Abstract: This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, for wireless communication. In one aspect of the disclosure, a method for wireless communication performed by a user equipment (UE) includes apportioning semantic feature data associated with a semantically-encoded image or video frame into a plurality of portions in accordance with a modulation and coding scheme (MCS) and a resource allocation. The method includes hyperprior decoding compressed feature probability data associated with the semantic feature data. The method includes encoding each portion of the plurality of portions of the semantic feature data in association with a respective portion of a plurality of portions of the decoded feature probability data. The method includes transmitting a transport block (TB) that includes one or more of the encoded portions of the semantic feature data. Other aspects and features are also claimed and described.

Abstract: Various aspects of the present disclosure relate to techniques that enable simplified encoding operations, decoding operations, or both, by a wireless communication device, such as a user equipment (UE) or a base station. In an example, the wireless communication device may use a medium access control layer (MAC) to inspect packets. If two inspected packets indicate different encoding processes, including at least one semantic encoding process, the MAC layer may avoid assigning the packets to the same MAC packet data unit (PDU) (also referred to as multiplexing the packets) and may instead assign the packets to different MAC PDUs. In an alternative implementation of the first example, packets associated with different encoding processes may be assigned to different radio bearers, and the MAC layer may avoiding assigning the packets to the same MAC PDU in accordance with the packets being associated with the different radio bearers.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may obtain channel measurements associated with one or more measurement resources, wherein the one or more measurement resources are associated with a low-density reference signal pattern, and the one or more measurement resources are associated with one or more of an inference-based channel estimation or a performance monitoring. The UE may determine a key performance indicator (KPI) based at least in part on the channel measurements. The UE may transmit a report that indicates one or more of the KPI or the channel measurements. Numerous other aspects are described.

Abstract: Methods, systems, and devices are described for wireless communications that support transmitting channel state information (CSI) feedback utilizing flexible uplink control resources. A method may include determining a size of a frequency subband corresponding to components of a CSI feedback report based on configuration signaling or a size of allocated uplink control resources. A method may include encoding a CSI report into a single packet and transmitting the single packet over uplink control resources. A method may include encoding a first plurality of components of a CSI report in a first packet, encoding a second plurality of components of the CSI report in a second packet, and mapping the packets to uplink control resources. A method may include transmitting a first plurality of components of a CSI report on a first slot and a second plurality of components of the CSI report on one or more subsequent slots.

Abstract: Methods, systems, and devices for wireless communications are described. The method may include receiving, from a base station and while the UE is operating in a first mode, a broadcast transmission that includes a reference signal configuration for communications between the base station and the UE, the reference signal configuration indicating one or more reference signal parameters and the first mode being either an idle mode or an inactive mode, receiving, while operating in the first mode, one or more reference signals from the base station in accordance with the reference signal configuration, and determining one or more channel measurements based on the one or more reference signals received from the base station.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive configuration information that specifies one or more parameters associated with generating, by the UE, a time domain covariance matrix specific to the UE. The UE may receive a channel state information (CSI) reference signal (CSI-RS). The UE may transmit, based at least in part on the CSI-RS and the one or more parameters, a CSI report, the CSI report including data representing the time domain covariance matrix. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a downlink control information (DCI) comprising a grant scheduling a data transmission for the UE, the data transmission associated with a rateless coding scheme. The UE may determine to disable feedback information for the data transmission based at least in part on the rateless coding scheme and one or more of: the DCI, a resource associated with the DCI, or a semi-persistent scheduling configuration associated with the data transmission. The UE may perform or monitor for the data transmission according to the DCI and the rateless coding scheme. The UE may perform or monitor for the feedback information for the data transmission according to the determining.

Abstract: Methods, systems, and devices for wireless communications are described. A communication device, which may be a user equipment (UE), may receive a message including an indication of a set of demodulation reference signal (DMRS) candidates for a data channel. The data channel may be a physical downlink shared channel (PDSCH) or a physical uplink shared channel (PUSCH) in some examples. The UE may determine a set of parameters associated with the set of DMRS candidates based on the received message. The set of parameters may correspond to a radio frequency spectrum subband or a radio frequency spectrum band associated with the data channel. The UE may estimate one or more characteristics of the data channel using the set of parameters associated with the set of DMRS candidates to perform wireless communication (e.g., PDSCH reception, PUSCH transmission).

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may jointly measure channel state information (CSI) resources corresponding to a first reporting occasion of a first CSI report setting and a second reporting occasion of a second CSI report setting if the first reporting occasion is linked to the second reporting occasion based at least in part on a slot position of the first reporting occasion relative to a slot position of the second reporting occasion. The first CSI report setting may be associated with the second CSI report setting for reporting CSI associated with non-coherent joint transmission. The UE may transmit a first report for the first CSI report setting at the first reporting occasion and a second report for the second CSI report setting at the second reporting occasion. Numerous other aspects are described.

Abstract: Certain aspects of the present disclosure provide techniques for determining applicability of machine learning (ML) models to a cell in wireless communications networks. An example method for wireless communications, performed at a User Equipment (UE) includes storing, for a first machine learning (ML) model, at least a first type of generalization characteristics supported by the first ML model; and determining applicability of the first ML model for a cell, based on the first type of generalization characteristics supported by the first ML model and deployment characteristics for the cell indicated by a network entity of the cell.

