Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, a grant for a communication with the base station. The UE may determine whether the communication is associated with a hybrid automatic repeat request (HARQ)-based transmission mode or a HARQ-less transmission mode. The UE may communicate with the base station based at least in part on the grant and the determination of whether the communication is associated with the HARQ-based transmission mode or the HARQ-less transmission mode. Numerous other aspects are described.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may provide information identifying a band combination capability for carrier aggregation during a handover of the UE, wherein the band combination capability identifies a plurality of bands or carriers; and perform the handover based at least in part on the information identifying the band combination capability, wherein at least one first band or carrier, of the plurality of bands or carriers, is used for a source base station of the handover and at least one second band or carrier, of the plurality of bands or carriers, is used for a target base station of the handover. Numerous other aspects are provided.

Abstract: Methods, systems, and devices for wireless communication are described. A user equipment (UE) may transmit, to a network entity, a consent profile registration request, the consent profile registration request identifying a user identifier. The UE may transmit, to the network entity, a consent profile based at least in part on the consent profile registration request, the consent profile comprising one or more consent types for the user identifier that configure one or more consent parameters for the user identifier on a least a per-user basis.

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for a UE capability for AI/ML. A UE may receive a request from a network to report a UE capability for at least one of an AI procedure or an ML procedure. The UE may transmit to the network, based on the request to report the UE capability, an indication of one or more of an AI capability, an ML capability, a radio capability associated with the at least one of the AI procedure or the ML procedure, or a core network capability associated with the at least one of the AI procedure or the ML procedure.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may perform radio link monitoring (RLM) reference signal measurements on a primary secondary cell (PSCell) while the UE is operating in a secondary cell group (SCG) deactivated state. The UE may perform beam failure detection (BFD) reference signal measurements while the UE is operating in the SCG deactivated state. The UE may transmit, to a master node associated with a master cell group (MCG), an SCG failure information message based at least in part on one of: a PSCell radio link failure (RLF) detection based at least in part on the RLM reference signal measurements, or a BFD based at least in part on the BFD reference signal measurements. Numerous other aspects are described.

Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for an ML model training procedure. A network entity may receive a trigger to activate an ML model training procedure based on at least one of an indication from an ML model repository or a protocol of the network entity. The network entity may transmit an ML model training request to activate the ML model training at one or more nodes. The one or more nodes may be associated with a RAN that may transmit, based on receiving the ML model training request, ML model training results indicative of a trained ML model. In aspects, an apparatus, such as a UE, may train the ML model based on an ML model training configuration received from the RAN, and transmit an ML model training report indicative of the trained ML model.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit an update to a previously reported set of UE artificial intelligence (AI) or machine learning (ML) capabilities. The UE may receive a configuration associated with performance of UE AI or ML operations based at least in part on the update. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communications are described. In some systems, a user equipment (UE) and a network entity may support a configured grant (CG)-specific retransmission timer configuration based on a traffic type to be communicated using a given CG. For example, the network entity may indicate a CG for uplink transmissions and may indicate a retransmission timer that is specific to the CG. As such, the UE may transmit a data message in accordance with the CG and may select a time period during which to monitor a downlink control channel for control information indicating a retransmission request for the data message in accordance with a value of the retransmission timer. Additionally, or alternatively, the UE and the network entity may support a downlink-to-uplink configuration dependency for determining an uplink periodicity of a CG based on a downlink periodicity.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit capability information that indicates support for one or more model combinations of machine learning (ML) models, wherein the capability information further indicates one or more performance parameters of an ML model of the ML models with respect to a model combination of the one or more model combinations that includes the ML model. The UE may receive one or more indications to use one or more of the ML models based at least in part on the capability information. Numerous other aspects are described.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a network node, an indication of one or more data radio bearers between the UE and the network node that are configured for application data unit (ADU) traffic. The UE may communicate, with an application server, one or more ADU traffic flows through the network node using the one or more data radio bearers. Numerous other aspects are provided.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive, from a master node associated with a primary cell, a configuration for a conditional procedure for adding or changing a primary secondary cell (PSCell) associated with a secondary node. The UE may also receive, from the master node, a configuration for a handover procedure for the primary cell. The UE may transmit a report that includes information related to the conditional PSCell procedure, information related to the primary secondary cell, or both, based on a triggering order between the conditional PSCell procedure and the handover procedure.

Abstract: Methods, systems, and devices for wireless communication are described related to a duty cycle configuration for power saving. A user equipment (UE) may receive control signaling indicating a duty cycle for cycling between a first power state associated with a first configuration and a second power state associated with a second configuration. In some examples, the first and second configurations may indicate a bandwidth part (BWP) configuration, restricted reception or transmission of one or more channels within the BWP configuration, or both for the UE. The UE may communicate first data traffic in accordance with the first configuration while operating in the first power state. The UE may transition from the first power state to the second power state in accordance with the duty cycle. The UE may communicate second data traffic in accordance with the second configuration while operating in the second power state.

