Abstract: A method of wireless communication by a user equipment (UE) includes receiving different sets of parameters from different sources as input to a receiver neural network. The method also includes receiving, from a base station, a set of target long-term energy values associated with the receiver neural network. The method further includes calculating a scaling factor for each of the different sets of parameters based on the set of target long-term energy values, and separately scaling each of the different sets of parameters based on the scaling factor calculated for that set in order to generate multiple sets of scaled parameters. The method still further includes transmitting the multiple sets of scaled parameters to the receiver neural network.

Abstract: New radio (NR) transmission opportunity (TxOP) structure having flexible starting points are disclosed for wireless communications. When a typical listen before talk (LBT) procedure is performed, the transmitting node will not know ahead of time when the LBT will pass and, thus, when data transmissions can start. NR systems may include a mini-slot design for accommodating transmission units smaller than a slot. Aspects of the present disclosure provide for flexibly increasing the number of potential starting transmission boundaries depending on when the LBT pass is detected. Alternative aspects of the present disclosure determine the potential starting transmission points using a mini-slot based design, a floating slot based design, or a punctured slot based design with a code block group (CBG) level retransmission mechanism.

Abstract: A user equipment (UE) may receive a positioning model registration message. The positioning model registration message may include a set of positioning model IDs and an indicator of a set of positioning model configurations. Each of the set of positioning model IDs may be associated with at least one of the set of positioning model configurations. The UE may receive a set of positioning signals. The UE may measure the set of positioning signals. The UE may select a positioning model ID from the set of positioning model IDs based on the set of positioning model configurations and an environmental attribute of the UE. The UE may calculate a set of positioning model outputs based on the measured set of positioning signals and a positioning model associated with the selected positioning model ID.

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: Some examples of the techniques described herein may address one or more issues for some non-linear channel codes (e.g., for artificial intelligence-based channel codes that are non-linear or that generate codes in the set of real numbers). Some of the techniques described herein, using a non-linear code with unequal error probabilities among codewords, may reduce error probability differences (e.g., may provide equal or approximately equal error probabilities) regardless of the messages to be transmitted while maintaining reduced average error probability. In some examples, scrambling may be performed to achieve reduced error probability differences among codewords for a non-linear code. Other scrambling approaches may be used to randomize inter-cell interference or to avoid biases in the generated codewords. In some approaches, scrambling may be performed after channel coding. Some examples of the techniques described herein may include performing scrambling before channel coding.

Abstract: Aspects of the disclosure are directed to signaling of a quasi-model relation (QML) between machine-learning (ML)-based UE position estimation models. In this way, only certain parts of the entire (potentially large) ML-based user equipment (UE) positioning models need be communicated (e.g., differences between a signaled ML-based UE positioning model and a reference ML-based UE positioning model). Such aspects may provide various technical advantages, such as reducing network overhead, fast and simple model relation indication, fast and simple model life cycle management (LCM), and so on.

Abstract: Aspects presented herein may enhance the accuracy and/or latency of UE positioning based on crowd-sourcing, where a network entity may compute a position estimate of a UE based on neighbor-cell scan data from the UE and one or more reference UEs. In one aspect, a network entity receives a first set of measurements associated with at least one cell from a UE. The network entity performs a position estimation of the UE based on at least one of the first set of measurements associated with the at least one cell, a second set of measurements for each of a set of reference UEs, or a location of each of the set of reference UEs via an ML model, where the UE and the set of reference UEs include at least one common cell.

Abstract: Techniques are provide for neural network based positioning of a mobile device. An example method for measuring a channel in a wireless communication system includes: receiving reference signal information; determining one or more channel frequency responses based on the reference signal information and one or more timing hypotheses; determining one or more channel impulse responses comprising a channel impulse response for each of the one or more channel frequency responses; processing the one or more channel impulse responses with a neural network; and determining an output of the neural network.

Abstract: Disclosed are techniques for wireless positioning. In an aspect, a base station determines a channel profile for a multipath channel between the base station and a user equipment (UE) based on at least one positioning reference signal transmitted to the UE or received from the UE by the base station on one or more radio beams, compresses the channel profile into a compressed representation of the channel profile, and transmits the compressed representation of the channel profile to a network entity. The network entity receives the compressed representation of the time-angle channel profile and determines a location of the UE based on the compressed representation of the channel profile.

