CAPABILITY INDICATION FOR A MULTI-BLOCK MACHINE LEARNING MODEL

    公开(公告)号:US20240205668A1

    公开(公告)日:2024-06-20

    申请号:US18555501

    申请日:2021-07-02

    发明人: Yuwei Ren Huilin Xu

    IPC分类号: H04W8/24 H04W72/21

    CPC分类号: H04W8/24 H04W72/21

    摘要: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may indicate a support for an end-to-end multi-block machine learning application, a first UE capability for a backbone block of the multi-block machine learning application that makes up one or more front-end layers (e.g., one or more backbone layers), a second UE capability for a task-specific block of the multi-block machine learning application that makes up the end layer (s) of the end-to-end model (e.g., one or more task-specific layers), or a combination thereof. In some examples, the UE may transmit separate indications for the first UE capability and for the second UE capability. Additionally or alternatively, the UE may transmit a general machine learning capability indication, where a base station then determines the first UE capability for the base stage and the second UE capability for the task-specific stage from the general machine learning capability.

    Communicating multiple transport formats in a slot with full-duplex

    公开(公告)号:US12016032B2

    公开(公告)日:2024-06-18

    申请号:US17310715

    申请日:2020-02-28

    摘要: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a node may determine a first set of time-frequency resources, within a time duration, for full-duplex communications and a second set of time-frequency resources, within the time duration, for non-full-duplex communications. The node may transmit to a wireless communication device and based at least in part on determining the first set of time-frequency resources and the second set of time-frequency resources, an indication of the first set of time-frequency resources, the second set of time-frequency resources, and corresponding transport formats for the first set of time-frequency resources and the second set of time-frequency resources. Numerous other aspects are provided.

    Codebook design with differential phase feedback in frequency domain

    公开(公告)号:US11563472B2

    公开(公告)日:2023-01-24

    申请号:US17427585

    申请日:2020-01-31

    IPC分类号: H04B7/0456 H04B7/06 H04W72/04

    摘要: Methods, systems, and devices for wireless communications are described. In some systems, a user equipment (UE) may transmit feedback to a base station indicating phase values for sub-bands in a bandwidth part (BWP). The base station may use the phase feedback to perform precoding on a set of beams. To support a reduced payload overhead for the feedback, the UE may implement differential phase feedback. For example, the UE may divide the BWP into a number of sub-band groups and may generate, for each sub-band group of each beam, a first set of bits indicating an absolute phase value for a first sub-band of the sub-band group. The UE may additionally generate a second set of bits indicating differential phase values for the other sub-bands of each sub-band group. The UE may report the first and second sets of bits for the beams to the base station for precoding.

    User equipment position determination using an uplink random access channel message

    公开(公告)号:US11940546B2

    公开(公告)日:2024-03-26

    申请号:US17310518

    申请日:2020-02-10

    摘要: In some aspects, a base station may transmit, to a user equipment (UE), an instruction that triggers the UE to transmit an uplink random access channel (RACH) message, the instruction identifying a RACH preamble index corresponding to a RACH preamble to be used for the uplink RACH message; transmit, to a plurality of neighbor base stations, information that identifies the RACH preamble index; receive the uplink RACH message from the UE; receive, from the plurality of neighbor base stations, feedback that indicates respective timings with which the uplink RACH message was received by the plurality of neighbor base stations; and estimate a position of the UE based at least in part on a timing with which the uplink RACH message was received by the base station and at least two of the respective timings with which the uplink RACH message was received by the plurality of neighbor base stations.

    Cross link interference detection systems and methods

    公开(公告)号:US11792675B2

    公开(公告)日:2023-10-17

    申请号:US17284740

    申请日:2019-10-15

    摘要: Aspects are provided allowing a first base station to distinguish between cross-link interference and remote interference caused to a second base station and to apply different mitigation mechanisms based on the type of interference. A UE receives from a second base station a reference signal based on a reference signal identifier that indicates a location of the second base station that is experiencing interference from the first base station. The UE sends to the first base station an indication of the reference signal received from the second base station. The first base station receives from the UE the indication of the reference signal from the second base station based on the reference signal identifier. The first base station applies a mitigation mechanism based on whether the reference signal identifier indicates that the second base station is a remote base station or a neighbor base station.

    DCI SIZE LIMIT AND DROPPING RULE FOR REDUCED CAPABILITY UE

    公开(公告)号:US20240007900A1

    公开(公告)日:2024-01-04

    申请号:US18252768

    申请日:2021-01-09

    发明人: Yuwei Ren Huilin Xu

    摘要: Systems and method for providing downlink control information (DCI) sizes prioritization rules to enable a wireless network to monitor and decode a number of DCI sizes without exceeding a DCI sizes budget of a UE are disclosed. In embodiments, a UE monitors for a downlink control information (DCI) message having one of a number of different formats and one of a number of different sizes. The UE is configured with a DCI sizes budget indicating a number of different DCI sizes that the UE is configured to decode. The UE applies a DCI sizes prioritization rule to generate a prioritized set of DCI sizes. The prioritized set of DCI sizes includes a number of DCI sizes to be monitored, which is less than or equal to the DCI sizes budget. The UE decodes the DCI message based on the prioritized set of DCI sizes.