Abstract: Disclosed are systems and techniques for wireless communications. For instance, a network entity can determine a first data heterogeneity level associated with input data for training a machine learning model. In some cases, the network entity can determine, based on the first data heterogeneity level, a first data aggregation period for training the machine learning model. In some aspects, the network entity may obtain a first set of updated model parameters from a first client device and a second set of updated model parameters from a second client device, wherein the first set of updated model parameters and the second set of updated model parameters are based on the first data aggregation period. In some examples, the network entity can combine the first set of updated model parameters and the second set of updated model parameters to yield a first combined set of updated model parameters.

Abstract: A method of wireless communication by a user equipment (UE) includes receiving, from a network device, a request to initiate gradient computations for a round of federated learning. The method also includes computing gradients in response to receiving the request to initiate gradient computation. The method further includes informing the network device of availability of the gradients. The method still further includes receiving, from the network device, information to enable transfer of the gradients to the network device. The method further includes transferring the gradients to the network device in response to receiving the information to enable transfer.

Abstract: A protocol stack architecture for processing machine learning (ML) data includes a ML layer to manage ML data communication with a network device. The ML layer is coupled to multiple ML training blocks, and ML and inference blocks for multiple neural networks, and an analog data communications stack coupled to the ML layer. The analog data communications stack has an upper media access control analog (MAC-A) layer coupled to the ML layer and configured to store data for each neural network, a lower MAC-A layer coupled to the upper MAC-A layer and configured to segment and reassemble analog ML data, and an analog physical layer coupled to the lower MAC-A layer and configured to communicate analog data with the network device. The architecture includes a digital data communications stack coupled to the ML layer and the lower MAC-A layer and configured to manage digital communications with the network device.

Abstract: A first network node may transmit, to a second network node, first information associated with granular user consent control. The first information may be further associated with a data processing task and a UE. The second network node may receive, from the first network node or the UE, second information associated with the granular user consent control. The second information may be further associated with the data processing task and the UE. The second network node may identify a user consent result associated with the data processing task and a user of the UE based on the granular user consent control. The user consent result may be further based on the first information or the second information. The second network node may transmit, to the first network node, the user consent result. Thereafter, the first network node may handle the data processing task based on the user consent result.

Abstract: A method of wireless communication by a user equipment (UE) includes generating, by an upper analog media access control (MAC-A) layer of a protocol stack, a data packet with a header and a data field. The header indicates a neural network identifier (ID) and a request ID. The data field includes gradient data for a federated learning iteration. The method also includes transferring the data packet to lower layers of the protocol stack for transmission to a network device across a wireless network.

Abstract: A method of wireless communication by a user equipment (UE) includes receiving an uplink grant from a network device. The method also includes determining, by a lower analog media access control (MAC-A) layer of an analog data communications stack, a quantity of analog neural network gradients to transmit in a data packet using resources allocated by the uplink grant. The determining is based on an analog physical (PHY-A) layer encoding scheme and the resources allocated by the uplink grant. The method further includes segmenting the analog neural network gradients into the data packet. The method still further includes transferring the data packet to the PHY-A layer for transmission to the network device across a wireless network.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may perform radio link monitoring (RLM) reference signal measurements on a primary secondary cell (PSCell) while the UE is operating in a secondary cell group (SCG) deactivated state. The UE may perform beam failure detection (BFD) reference signal measurements while the UE is operating in the SCG deactivated state. The UE may transmit, to a master node associated with a master cell group (MCG), an SCG failure information message based at least in part on one of: a PSCell radio link failure (RLF) detection based at least in part on the RLM reference signal measurements, or a BFD based at least in part on the BFD reference signal measurements. Numerous other aspects are described.

Abstract: Logical channel prioritization and mapping to different numerologies is disclosed for 5G networks having multiple network slices operable for communication via logical channels associated with different numerologies. For user equipments (UEs) configured to handle multiple numerologies, different rules for mapping logical channels associated with different numerologies may be defined for data and non-data channels. Thus, when new data arrives at a UE for communication via a logical channel associated with a different numerology, the UE checks whether the mapping rules would allow multiplexing of the new numerology data onto an existing data channel. If no data channel has already been allocated or if an allocated data channel may not include data from the new numerology, then a mapping is followed for specifically requesting resources for communication of the new numerology data. The new mapping may trigger scheduling request or random access procedures specifically associated with the new numerology.