Abstract: There is provided mechanisms for transmission of reference signals. A method is performed by a terminal device. The terminal device comprises at least two physical antenna ports. The method comprises obtaining channel information. The method comprises determining, for at least one given precoder in a codebook, an uplink reference signal to physical antenna port mapping based on the channel information. The method comprises transmitting uplink reference signals in the physical antenna ports according to the determined mapping.

Abstract: According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises allocating physical uplink control channel (PUCCH) resources for one of the one or more fields based on the obtained priority and transmitting the uplink transmission using the allocated PUCCH resources.

Abstract: According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises applying a resource element mapping rule to one of the one or more fields based on the obtained priority and transmitting the uplink transmission based on the applied resource element mapping.

Abstract: A method for enabling a model trainer to train a model. The method includes transmitting a first certificate request message to an endpoint associated with a first secure enclave. The method also includes receiving a first certificate response message responsive to the first certificate request message, wherein the first certificate response message comprises a first certificate generated by the first secure enclave and a first digital signature generated by the first secure enclave for authenticating the first certificate. The method also includes determining whether the first certificate is valid. The method also includes, as a result of determining that the first certificate is valid, transmitting to the endpoint or to the model trainer a model information message comprising information pertaining to the model.

Abstract: According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises allocating a transmit power to one of the one or more fields based on the obtained priority and transmitting the uplink transmission based on the allocated transmit power.

Abstract: According to some embodiments, a method performed by a wireless device comprises obtaining a priority associated with each of one or more fields of an uplink transmission. An interpretation of the one or more fields is based on a machine learning model and is undefined with respect to an existing uplink control information (UCI) type. The method further comprises transmitting the uplink transmission, wherein one of the one or more fields is included in the uplink transmission based on the obtained priority.

Abstract: Embodiments described herein relate to methods and apparatuses for training a first machine learning, ML, model and a second ML model. A computer-implemented method of training a first ML model comprises: receiving a first latent space representation of a first channel state information, CSI, training data set, H1, from a first wireless device; decoding, using first parameters of the first ML model, the first latent space representation to determine a first reconstructed CSI data set; classifying, using second parameters of the first ML model, the first latent space representation to estimate an estimated classification; determining a first loss based on the estimated classification and a true classification; and updating the first parameters and the second parameters based on the determined first loss.

Abstract: A method, network node and wireless device (WD) to perform procedures based on a beam identification (ID) update guard interval are disclosed. According to one aspect, a method in a network node includes configuring a beam ID update guard period during which the WD is configured to assume that a same network node spatial filter is used during the beam ID update guard period unless otherwise indicated by the network node. The method also includes transmitting an indication of the configuration to the WD.

Abstract: A wireless device (WD) is described. The WD is configured to communicate with a network node and to determine one or more beam identifiers (IDs) one or both of are not included in training data of the artificial intelligence model and have not been used for training an artificial intelligence model. If the one or more beam IDs one or both of are not included in the training data of the artificial intelligence model and have not been used for training the artificial intelligence model, a first request is transmitted to the network node requesting assistance information associated with the one or more beam IDs and/or the assistance information is received. In addition, the WD is configured to cause the artificial intelligence model to be trained using the received assistance information and perform one or more actions using the artificial intelligence model.

Abstract: There is provided mechanisms for selecting a transmission hypothesis. A method is performed by a terminal device. The method comprises receiving reference signals from at least two transmission and reception points (TRPs). The method comprises selecting, from signal quality measurements on the reference signals, a transmission 5 hypothesis from alternative transmission hypotheses pertaining to which one or more of the TRPs that is to transmit data to the terminal device. Which of the transmission hypotheses to select is affected by an adjustment term. The method comprises reporting an indication of the selected transmission hypothesis to at least one of the at least two TRPs.

Abstract: A method performed by a user equipment (UE) for CSI reporting is provided. The method comprises receiving (1002) a configuration of CSI reference signal (CSI-RS) resources for channel measurements and performs (1006) the channel measurements on the CSI-RS resources according to the received configuration. The method further comprises determining (1008) one of: (1) a set of spatial domain basis vectors, a set of frequency domain basis vectors, a set of combination coefficients for combining the set of spatial domain basis vectors and the set of frequency domain basis vectors, and a time-domain information; or (2) a set of spatial domain basis vectors, a set of frequency domain basis vectors, and a plurality of sets of combination coefficients per layer for combining the set of spatial domain basis vectors and the set of frequency domain basis vectors. The method further comprises sending (1016) a CSI report to the network node.

