Abstract: A method of wireless communication, by a user equipment (UE), includes receiving multiple neural network training configurations for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes training each of a group of neural network decoder/encoder pairs in accordance with the received training configurations. A method of wireless communication, by a base station, includes transmitting multiple neural network training configurations to a user equipment (UE) for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes receiving a neural network decoder/encoder pair trained in accordance with the training configurations.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may perform a measurement operation to attain multiple measurements to report to a base station. The measurements may correspond to a first number of bits if reported. The UE may compress the measurements using an encoder neural network (NN) to obtain an encoder output indicating the measurements. This encoder output may include a second number of bits that is less than the first number of bits. The UE may report the encoder output to the base station in this compressed form. At the base station, the encoder output may be decompressed according to a decoder NN. Once the base station decompresses the encoder output, the UE and base station may communicate according to the measurements determined from the decompression. In some cases, the base station may perform load redistribution based on the measurements.

Abstract: Certain aspects of the present disclosure provide techniques for fast adaptation of transmission properties of sounding reference signal (SRS) resource sets. A method that may be performed by a user equipment (UE) includes receiving sounding reference signal (SRS) configuration information, configuring the UE with one or more SRS resource sets, wherein each of the one or more SRS resource sets comprises one or more SRS resources; receiving signaling comprising a field indicating which of the one or more SRS resources in the one or more SRS resource sets are active and which of the one or more SRS resources in the one or more SRS resources sets are inactive; and transmitting one or more SRSs using only the one or more SRS resources that are active.

Abstract: Disclosed are techniques for computing and reporting a relevance metric for a positioning beacon beam. In an aspect, a first node receives, from a second node, a plurality of beams, determines a relevance metric for each of one or more beams of interest from the plurality of beams, wherein the relevance metric for each beam of the one or more beams of interest is based on a time of arrival at the first node of the beam and a signal strength of the beam, and sends, to the second node, a report identifying each of the one or more beams of interest and including the relevance metric for each of the one or more beams of interest.

Abstract: A method of wireless communication by a user equipment (UE) includes receiving, from a base station, a configuration to train a neural network for multiple different signal to noise ratios (SNRs) of a channel estimate for a wireless communication channel. The method also includes determining a current SNR of the channel estimate is above a first threshold value. The method further includes training the neural network based on the channel estimate, to obtain a first trained neural network. The method still further includes perturbing the channel estimate to obtain a perturbed channel estimate, and training the neural network based on the perturbed channel estimate, to obtain a second trained neural network. The method includes reporting, to the base station, parameters of the first trained neural network along with the channel estimate, and parameters of the second trained neural network.

Abstract: Methods, systems, and devices for wireless communications are described. In some systems, a user equipment (UE) may transmit feedback to a base station indicating phase values for sub-bands in a bandwidth part (BWP). The base station may use the phase feedback to perform precoding on a set of beams. To support a reduced payload overhead for the feedback, the UE may implement differential phase feedback. For example, the UE may divide the BWP into a number of sub-band groups and may generate, for each sub-band group of each beam, a first set of bits indicating an absolute phase value for a first sub-band of the sub-band group. The UE may additionally generate a second set of bits indicating differential phase values for the other sub-bands of each sub-band group. The UE may report the first and second sets of bits for the beams to the base station for precoding.

Abstract: Certain aspects of the present disclosure provide techniques for measurement encoding and decoding using neural networks to compress and decompress measurement data. One example method generally includes: generating, via each of a plurality of neural network encoders operating on measurement data, a compressed measurement based on a respective portion of the measurement data, wherein each of the neural network encoders is based on the same neural network model; generating at least one message indicative of the measurement data based on the compressed measurements; and transmitting the at least one message.

Abstract: Methods, systems, and devices for wireless communications are described. Techniques described herein provide for a user equipment (UE) receiving a set of downlink reference signals associated with a downlink channel. In some cases, the set of downlink reference signals may include a channel state information reference signals (CSI-RS). The UE may calculate a transmission rank and a channel quality based on the received set of downlink reference signals. In some cases, the indication of the transmission rank may include a rank indication (RI), and the indication of the channel quality includes a channel quality indicator (CQI). The UE may then transmit the indications of the transmission rank and the channel quality using an uplink control channel, and may transmit an indication of a remaining channel state feedback using a precoded uplink reference signal.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit a first part of a channel state information (CSI) report, wherein the first part includes an indication of whether a value of a second part of the CSI report matches a value of a previous CSI report; and selectively transmit the second part of the CSI report based at least in part on whether the indication indicates that the value of the second part of the CSI report matches the value of the previous CSI report. In some aspects, a UE may determine a modified subband size of the UE, wherein the modified subband size is different than a configured subband size of the UE; and transmit, in a CSI report, an indication regarding the modified subband size to a base station. Numerous other aspects are provided.