Abstract: Methods, systems, and devices for wireless communications are described. The described techniques provide for detecting when a control link between a user equipment (UE) and a base station is lost and recovering the control link. In one example, a UE may detect that a control link with a base station is lost based on a timer or counter expiring or based on failing to receive signaling from the base station. In another example, a UE may be configured to transmit uplink transmissions to a base station to maintain a control link with the base station, and the base station may detect that a control link with the UE is lost if the base station fails to receive one or more uplink transmissions from the UE. If the control link is lost, the base station and the UE may communicate to re-establish the control link.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating channel estimates in a spatial environment based on learned material properties for objects in the spatial environment. An example method generally includes receiving, from a ray-tracing model, a plurality of multipath components corresponding to a signal transmitted from a transmitter at a first location in a spatial environment to a receiver at a second location in the environment. For each respective multipath component, energy field characteristics of the respective multipath component are estimated, using a machine learning model, based on interactions with one or more objects in the environment, one or more learned parameters of the machine learning model being associated with one or more properties of the objects. A channel estimate is generated based on the estimated characteristics of each multipath component. One or more actions may be taken based on the generated channel estimate.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a configuration for a reference signal used for data collection and/or a first message that indicates that data collection based on the reference signal is allowed. The UE may receive the reference signal. The UE may collect data based at least in part on the reference signal. The UE may transmit the data that is collected. Numerous other aspects are described.

Abstract: In a wireless communication system, a user equipment (UE) vendor and a network entity vendor may configure one or more UEs and network entities to perform data collection, and to train for channel status information (CSI) feedback (CSF) models.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved wireless channel modeling. A set of simulated channel information for a wireless signal propagating in a simulated physical space is generated, and a set of latent tensors is generated based on the set of simulated channel information using a transformation machine learning model. A channel estimate is generated based on the set of latent tensors using a decoder machine learning model. One or more actions are taken based on the channel estimate.

Abstract: In an aspect, a method of wireless communication performed by a user equipment (UE) includes determining that a positioning model error instance has occurred during a positioning occasion based on 1) a position uncertainty associated with a first position estimate satisfying positioning uncertainty error criteria, wherein the first position estimate is obtained during the positioning occasion by applying a first positioning model to radio frequency fingerprint (RFFP) measurements, 2) a positioning mismatch between the first position estimate of the UE and a second position estimate of the UE satisfying position mismatch error criteria, wherein the second position estimate of the UE is obtained during the positioning occasion by performing a positioning technique that does not use the first positioning model, or 3) any combination thereof; and determining that the first positioning model has failed based on a number of positioning model error instances satisfying positioning model failure criteria.

Abstract: Monostatic radar with progressive length transmission may be used with half-duplex systems or with full-duplex systems to reduce self-interference. The system transmits a first signal for a first duration and receives a first reflection of the first signal from a first object during a second duration. The system transmits a second signal for a third duration longer than the first duration and receives a second reflection of the second signal from a second object during a fourth duration. The system calculates a position of the first object and the second object based on the first reflection and the second reflection. The first signal, first duration, and second duration are configured to detect reflections from objects within a first distance of the system. The second signal, third duration, and fourth duration are configured to detect reflections from objects between the first distance and a second distance from the system.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a network entity, a configuration associated with channel measurement resources (CMRs). The UE may perform downlink channel measurements associated with the CMRs, wherein the downlink channel measurements are associated with one or more time instances. The UE may store the downlink channel measurements associated with the one or more time instances for a period of time at the UE. The UE may transmit, to the network entity and based at least in part on a request, at least a portion of the downlink channel measurements associated with the one or more time instances. Numerous other aspects are described.

Abstract: Disclosed are techniques for wireless communication. In an aspect, a first network node receives one or more request location information messages from a network entity, wherein the one or more request location information messages configure the first network node to use machine learning to derive one or more features of a wireless channel between the first network node and a second network node, and transmits one or more provide location information messages to the network entity, wherein the one or more provide location information messages include the one or more features of the wireless channel, and wherein the one or more features of the wireless channel are derived based on a machine learning model.

Abstract: Disclosed are techniques for communication. In an aspect, a user equipment may receive area information for one or more areas, the area information including area identifiers (IDs) of the one or more areas, an area description of the one or more areas, or both. The user equipment may transmit an indication of support for area-specific positioning in at least a first area of the one or more areas.

Abstract: Monostatic radar with progressive length transmission may be used with half-duplex systems or with full-duplex systems to reduce self-interference. The system transmits a first signal for a first duration and receives a first reflection of the first signal from a first object during a second duration. The system transmits a second signal for a third duration longer than the first duration and receives a second reflection of the second signal from a second object during a fourth duration. The system calculates a position of the first object and the second object based on the first reflection and the second reflection. The first signal, first duration, and second duration are configured to detect reflections from objects within a first distance of the system. The second signal, third duration, and fourth duration are configured to detect reflections from objects between the first distance and a second distance from the system.