Abstract: A first device may transmit an indication of a base graph recommendation. A second device may receive the indication of the base graph recommendation. The second device may select a base graph from a plurality of base graphs based on the base graph recommendation. The second device may transmit an indication of the selected base graph from the plurality of base graphs after the selection of the indication of the base graph recommendation. The first device may receive the indication of the selected base graph from the plurality of base graphs after an output of the indication of the base graph recommendation. The second device may transmit a low density parity check (LDPC) coded transmission based on the selected base graph. The first device may receive the LDPC coded transmission based on the selected base graph.

Abstract: Aspects relate to wireless communication for slot postponing of aperiodic sound reference signals (A-SRS) by a user equipment in a wireless network. A network node, such as a gNodeB, may send at least a portion of a slot postponing configuration for transmission of aperiodic sounding reference signals (A-SRSs) to a user equipment (UE). In a particular aspect, the slot postponing configuration is established through RRC signaling and does not utilize downlink control information (DCI) or MAC-CE sent parameters for establishing the slot postponing configuration. The slot positioning configuration is used to control slot offset postponing, the number of slot offsets, the number of times transmission of A-SRS can be postponed in the UE, and priority rules based on the postponing configuration.

Abstract: A configuration to allow for an SRS resource set trigger list configuration to be updated using MAC-CE. The apparatus transmits, to a UE, an SRS resource set trigger list configuration via RRC signaling. The apparatus transmits, to the UE, an updated trigger list value via MAC-CE to update the SRS resource set trigger list configuration. A trigger state of at least one SRS resource set is updated based on the updated trigger list value. The apparatus receives, from the UE, at least one SRS based on the updated SRS resource set trigger list configuration.

Abstract: Methods, systems, and devices for wireless communications are described. A base station may receive a capability message from a user equipment (UE) based on a number of receive antennas exceeding a number of transmit antennas at the UE. The base station may configure the UE with a mapping between sounding reference signal (SRS) resources and bit sequences, or SRS resource indices (SRIs), based on the capability message. The base station may transmit a control message including one or more SRIs indicating respective SRS resources. The UE may use the one or more SRIs included in a control message from the base station to select respective SRS resources from a resource set. Once the UE selects one or more SRS resources, the UE may transmit one or more SRSs in the SRS resources.

Abstract: A user equipment may be configured to assist channel reconstruction using partial spatial sounding. In some aspects, the user equipment (UE) may transmit, to another device, correlation capability information indicating a sounding reference signal (SRS) grouping capability of the UE, and receive, from the other device, reference signal (RS) configuration information for configuring a sounding procedure to be performed by the UE. Further, the UE may transmit a reference signal to the other device over a reference antenna port of the UE to allow the other device to determine channel information for another antenna port of the UE, and receive data from the other device based on the channel information.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may determine a metric based at least in part on an input sample and training samples, the training samples being associated with an artificial intelligence or machine learning (AI/ML) model, and the metric being determined during a monitoring of the AI/ML model. The UE may compare the metric to a threshold. The UE may determine a decision based at least in part on the comparison of the metric to the threshold. The UE may transmit, to a network node, an indication of the metric and the decision. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communications are described. Generally, the described techniques provide for a device such as a user equipment (UE), a base station, or both, to perform a channel noise and interference estimation based on a set of null resources in a data channel. The device may identify a first configuration for a set of demodulation reference signals (DMRSs) in a first set of time periods of a data channel and a second configuration for a set of null resources in a second set of time periods of the data channel. The second set of time periods may be nonoverlapping with the first set of time periods. The device may perform a channel estimation procedure on the data channel based on the null resources and the DMRS resources. The device may process data received via resources of the data channel based on the channel estimation procedure.

Abstract: A configuration for a device to interleave a codeword, where the codeword is based on an enhanced noncoherent error correction code. The apparatus encodes a set of bits based on a noncoherent error correction code to generate a first codeword. The apparatus interleaves the first codeword to permute coded bits of the first codeword into a second codeword. The apparatus transmits the second codeword to a second device.

Abstract: This disclosure provides systems, methods, and devices for wireless communication that support UE-driven sequential training. In a first aspect, a method of wireless communication includes obtaining channel state information data associated with a second network node; training a shared UE encoder based on the channel state information data and based on a decoder to generate a sequential training dataset; and transmitting the sequential training dataset to a third network node. Other aspects and features are also claimed and described.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communications by a user equipment (UE). The method generally includes receiving a downlink control information (DCI) with at least one block configured to trigger aperiodic sounding reference signal (SRS) transmission from the UE on at least one SRS resource set, determining a transmit power control (TPC) command to apply to the A-SRS if the DCI lacks a transmit power control (TPC) command for the at least one SRS set, and transmitting the A-SRS in accordance with the DCI and the determined TPC command.