Abstract: A method for wireless communication by a receiving device, includes receiving, from a transmitting device, a latent representation of a channel sequence for a wireless signal. A decoder applies a physical propagation channel model to the latent representation to reconstruct the channel sequence for the wireless signal.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may perform a measurement operation to attain multiple measurements to report to a base station. The measurements may correspond to a first number of bits if reported. The UE may compress the measurements using an encoder neural network (NN) to obtain an encoder output indicating the measurements. This encoder output may include a second number of bits that is less than the first number of bits. The UE may report the encoder output to the base station in this compressed form. At the base station, the encoder output may be decompressed according to a decoder NN. Once the base station decompresses the encoder output, the UE and base station may communicate according to the measurements determined from the decompression. In some cases, the base station may perform load redistribution based on the measurements.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit a sounding reference signal (SRS) on a first set of sub-bands (305). The UE may report channel state information (CSI) associated with a second set of sub-bands (310). The first set of sub-bands may be different from the second set of sub-bands. The CSI may include information that identifies one or more frequency domain correlations among the first set of sub-bands and the second set of sub-bands. Numerous other aspects are described.

Abstract: Embodiments include methods for managing information transmission between a base station and a wireless device. A base station may apply an encoder neural network to assistance information that may aid a wireless device in communicating with the base station to generate encoded assistance information. The base station may transmit the encoded assistance information to the wireless device via a control or data channel. The wireless device may use the encoded assistance information to update one or more behaviors of the wireless device without decoding the encoded assistance information. The wireless device may include a different neural network configured to learn how to use the encoded assistance information to update one or more behaviors of the wireless device.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive an indication of one or more encoding operations to use for encoding a compressed dataset, the one or more encoding operations including a differential encoding operation, or an entropy encoding operation, or both. In some examples, using a neural network, the UE may first encode a dataset based on an additional encoding operation to generate a compressed dataset and then quantize the compressed dataset encoded based on the additional encoding operation. Subsequently, after the dataset has been initially encoded and then quantized, the UE may use the indication of the one or more encoding operations to further encode and compress the dataset. The UE may then transmit the dataset to a second device based on the one or more encoding operations.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a transmitting wireless communication device may encode a data set using a single shot encoding operation and a temporal processing operation associated with at least one neural network to produce an encoded data set, wherein a dimensionality of a subset of inputs of a set of inputs to the temporal processing operation is greater than a dimensionality of the encoded data set. The transmitting wireless communication device may transmit the encoded data set to a receiving wireless communication device. Numerous other aspects are described.

Abstract: An apparatus for wireless communication transmits a demodulation reference signal (DMRS) for at least eight orthogonal DMRS ports in a single symbol of at least one slot. The apparatus also transmits data in the at least one slot. The apparatus may correspond to a base station transmitting DMRS and downlink data. The apparatus may correspond to a user equipment (UE) transmitting DMRS and uplink data. The apparatus may bundle the DMRS across multiple slots with a bundled DMRS including a first set of the DMRS ports in a first single symbol of a first slot and a second set of the DMRS ports in a second single symbol of a second slot. The apparatus may transmit the DMRS in only a single slot in a physical resource block group (PRG) including two or more resource blocks using four frequency domain orthogonal cover codes (FD-OCC) and a frequency offset pattern.

Abstract: Systems and techniques are disclosed to enhance the efficiency of available bandwidth between UEs and base stations. A UE transmits a sounding reference signal (SRS) to the base station. The base station characterizes the uplink channel based on the SRS received and, using reciprocity, applies the channel characterization for the downlink channel. As part of applying the channel information, the base station forms the beam to the UE based on the uplink channel information obtained from the SRS. The UE may include an array of antennas, each UE transmitting a different SRS that the base station receives and uses to characterize the downlink. Multiple UEs (or a single UE with multiple antennas) transmit SRS at the same time and frequency allocation (non-orthogonal), but with each sending its own unique SRS. Further, multiple UEs (or a single UE with multiple antennas) may send their SRS at unique time/frequency allocations (orthogonal).

Abstract: A user equipment (UE) receives a first channel state information reference signal (CSI-RS) on a first set of beams and receives a second CSI-RS on a second set of beams. The apparatus determines a channel quality indicator (CQI), a rank indicator (RI), and a precoding matrix indicator (PMI) based on the first CSI-RS. The apparatus reports the CQI and RI using an uplink control channel and indicates the PMI using a precoded SRS transmission. The precoded SRS transmission may be precoded based on a dissimilarity between the first CSI-RS and the second CSI-RS. The first CSI-RS may include a defined precoder, and the second CSI-RS may include a precoder based on an uplink channel estimate of a non-precoded SRS from the UE.

Abstract: Systems and methods facilitating feedback of robust channel state information (CSI), such as to provide full CSI feedback or otherwise providing CSI feedback, are described. CSI encoders and/or decoders used by network nodes may implement channel compression/reconstruction based upon neural-network (NN) training of collected channels. A structured payload having an interpretable payload portion and an uninterpretable payload portion may utilized with respect to CSI feedback. The channel compression provided according to some aspects of the disclosure supports feedback of robust CSI, in some instances including full CSI, as determined by a particular network node. Other aspects and features are also claimed and described.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a sounding reference signal (SRS) configuration that indicates a maximum number of SRS ports and whether the UE is permitted to determine an actual number of SRS ports to be used for SRS transmission that is different from the maximum number of SRS ports. The UE may determine the actual number of SRS ports to be used for SRS transmission based at least in part on the SRS configuration. The UE may transmit one or more SRSs using the actual number of SRS ports. Numerous other aspects are provided.