Abstract: A method, system, and computer program product for reconstructing training data and building a new incremental learning model with the reconstructed training data that can be further trained. The method may include receiving new data to be inputted into a previously trained machine learning model, where the previously trained machine learning model has inaccessible training data. The method may also include generating simulated training data using a reverse form of the previously trained machine learning model. The method may also include verifying the simulated training data. The method may also include creating a new machine learning model using the simulated training data, where the new machine learning model includes a same structure as the previously trained machine learning model. The method may also include inputting the new data into the new machine learning model, where the new machine learning model is further trained with the new data.

Abstract: Certain aspects of the present disclosure provide techniques for interference avoidance in full duplex communications. A method that may be performed by a user equipment (UE) includes transmitting, to a network entity, a request to provide a configuration for interference avoidance between a first signal and a second signal, wherein the first signal is scheduled in a same transmission occasion as the second signal is scheduled for reception. The method further includes receiving, from the network entity, the configuration and configuring resources for at least one of transmission of the first signal or reception of the second signal in response to receiving the configuration. The method also includes transmitting the first signal via the configured resources and receiving the second signal in the transmission occasion.

Abstract: When a user equipment (UE) detects that a beam used to communicate with a base station has failed, the UE may transmit a beam failure recovery message to initiate a beam failure recovery procedure. Furthermore, the beam failure recovery message may include a new beam indication (NBI) to indicate a new beam in a candidate beam set with a measurement that satisfies a threshold. In such cases, the base station may enable communication using the new beam via dynamic signaling (e.g., downlink control information). Otherwise, beam failure recovery is performed using radio resource control signaling, which increases latency. Accordingly, some aspects described herein relate to techniques and apparatuses to report beam information (e.g., a preferred new beam) in a beam failure recovery message in cases where the UE is unable to identify any beam in the candidate beam set with a measurement that satisfies the threshold.

Abstract: Performing a three-dimensional (3D) reconstruction process of a set of selected image frames. In some instances, a plurality of sequential image frames that are extracted from a video file (including video content created through the use of Augmented Reality) are converted into a grayscale format. Once these image files are converted to a grayscale format, a two-dimensional (2D) entropy process is performed that is ultimately used to create a set of user-defined clusters, with each of these user-defined clusters being associated with at least a sub-set set of the grayscale frames. After a cluster is selected, a 3D reconstruction process is performed on the frames associated with the selected cluster.

Abstract: A base station and a UE may use a unified TCI to indicate a power control parameter for a plurality of UL channels. The base station may receive the UE's capability to support the unified TCI power control parameter, and configure the at least one power control parameter associated with at least one of a first component associated with the TCI state and a plurality of second component associated with the plurality of uplink channels.

Abstract: This disclosure provides systems, methods and apparatus, including computer programs encoded on computer storage media, for a sounding reference signal (SRS) resource set configuration to facilitate uplink panel selection between a set of asymmetric panels of a user equipment (UE), each panel of the set of asymmetric panels of the UE being associated with a different number of SRS ports. In one aspect, the UE may receive such an SRS resource set configuration indicating one or more SRS resource sets and SRS resources of the one or more SRS resource sets may be associated with different numbers of SRS ports or a dynamically configurable number of SRS ports. The UE may receive control signaling from a base station (BS) and the control signaling may indicate a panel for an uplink transmission from the UE by indicating an SRS resource, an SRS resource set, or a number of SRS ports.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a physical downlink shared channel communication in a first resource, wherein the first resource is associated with a beam indication downlink control information with a time domain resource allocation field identifying a parameter relating to the physical downlink shared channel communication. The UE may transmit, in a physical uplink control channel, hybrid automatic repeat request feedback information in a second resource, wherein the second resource is based at least in part on the first resource and a configuration of the parameter relating to the physical downlink shared channel communication. Numerous other aspects are described.

Abstract: Prompt learning is performed, using a prompt encoder, on an input data set to generate a revised text pattern. The revised text pattern is processed, using a text generative adversarial network, based on an existing data set to generate a fused data set and a machine learning system is updated with the fused data set.

Abstract: Information extraction and image restructuring includes generating semantic vectors to encode portions of text extracted from a document. For each semantic vector a semantic similarity between a schema key and other text encoded therein is determined based on their respective positions within the document. An enhanced NLP model is created using the semantic vectors, each labeled according to the semantic similarity. The text, including schema key, are re-encoded as a key and candidate vectors. Key-value pairs are generated by matching the key vector with a predetermined number of candidate vectors. The enhanced NLP model, using prompt learning, is repurposed to perform a next-sentence prediction that predicts which of the candidate vectors is logically related to the schema key. Based on the next-sentence prediction, the discrete portion of text identified as the schema key and portion of text determined to be logically related thereto are output.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may select, as a default path loss reference signal (PLRS), a reference signal (RS) resource that corresponds to an active physical downlink shared channel (PDSCH) transmission configuration indicator (TCI) state of an active downlink (DL) bandwidth part (BWP) if a control resource set (CORESET) is not provided in the active DL BWP. The UE may receive the default PLRS. In some aspects, the UE may select, as a default spatial relation for a physical uplink control channel (PUCCH) communication, a spatial relation that corresponds to an active PDSCH TCI state of an active DL BWP if a CORESET is not provided in the active DL BWP. The UE may receive the PUCCH communication using a TCI state that corresponds to the default spatial relation. Numerous other aspects are described.

