Abstract: Certain aspects of the present disclosure generally relate to techniques for selecting a base graph to be used for wireless communications. Selection can be based on a variety of factors. A base graph can be used to derive a low-density parity-check (LDPC) code used for encoding a retransmission of an original transmission. An exemplary method generally includes selecting, based on a modulation and coding scheme (MCS) and a resource allocation (RA) for transmitting a codeword, a base graph (BG), from which to derive a low density parity check (LDPC) code for use in encoding data bits in the codeword (e.g., encoding data bits of a bitstream such that some redundant bits are included in the codeword), encoding the data bits to generate the codeword using the LDPC code derived from the selected BG, and transmitting the codeword using the MCS via resources of the RA.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for beam selection using machine learning. A plurality of data samples corresponding to a plurality of data modalities is accessed. A plurality of features is generated by, for each respective data sample of the plurality of data samples, performing feature extraction based at least in part on a respective modality of the respective data sample. The plurality of features is fused using one or more attention-based models, and a wireless communication configuration is generated based on processing the fused plurality of features using a machine learning model.

Abstract: Aspects of the present disclosure provide a wireless device that communicates with another wireless device utilizing self-contained subframes. The wireless device communicates with a scheduling entity utilizing a plurality of self-contained subframes that include a first subframe and a second subframe. Each of the self-contained subframes includes an uplink (UL) portion and a downlink (DL) portion. The wireless device further receives DL control information from the scheduling entity in the DL portion of the first subframe, and transmits UL data that includes a plurality of reference signal bursts to the scheduling entity in the UL portion of the first subframe. The plurality of reference signal bursts are uniformly spaced in at least a portion of the UL portion of the first subframe.

Abstract: Bandwidth part (BWP) switching may benefit a wireless communications system. Such BWP switching may include indication of one or more timing parameters used for time domain resource allocation. For example, the timing parameters may be indicated based on an index to a look-up table (e.g., a bit field in a control transmission). In some cases, one or more tables may be configured for a given BWP, and different tables may contain a different number of rows. The size of the bit field indexing the table may in turn depend on the number of rows. When switching from a first BWP to a second BWP, the size of the bit field may be based on the table of the first BWP, but the bit field may index the table of the second BWP. Techniques supporting improved timing parameter management during BWP switching are discussed herein.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a configuration message configuring the UE to communicate coordinated transmissions with multiple transmission reception points (TRPs) using a first coordinated transmission mode of a set of different coordinated transmission modes. The UE may receive, based on the configuration message, downlink control information including at least one indicator and receive a first coordinated transmission communicated in accordance with the first coordinated transmission mode. The UE may transmit, in accordance with a feedback configuration corresponding to the at least one indicator and the first coordinated transmission mode, a feedback message for the first coordinated transmission to at least one of the multiple TRPs.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment may determine at least one of a downlink path loss value or an uplink path loss value associated with a base station; receive system information, a semi-persistently configured grant via RRC or a dynamic uplink grant via DCI from the base station, wherein the RRC signaling or the dynamic uplink grant identifies a power control value associated with one user or a plurality of users associated with the base station; and determine a transmit power for a data or control transmission based at least in part on at least one of the downlink path loss value or the uplink path loss value and the power control value. Numerous other aspects are provided.

Abstract: Certain aspects of the present disclosure provide techniques for remote interference mitigation between base stations using reference signals. Certain aspects provide a method for wireless communication by a first base station (BS). The method includes receiving a reference signal (RS) from a second BS. The method further includes performing interference measurement corresponding to interference from the second BS based on the RS being associated with the second BS.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive an indication of a positioning reference signal configuration of a base station. The UE may determine, based on the positioning reference signal configuration, a reference point within a carrier bandwidth of a component carrier and a frequency domain allocation for a positioning reference signal relative to the reference point. The UE may transmit the positioning reference signal or measure the positioning reference signal based on the frequency domain allocation.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for training and using machine learning models to estimate a layout of a spatial area. An example method generally includes estimating a representation of a channel using a machine learning model trained to generate the estimated representation of the channel based on a location of a transmitter in a spatial environment, a location of a receiver in the spatial environment, and a three-dimensional representation of the spatial environment. One or more actions are taken based on the estimated representation of the channel.

Abstract: Methods, systems, and devices for wireless communications are described. A wireless device may receive an assignment of a set of resources associated with a channel, where the set of resources includes a first subset of resources allocated for data transmission and a second subset of resources allocated for a reference signal. The wireless device may generate, from the reference signal in accordance with a minimum mean square estimation (MMSE) operation, a first set of multiple channel estimations per layer of the channel. The wireless device may generate, in accordance with a nonlinear two-dimensional interpolation of the channel, a second set of multiple channel estimations per layer of the channel and may perform a refinement operation utilizing the estimations to generate a channel estimation associated with multiple layers.

