Abstract: A wireless transmit/receive unit (WTRU) may determine an artificial intelligence/machine learning (AI/ML) model. The AI/ML model may be associated with channel state information (CSI) feedback function. The WTRU may receive configuration information. The configuration information may include an indication of downlink reference signals. The WTRU may generate one or more latent representations using the AI/ML model, for example based on the downlink reference signals. The WTRU may map the one or more latent representations to uplink resource elements (REs), for example without performing one or more of quantization, forward error correction, and/or modulation. The WTRU may determine one or more scaling factors. The WTRU may transmit an indication of the one or more latent representations, for example using the one or more scaling factors.

Abstract: A WTRU may receive, from a network, a training configuration message that includes an allocation of one or more uplink (UL) resources (e.g., resource elements (REs)). The WTRU may generate a first set of one or more latent representations, and may map the generated first set of one or more latent representations to the allocated UL REs. The WTRU may transmit the mapped first set of one or more latent representations to the network. The WTRU may receive a first response message from the network comprising a second set of one or more latent representations. The WTRU may transmit a second response message comprising information associated with the second set of one or more latent representations to the network. The WTRU may generate one or more WTRU-side reconstruction training dataset samples based on the second set of latent representations and an AI/ML-based CSI function.

Abstract: A wireless transmit/receive unit (WTRU) may receive first configuration information from a network device. The first configuration information may comprise one or more initial constellations associated with an AI/ML constellation model. The WTRU may receive second configuration information from the network device. The second configuration information indication may comprise an allocation associated with online constellation learning training. The WTRU may determine one or more estimated downlink training bits based on the allocation associated with online constellation learning training and the one or more initial constellations. The WTRU may recreate one or more downlink training bits used by the network device. The WTRU may determine one or more constellation performance metrics for the one or more initial constellations based on the estimated downlink training bits and the recreated downlink training bits.

Abstract: A method implemented by a wireless transmit/receive unit (WTRU) may include receiving configuration information for over-the-air federated learning (OTA-FL) training rounds of an Artificial Intelligence/Machine Learning (AI/ML) model residing at the WTRU, which may include allocations of over-the-air reference signal (OTA-RS) resources and mechanisms for the uplink pre-equalization. An indication of uplink resource allocations for transmitting pre-equalized locally updated AI/ML model parameters may be received during the OTA-FL training rounds. A trained AI/ML model may be determined by local AI/ML model training. Local AI/ML model parameters or gradients may be generated for an FL task. Channel estimation may be performed during training rounds. Uplink pre-equalization parameters may be determined based on the channel estimation. Locally updated AI/ML model parameters may be pre-equalized for transmission.

Abstract: A WTRU may receive over the air federated learning (OTA-FL) configuration information associated with a local AI/ML model at the WTRU. The WTRU may send feedback information. The WTRU may receive from the network model parameter reporting configuration. The model parameter reporting configuration may include an uplink scaling factor. The WTRU may determine one or more uplink pre-equalization factors for one or more resource elements associated with one or more model parameters associated with the local AI/ML model based on, for example, the uplink scaling factor. The WTRU may send to the network the one or more pre-equalized model parameters using the one or more associated resource elements of the local AI/ML model.

Abstract: A wireless transmit/receive unit (WTRU) comprises a processor configured to receive configuration information from a network. The configuration information may include one or more initial constellations associated with an AI/ML constellation model.

Abstract: A wireless transmit/receive unit (WTRU) may comprise a processor configured to receive configuration information that may include an indication of information to be included in an ON/OFF feedback report and a reporting configuration associated with sending of the ON/OFF feedback report. The processor may receive a network discontinuous reception (DRX) feedback message from the network, determine a state and a reward for a reinforcement learning (RL) model of the WTRU based on the received network DRX feedback message, determine an updated ON/OFF pattern using the RL model of the WTRU based on the state and the reward, and send the on/off feedback report to the network based on the reporting configuration being satisfied.

Abstract: A wireless transmit/receive unit (WTRU) may receive a first configuration information indicating a discontinuous reception (DRX) pattern. The WTRU may receive a second configuration information comprising one or more of parameters associated with a DRX feedback report, a reporting condition for transmitting the DRX feedback report, and/or uplink (UL) resource configurations for carrying the DRX feedback report. The WTRU may transmit the DRX feedback report based on the reporting condition. The DRX feedback report may comprise one or more of WTRU battery state information and/or information associated with a calculation of a reward used in a reinforcement learning model (e.g. at the network to determine the DRX pattern).

Abstract: A wireless transmit/receive unit (WTRU) may receive network assistance information. The WTRU may determine a downlink channel state information (CSI) based one on more downlink reference signals (RSs). The WTRU may determine a value associated with an uplink/downlink (UL/DL) channel relation based on the network assistance information and measurements performed on the one or more downlink RSs. The WTRU may send a CSI feedback report, wherein the CSI feedback report is based on the measurements performed on the one or more downlink RSs and/or the associated value that quantifies the UL/DL channel relation. The associated value that quantifies UL/DL channel relation indicates a relation between an uplink channel and a downlink channel associated with the one or more downlink RSs. In an example, the processor is configured to determine a CSI compression ratio for the CSI feedback report based on the associated value that quantifies the UL/DL channel relation.

Abstract: A wireless transmit/receive unit (WTRU) comprises a processor configured to receive preemption configuration information from a network. The processor may be configured to receive a downlink transmission. The processor may be configured to determine, using a trained artificial intelligence (AI) or machine learning (ML) model, that one or more resources of the downlink transmission were preempted by the network without receiving a preemption indication and based on the preemption configuration information and measurements performed on the downlink transmission. The processor may be configured to send preemption detection information to the network.

Abstract: A wireless transmit/receive unit (WTRU) and a network (NW) may perform end-to-end training of an artificial intelligence (AI) or machine learning (ML) model for channel state information (CSI) feedback. The NW may generate training data for the training using a set of one or more seed values. The WTRU may be aware of the seed values and may use them to generate ground truth data, which can be used to determine the value of an end-to-end error and/or loss function. The WTRU and the NW may compute or approximate derivatives of the loss function and may send one another the derivatives. The WTRU and the NW may utilize the derivatives to update one or more AI or ML models.

Abstract: A wireless transmit/receive unit (WTRU) may receive configuration information. The configuration information may include an indication of a first receiver function training allocation type, a second receiver function training allocation type, or a third receiver function training allocation type. The first receiver allocation type may be associated with user data allocations. The second receiver training allocation type may be associated with pseudo-random data (PRD) allocations. The third receiver training allocation type may be associated with user data allocations and PRD allocations. The WTRU may generate labels including one or more of bits and/or symbols, for example based on the receiver function training allocation type. The WTRU may train an artificial intelligence/machine learning (AI/ML)-based joint receiver function.

Abstract: A wireless transmit/receive unit (WTRU) may receive configuration information. The configuration information may include channel state information (CSI) reference signal (RS) (CSI-RS) resource configuration information and/or CSI feedback reporting configuration information. The WTRU may determine a downlink (DL) CSI estimate based on one or more CSI-RSs received in accordance with the CSI-RS resource configuration information. The WTRU may generate a CSI feedback report based on a comparison between the DL CSI estimate and historical DL CSI estimates. The WTRU may send the CSI feedback report.