Abstract: A configuration to configure a UE to receive a plurality of CSI-RS ports where different ports may be transmitted on different sets of RBs within the frequency band of the CSI-RS. The apparatus receives CSI-RS through a plurality of CSI-RS ports, wherein different CSI-RS ports of the plurality of CSI-RS ports are transmitted on a different set of RBs. The apparatus reports at least one CSI based on a CSI-RS pattern.

Abstract: Disclosed are techniques for radio frequency (RF) sensing. In an aspect, a network entity (e.g., base station or road-side unit) may perform RF sensing in a first mode for sensing a horizontal angle using horizontal multiple input, multiple output (MIMO) radar with vertical beamforming, in which a two-dimensional MIMO antenna array is configured into a plurality of vertical columns, each column comprising a plurality of antenna elements configured to transmit as a phased array, each column transmitting a different orthogonal signal from the other columns. The network entity may perform RF sensing in a second mode for sensing a vertical angle using vertical MIMO radar with horizontal beamforming, in which the MIMO antenna array is configured into a plurality of horizontal rows, each row comprising a plurality of antenna elements configured to transmit as a phased array, each row transmitting a different orthogonal signal from the other rows.

Abstract: Certain aspects of the present disclosure provide a method of wireless communications by a user equipment (UE), generally including receiving signaling, from a network entity, indicating at least a first channel state information (CSI) reference signal (CSI-RS) pattern indicating CSI-RS resources, wherein the first CSI-RS pattern indicates a lower density of CSI-RS resources in a channel frequency range, than a second CSI-RS pattern; updating a machine learning (ML) model based on the first CSI-RS pattern; generating, using the updated ML model, CSI for the channel frequency range based on measurements taken by the UE according to the first CSI-RS pattern; and transmitting a report to the network entity indicating the CSI for the channel frequency range.

Abstract: Methods, systems, and devices for wireless communications are described. The method includes transmitting, to a base station, a capability parameter indicating one or more predictive retransmission feedback capabilities of the UE, receiving, from the base station, an activation indicator that indicates a predictive retransmission feedback procedure is enabled, receiving data from the base station, and transmitting a predictive retransmission feedback associated with the data to the base station, the predictive retransmission feedback being computed, in accordance with the activation indicator, prior to completing a decoding of the data.

Abstract: Methods, systems, and devices for wireless communication are described. A user equipment (UE) may identify a set of groups, each group in the set of groups comprising a machine learning model for each of one or more functions implemented by the UE, each machine learning model corresponding to a condition in which each function is implemented by the UE. The UE may receive an indication to switch from a first group to a second group in the set of groups based at least in part on a threshold change of the condition. The UE may switch each associated function implemented by the UE from a first machine learning model associated with the first group to a second machine learning model associated with the second group based at least in part on the indication to switch.

Abstract: Certain aspects of the present disclosure provide wireless communications by a user equipment (UE), generally including receiving signaling indicating a configuration of channel state information (CSI) reference signal (CSI-RS) resources, obtaining, from the configuration, at least first and second CSI-RS patterns, wherein the first CSI-RS pattern indicates a higher density of CSI-RS in a channel frequency range, than the second CSI-RS pattern, collecting target model output data for a machine learning (ML) model, based on channel measurements taken according to the first CSI-RS pattern, collecting nominal data for training the ML model, based on channel measurements taken according to the second CSI-RS pattern, and transmitting at least the target model output data to an entity for training the ML model.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may select variable bit allocations that indicate quantization sizes for respective segments of a latent message, the latent message representing channel state information. The UE may quantize the respective segments to form the latent message based at least in part on the quantization sizes for the respective segments. The UE may transmit the variable bit allocations with the latent message. Numerous other aspects are described.

Abstract: An apparatus for wireless communication includes a processor coupled to the memory and configured to: receive control information that includes information indicative of parameters related to one or more common streams, wherein the one or more common streams each correspond to one or more common stream resource sets, and wherein the one or more common streams include at least a partial message for at least one user equipment (UE); receive a private stream; determine a common stream resource set from the one or more common stream resource sets; jointly demodulate at least one common stream and the private stream based on parameters related to at least one common stream that corresponds to the common stream resource set to generate at least one demodulated common stream and demodulated private stream; and decode the private stream based at least on the demodulated private stream.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may generate a proxy model to be used for monitoring a UE model, the proxy model being configured to receive an input that corresponds to an input of the UE model, an intermediate result associated with the UE model, or an output of the UE model, and being configured to generate an output that corresponds to a system performance metric, an intermediate key performance indicator, or a prediction of reconstructed channel state information obtained by a network model. The UE may monitor the UE model using the proxy model. The UE may selectively transmit, to a network node, a report associated with monitoring the UE model using the proxy model. Numerous other aspects are described.

Abstract: A user equipment (UE) may receive a configuration of at least one of scheduling request (SR) resources or physical uplink control channel (PUCCH) resources, wherein the configuration indicates at least one of: a first SR resource having a first format and a first repetition-factor and a second SR resource having the first format and a second repetition-factor; or a first PUCCH resource having a second format and a third repetition-factor and a second PUCCH resource having the second format and a fourth repetition-factor; and may transmit at least one of: a first SR via the first SR resource according to the first repetition-factor; a second SR via the second SR resource according to the second repetition-factor; a first PUCCH via the first PUCCH resource according to the third repetition-factor; or a second PUCCH via the second PUCCH resource according to the fourth repetition-factor.