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 radio resource control (RRC) configuration with one or more high layer parameters that enable one or more of an aperiodic sounding reference signal (SRS) triggering without data scheduling or a secondary cell (SCell) dormancy indication using downlink control information (DCI). The UE may receive, from the base station and based at least in part on the RRC configuration, DCI that is associated with at least one of: the aperiodic SRS triggering without data scheduling or the SCell dormancy indication. The UE may transmit, to the base station, an aperiodic SRS based at least in part on the DCI that triggers the aperiodic SRS. 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 one or more channel state information (CSI)-reference signals (RSs). The UE may transmit a compressed CSI report that comprises an indication of a plurality of channel metrics, an indication of a channel metric of the plurality of channel metrics comprising a compressed output of a machine learning model having an input as the channel metric, wherein at least one of the plurality of channel metrics is based at least in part on expected orthogonalization of the compressed CSI report at a network node. Numerous other aspects are described.

Abstract: Aspects relate to transmission of a sounding reference signal (SRS). A scheduling entity such as a base station may configure the transmission of an SRS by a scheduled entity such as a user equipment (UE). In some aspects, this configuration may be based on the number of antenna ports that the UE will use to transmit the SRS. For example, the scheduling entity may specify that the scheduled entity is to use a first table or a second table to map transmission combs to the maximum number of cyclic shifts. In some aspects, the selection of the first table or the second table may be based on the number of antenna ports that the scheduled entity will use to transmit the SRS.

Abstract: In some scenarios, SRS transmission over the full SRS bandwidth may be unnecessary and/or inefficient. Therefore, a need exists for approaches to SRS transmission over less than the full SRS bandwidth. Described herein are techniques and solutions of SRS transmission using only a portion of the full SRS bandwidth, or a partial SRS bandwidth. The present disclosure provides for SRS transmission using a partial SRS bandwidth through sounding patterns that use only the partial SRS bandwidth and/or using a partial SRS bandwidth through various SRS sequence generation configured for the partial SRS bandwidth. An apparatus receives an SRS configuration indicating a full SRS bandwidth; determines a frequency hopping pattern for SRS transmission based on the SRS configuration, and the frequency hopping pattern is limited to a partial SRS bandwidth less than the full SRS bandwidth; and transmits the SRS transmission to the base station based on the frequency hopping pattern.

Abstract: Methods, systems, and devices for wireless communications are described. A method for wireless communication may include receiving a single frequency networked composite reference signal (SFNed RS) at a first port of a user equipment (UE) and receiving a reference signal (RS) at a second port of the UE that is different than the first port of the UE. The method may also include performing channel estimation for at least one of the first port or the second port based at least in part on receiving the SFNed RS and the RS. A method for wireless communication may include transmitting a first portion of an SFNed RS from a first port of a first transmit/reception point to a UE and transmitting a downlink control information message to the UE that indicates at least one transmission configuration indicator state identifier that identifies the SFNed RS.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may identify channel information based at least in part on a set of channel state information reference signals (CSI-RSs). The UE may generate compressed channel state information (CSI) using a model, wherein an input of the neural network model is based at least in part on the channel information, and wherein the compressed CSI is compressed in a frequency domain. The UE may transmit the compressed CSI. Numerous other aspects are described.

Abstract: An apparatus for wireless communication at a UE is provided. The apparatus is configured to receive a first channel state information reference signal (CSI-RS) from a network entity through a transmission channel. The apparatus is further configured to receive a second CSI-RS that has a higher resolution than the first CSI-RS, and determine channel information of the transmission channel and a target output based on the second CSI-RS. The apparatus is further configured to transmit the channel information and the target output to the network entity.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may determine a first channel state information (CSI) for a first group of antennas of the UE and a second CSI for a second group of antennas of the UE, where the first group of antennas are different than the second group of antennas. The UE may transmit one or more of the first CSI or the second CSI in a CSI report. Numerous other aspects are provided.

Abstract: This disclosure provides systems, methods, and devices for wireless communication that support mechanisms for base station-assisted UE antenna port selection. A user equipment (UE) transmits, to a base station, a sounding reference signal (SRS) switching capability report (e.g., a xTyR report) indicating to the base station a number of receive antenna ports configured for the UE. (e.g., capability to transmit on x antenna ports and reception over a total of y antenna ports). The UE transmits an SRS to the base station sounding the y antenna ports. The base station selects and indicates y? antenna ports out of the y antenna ports for the UE to receive a subsequent downlink data transmission based on a channel estimation based on the SRS transmission, or based on channel state feedback (CSF). In aspects, the UE provides a recommendation of y?, and the base station may determine y? based on the UE's recommendation.

Abstract: Aspects for time bundling an SRS resource over a plurality of instances are disclosed. The apparatus may include a user equipment (UE). The user equipment may receive a configuration from a base station for time-bundling at least one sounding reference signal (SRS) resource. The time-bundling may be performed by the UE transmitting a plurality of SRS signals at different times using an identical center frequency and at least two different frequency resource allocations. The UE may transmit the plurality of SRS signals based on the configuration.