Abstract: Methods, systems, and devices for wireless communications are described. A wireless device may receive an assignment of a set of resources associated with a channel where the set of resources includes a first subset of resources allocated for data transmission and a second subset of resources allocated for a reference signal. The wireless device may generate multiple channel estimations per layer of the channel and perform a refinement operation utilizing the estimations to generate a channel estimation associated with multiple layers. Each iteration of the refinement operation may include generating respective gradients associated with each per layer channel estimation; generating a current set of values of a latent variable; and modifying the channel estimations.

Abstract: Certain aspects of the present disclosure provide techniques and apparatuses for training and using machine learning models to estimate a representation of a channel between a transmitter and a receiver in a spatial environment. An example method generally includes estimating a representation of a channel using a machine learning model trained to generate the estimated representation of the channel based on a location of a transmitter in a spatial environment, a location of a receiver in the spatial environment, and information about the spatial environment. One or more actions are taken based on the estimated representation of the channel.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may identify that an uplink control information (UCI) payload satisfies a threshold size condition. The UE may map the UCI payload to an uplink control sequence. The UE may transmit a physical uplink control channel (PUCCH) that include the uplink control sequence to a base station. The uplink control sequence may be representative of the UCI payload. The base station may receive the PUCCH that includes the uplink control sequence from the UE. The base station may also determine the UCI payload by associating the uplink control sequence with a corresponding sequence index of the one or more sets of uplink control sequences.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may determine a mapping between synchronization signal blocks (SSBs) and a random access message of a two-step random access procedure based on an indication in system information signaling or radio resource control (RRC) signaling. The random access message may include a random access preamble and a random access payload. The UE may determine, based on the mapping, an association between one or more beams carrying the SSBs and one or more additional beams carrying the random access preamble and the random access payload of the random access message. As a result, the UE may perform the two-step random access procedure with a base station according to the beam association, and coexist with a four-step random access procedure in a more reliable and efficient manner.

Abstract: Certain aspects of the present disclosure generally relate to methods and apparatus for minimum scheduling delay signaling.

Abstract: Aspects of the present disclosure provide a self-contained subframe structure for time division duplex (TDD) carriers. Information transmitted on a TDD carrier may be grouped into subframes, and each subframe can provide communications in both directions (e.g., uplink and downlink) to enable such communications without needing further information in another subframe. In one aspect of the disclosure, a single subframe may include scheduling information, data transmission corresponding to the scheduling information, and acknowledgment packets corresponding to the data transmission. Furthermore, the subframe may additionally include a header and/or a trailer to provide certain bi-directional communications functions.

Abstract: A method performed by an artificial neural network includes determining a conditional probability distribution representing a channel based on a data set of transmit and receive sequences. The method also includes determining a latent representation of the channel based on the conditional probability distribution. The method further includes performing a channel-based function based on the latent representation.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may be configured to estimate a signal-to-noise ratio for each antenna port associated with a reception of one or more tracking reference signals. The UE may receive one or more of multiple single-port tracking reference signals, a single multi-port tracking reference signal, or a tracking reference signal associated with multiple power ratios. The UE may be able to estimate a channel upon receiving a demodulation reference signal. The channel estimation may be based on the reception of one or more of multiple single-port tracking reference signals, the single multi-port tracking reference signal, or the tracking reference signal associated with multiple power ratios. The UE may communicate with the base station based on estimating the channel.

Abstract: Certain aspects relate to methods and apparatus for a flexible transmission unit and acknowledgement feedback timeline for low-latency communication. As described herein, a UE may receive, within a subframe a first portion of a downlink control region scheduling at least a first data unit, wherein the subframe comprises at least two TTIs and wherein the subframe comprises the downlink control region, a data region, and an uplink control region, receive the first data unit in a first TTI of the data region, receive a second data unit in a second TTI of the data region, and separately acknowledge receipt of the first and second data units. According to aspects, the acknowledgment for the first data unit may occur in the same subframe as the transmission of the first data unit. A BS may perform corresponding operations.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may transmit a UE capability message, the UE capability message indicating a supported transmit antenna switching (TxAS) capability for each port of the UE. The UE may receive a configuration message indicating an uplink multiple-input/multiple-output (UL MIMO) configuration for the UE, the UL MIMO configuration being based at least in part on the UE capability message. The UE may identify, based at least in part on the configuration message, a sounding reference signal (SRS) configuration to use for transmitting SRSs in conjunction with the UL MIMO communications, the SRS configuration comprising a configuration for transmission by the UE of SRSs using at least one of the two or more ports of the UE, the SRSs transmitted on one or more antennas of the UE selected according to a TxAS configuration for the respective port.