may initiate a quality of experience (QoE) session for a QE configuration at an application layer of the UE. The UE may provide, from the application to a radio resource control (RRC) layer of the UE, a session start or stop indication based at least in part on initiating the QoE session. The indication may include at least one of a service type, an RRC level identifier, a QoE reference, or a QoE measurement collection. The UE may provide, to a base station and based at least in part on the indication, information indicating the service type, the RRC level identifier, the QoE reference, or the QoE measurement collection. Numerous other aspects are described.

Abstract: The apparatus may be a wireless device configured to obtain, first information identifying a cell cluster comprising one or more cells of a plurality of cells, wherein the plurality of cells comprises a serving cell and one or more neighboring cells, and perform, based on the first information, a task associated with a ML model. The apparatus may be a network entity configured to transmit, for a UE, first information identifying a cell cluster comprising one or more cells of a plurality of cells, wherein the plurality of cells comprises a serving cell and one or more neighboring cells, and output, for a ML model associated with a task to be performed by the UE, a data collection configuration associated with the cell cluster.

Abstract: In accordance with some examples of the techniques described herein, a user equipment (UE) may be configured with probabilistic triggers for data collection, in which the UE may collect or buffer data when one of the triggers is active. Triggering rules or events may balance data collection or may ensure that data is not significantly biased by triggering events. The probabilistic trigger may help ensure diversity in artificial intelligence or machine learning (AI/ML)-based positioning or sensing data collection. In some approaches, a UE may indicate a capability to a network entity to collect or buffer data with probabilistic triggers. The UE may receive configuration information for collecting or buffering data with probabilistic triggers. In some aspects, the UE may request on-demand positioning reference signal (PRS) configurations (e.g., from a network entity, location server, or location management function (LMF)) for collecting or buffering data with probabilistic triggers.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive implicit or explicit information indicating whether to include location information in an uplink message based at least in part on whether the UE is a narrowband Internet of Things (NB-IoT) UE. The UE may transmit the uplink message in accordance with the implicit or explicit information. Numerous other aspects are described.