Abstract: This disclosure provides systems, methods and apparatus, including computer programs encoded on computer storage media, for TCI state activation and deactivation under multiple transmit receive point (TRP) operation. In some aspects, a number of activated transmission configuration indicator (TCI) states, and TCI state types, can be indicated using a single codepoint. In some implementations, codepoints may include multiple TCI states. Each TCI state identifier in the codepoint may correspond to a TCI state type, such as uplink, downlink, or both. In some implementations, the base station (BS) may configure two separate TCI state lists, one for downlink and one for uplink. Each codepoint may include an indication of one of the two configured lists with which the TCI state identifier is associated. In some implementations, the BS may configure two bitmaps, where a first bitmap corresponds to downlink TCI states, and a second bitmap corresponds to uplink TCI states.

Abstract: Certain aspects of the present disclosure provide techniques for communicating using a target transmission configuration indicator (TCI) state associated with a dynamically received target TCI prior to transmitting an acknowledgement for the target TCI. An example method performed by a user equipment (UE) includes receiving a target transmission configuration indicator associated with a target transmission configuration indicator state and one or more target channels and communicating one or more transmissions via a first target channel of the one or more target channels prior to transmitting signaling acknowledging the target transmission configuration indicator. Based on whether at least one criterion is satisfied or not, the UE may either use the target transmission configuration indicator state or a default transmission configuration indicator state when communicating the one or more transmissions.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment may determine an association between multiple phase tracking reference signal (PTRS) ports and multiple codewords that are to be used for an uplink communication that uses multiple antenna port groups, and transmit the uplink communication using the multiple codewords based at least in part on the association. Numerous other aspects are provided.

Abstract: This disclosure provides systems, methods and apparatus, including computer programs encoded on computer storage media, for a user equipment (UE)-initiated non-serving cell beam reporting mechanism. In one aspect, a UE may transmit a resource request that requests resources over which to transmit a non-serving cell beam report for a set of beams associated with one or more non-serving cells if the set of beams satisfy a Layer 1 (L1)-based condition. For example, the UE may transmit the resource request depending on whether a beam quality of each of the set of beams or an average beam quality of the set of beams satisfies a quality threshold. The UE may receive a request for the non-serving cell beam report responsive to transmitting the resource request and may transmit the non-serving cell beam report over resources indicated by the request for the non-serving cell beam report.

Abstract: A computer-implemented process for training a neural network having a plurality of transform layers includes the following operations. Input data for one transform layer of the plurality of transform layers is transformed by the one transform layer into output data. A neural-backed decision tree is generated for the transform layer, a neural-backed decision tree. The transforming and the generating are repeated for each of the plurality of transform layers. A neural-backed decision tree map for a particular one of the plurality of transform layers maps output data of the particular one of the plurality of transform layers into a list of interpretable words from a generative search domain of facts and evidence.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a medium access control (MAC) control element (CE) (MAC-CE) including an activation command associated with activating a periodic path loss reference signal (PL-RS). The UE may receive an indication associated with a temporary PL-RS, the temporary PL-RS and the periodic PL-RS being used to estimate path loss for a period of time after the reception of the activation command. The UE may transmit an uplink signal having a transmit power based at least in part on a path loss estimate, the path loss estimate being generated based at least in part on the temporary PL-RS and the periodic PL-RS. 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, from a serving cell, information indicating a set of activated channel state information (CSI) trigger states that are respectively associated with a set of transmission configuration indication (TCI) states each having a respective source reference signal. The UE may track, based at least in part on a capability to concurrently track multiple TCI states, a subset of TCI states, of the set of TCI states, including at least one TCI state for which the respective source reference signal is a non-serving cell synchronization signal block (SSB). Numerous other aspects are provided.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive downlink control information that indicates a transmit precoding matrix indicator, that identifies a precoding matrix, and a set of demodulation reference signal (DMRS) antenna ports. A first association may be between a first set of antenna indices of the precoding matrix, that form a first transmission group, and a first code-division multiplexing (CDM) group of the set of DMRS antenna ports, and a second association may be between a second set of antenna indices of the precoding matrix, that form a second transmission group, and a second CDM group of the set of DMRS antenna ports. The UE may transmit an uplink transmission according to the first association and the second association. Numerous other aspects are provided.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may communicate with a base station using UE cooperation. For example, a first UE may transmit an uplink signal indicating a request for the base station to transmit a UE discovery request signal to a second UE. In response to transmitting the uplink signal, the first UE may receive a sidelink signal from the second UE. The sidelink signal may indicate that the second UE may be available for a cooperative link with the first UE. In some cases, based on the sidelink signal, the first UE may establish the cooperative link with the second UE. In some examples, based on establishing the cooperative link, the first UE may receive downlink communications from the base station via at least sidelink communications from the second UE over the cooperative link.

Abstract: Techniques for wireless communications are described. A first device may communicate with a second device using a first beam. Based on communicating with the second device, the first device may indicate a reference signal associated with a different beam to indicate that the different beam associated with the reference signal is preferred for subsequent communications. The reporting device may switch to the different beam based on transmitting the indication of the reference signal. Based on switching to the different beam, the reporting device may determine a communication parameter based on the indicated reference signal and communicate with the scheduling device using the second beam based on the determined communication parameter.