Abstract: A method, performed by a first node having an AE-encoder, for training the AE-encoder to provide encoded CSI. The method includes providing first AE-encoder data to a second node comprising a first NN-based AE-decoder and having access to channel data representing a communications channel between a first communications node and a second communications node. Then the first node provides second AE-encoder data to a third node comprising a second NN-based AE-decoder and having access to the channel data, and then receives first training assistance information and second training assistance information. The first node determines whether or not to continue the training by updating encoder parameters of the AE-encoder based on the received first and second training assistance information.

Abstract: A method performed by a wireless device (510, 800, 1200) for reporting channel state information (CSI) for a downlink channel is disclosed. The method comprises transmitting (601, 705) a CSI report for the downlink channel to a network node (560, 1100), the CSI report comprising: a set of reported coefficients; an indication of how the network node is to interpret the set of reported coefficients; and an indication of a payload size of the set of the reported coefficients.

Abstract: There is provided mechanisms for transmission of reference signals. A method is performed by a terminal device. The terminal device comprises at least two physical antenna ports. The method comprises creating a virtual antenna port for, and applied over, at least two of the physical antenna ports. The method comprises transmitting, in the virtual antenna port, as many uplink reference signals as there are physical antenna ports.

Abstract: Providing channel state information, CSI, in a wireless communications network by a first node to a second node. The first node has access to one or more trained Neural Network, NN,-based Auto Encoder, AE,-encoder models for encoding the CSI and the second node has access to one or more trained NN-based AE-decoder models for decoding the CSI provided by the first node. The method includes receiving, from the second node, an indication of an NN-based AE-decoder model out of the one or more trained models; selecting a trained model out of the one or more trained models to use for the NN-based AE-encoder based on the received indication of the NN-based AE-decoder model such that the selected trained model is compatible with the indicated NN-based AE-decoder model; and transmitting (604) the CSI to the second node based on output from the selected trained model.

Abstract: A method (100) is disclosed for managing a wireless device that is operable to connect to a communication network, wherein the communication network comprises a Radio Access Network (RAN), and wherein the wireless device has available for execution a Machine Learning (ML) model that is operable to provide an output, on the basis of which a RAN operation performed by the wireless device may be configured. The method, performed by a RAN node of the communication network, comprises, on fulfilment of a trigger condition, causing an ML model Assurance Information, MAI, Request to be sent to the wireless device (110), the MAI Request comprising an indication of the ML model to which the MAI Request relates.

Abstract: The present disclosure relates to a method performed by a wireless node (100) for transmitting reference symbols, the node comprising an antenna with a plurality of antenna ports, the method comprising configuring channel state information, CSI, measurements of a user equipment, UE (110), by transmitting a downlink message, transmitting a first reference symbol using the plurality of antenna ports, wherein the first reference symbol is transmitted using a first number N of antenna ports, transmitting a second reference symbol using the plurality of antenna ports, wherein the second reference symbol is transmitted using a second number K of antenna ports, wherein the first reference symbol is transmitted using a first port distance smaller than a second port distance used when transmitting the second reference symbol, and wherein the K used antenna ports are less than the N used antenna ports.

Abstract: There is provided mechanisms for interference handling. A method is performed by a radio access network node. The method comprises obtaining an indication of interference in a time/frequency interval. The method comprises querying a neighbouring radio access network node about scheduling in the time/frequency interval of uplink wireless transmission from any terminal device served by the neighbouring radio access network node. The method comprises receiving a response from the neighbouring radio access network node. The response comprises information identifying uplink reference signal resources/ports, and their scheduling, as to be used by the terminal device scheduled in the time/frequency interval.

Abstract: Embodiments include methods for a radio access network (RAN) node configured to serve one or more user equipment (UEs). Such methods include transmitting reference signals (RS) for a downlink (DL) channel and receiving, from a UE, a report including encoded feedback representing the DL channel. The encoded feedback comprises a UE DL channel estimate mapped to a channel feature set based on a first mapping that is proprietary to the UE. The channel feature set is compressed based on a second mapping that is known by the UE and the RAN node. Such methods also include, using a decoder function of a neural-network autoencoder (NNAE), decoding the encoded feedback to obtain a reconstruction of the channel feature set. Other embodiments include complementary methods for a UE, as well as RAN nodes and UEs configured to perform such methods.

Abstract: Embodiments include methods for operating a network node in a wireless network. Such embodiments include applying non-linear precoding to a first data stream to remove a representation of expected inter-stream interference due to a second data stream, thereby generating a corrected first data stream. Such embodiments also include applying linear precoding to the corrected first data stream and to a first reference signal (RS) stream to generate a first signal layer. The first RS stream is not corrected for the expected inter-stream interference prior to applying the linear precoding. Such embodiments also include transmitting the first signal layer to a user equipment (UE). Other embodiments include complementary methods performed by a UE, as well as network nodes and UEs configured to perform operations corresponding to such methods.