CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority’ to U.S. Provisional Application Senal No. 63/422,417, entitled ‘ ENABLING MACHINE LEARNING TECHNIQUES FOR CHANNEL STATE INFORMATION REPORTING” and filed on November 3, 2022, which is expressly incorporated by reference herein in its entirety ⁷ .

TECHNICAL FIELD

[0002] The present disclosure relates generally to wireless communication, and more particularly, to channel state information (CSI) reports based on machine learning (ML) techniques.

BACKGROUND

[0003] The Third Generation Partnership Project (3GPP) specifies a radio interface referred to as fifth generation (5G) new radio (NR) (5G NR). An architecture for a 5G NR wireless communication system can include a 5G core (5GC) network, a 5G radio access network (5G- RAN), a user equipment (UE), etc. The 5G NR architecture might provide increased data rates, decreased latency, and/or increased capacity compared to other types of wireless communication systems.

[0004] Wireless communication systems, in general, may be configured to provide various telecommunication services (e.g., telephony, video, data, messaging, broadcasts, etc.) based on multiple-access technologies, such as orthogonal frequency division multiple access (OFDMA) technologies, that support communication with multiple UEs. Improvements in mobile broadband have been useful to continue the progression of such wireless communication technologies. For example, the integration of machine learning (ML) techniques into various UE procedures and functionalities may result in increased complexities at the UE. Hence, an implementation of the procedures and/or functionalities based on the ML techniques may cause operations of the UE to be changed in comparison to when the UE implements similar procedures and/or functionalities based on non-ML-techniques.

BRIEF SUMMARY

[0005] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

[0006] A user equipment (UE) can transmit UE capability information to a network entity, such as a base station or a radio unit of a base station, to indicate various functionalities that the UE supports. For example, the UE may transmit UE capability infonnation to the network entity to indicate periodic, aperiodic, and/or semi-persistent channel state information (CSI) reporting capabilities of the UE. The UE capability information may be indicated through one or more parameters, such as a csi-ReportFramework parameter or a csi-ReportFrameworkExt parameter. However, with machine learning (ML) techniques being integrated into the various functionalities of the UE, some parameters indicated in the UE capability information may not define how operations of the UE change between ML-based and non-ML-based applications of the parameters. For example, the UE may support a first maximum number of CSI reports per bandwidth part (BWP) for non-ML-based CSI reports, but support a second (e.g., smaller) maximum number of CSI reports per BWP for ML-based CSI reports due to increased complexities associated with ML-based techniques.

[0007] Aspects of the present disclosure address the above-noted and other deficiencies based on configuring the UE for ML-based CSI reports and/or non-ML-based CSI reports according to the UE capability information indicated to the network entity. In examples, the network entity may receive the UE capability infomiation from a network node other than the UE, such as a core network or a second network entity'. The UE transmits ML-based CSI reports and/or non-ML- based CSI reports to the netw ork entity based on configuration(s) of the UE.

[0008] According to some aspects, the UE receives, from the network entity based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report. The UE measures one or more CSI-RSs received from the network entity on dedicated CSI resources and generates, based on an ML model for CSI compression, the ML-based CSI report using a result of the measuring. The UE transmits, to the network entity, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration. The ML-based CSI report is associated w ith an output of the ML model.

[0009] According to some aspects, the network entity' transmits, to the UE based on the capability of the UE, at least one of the first configuration for the ML-based CSI report or the second configuration for the non-ML-based CSI report, as described above. The network entity transmits, to the UE, the one or more CSI-RSs on the dedicated CSI resources and receives, from the UE, at least one of the ML-based CSI report based on the first configuration and the one or more CSI-RSs or the non-ML-based CSI report based on the second configuration and the one or more CSI-RSs. The ML-based CSI report being associated with a compressed output of the ML model.

BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG. 1 illustrates a diagram of a wireless communications system that includes a plurality of user equipments (UEs) and network entities in communication over one or more cells. [0011] FIG. 2 illustrates a diagram of an example procedure for machine learning (ML)-based channel state information (CSI) compression at a UE and ML-based CSI decompression at a network entity.

[0012] FIG. 3 is a signaling diagram that illustrates ML-based CSI reporting.

[0013] FIGs. 4A-4C are flowcharts of methods of wireless communication at a UE.

[0014] FIGs. 5A-5E are flowcharts of a methods of wireless communication at a network entity.

[0015] FIG. 6 is a diagram illustrating a hardware implementation for an example UE apparatus.

[0016] FIG. 7 is a diagram illustrating a hardware implementation for one or more example network entities.

DETAILED DESCRIPTION

[0017] FIG. 1 illustrates a diagram 100 of a wireless communications system associated with a plurality of cells 190. The wireless communications system includes user equipments (UEs) 102 and base stations 104, where some base stations 104c include an aggregated base station architecture and other base stations 104a- 104b include a disaggregated base station architecture. The aggregated base station architecture includes a radio unit (RU) 106, a distributed unit (DU) 108, and a centralized unit (CU) 110 that are configured to utilize a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node. A disaggregated base station architecture utilizes a protocol stack that is physically or logically distributed among two or more units (e.g., RUs 106, DUs 108, CUs 110). For example, a CU 110 is implemented within a RAN node, and one or more DUs 108 may be co-located with the CU 110, or alternatively, may be geographically or virtually distributed throughout one or multiple other RAN nodes. The DUs 108 may be implemented to communicate with one or more RUs 106. Each of the RU 106, the DU 108 and the CU 110 can be implemented as virtual units, such as a virtual radio unit (VRU), a virtual distributed unit (VDU), or a virtual central unit (VCU). A base station 104 and/or a unit of the base station 104. such as the RU 106, the DU 108, or the CU 110, may be referred to as a transmission reception point (TRP).

[0018] Operations of the base stations 104 and/or network designs may be based on aggregation characteristics of base station functionality. For example, disaggregated base station architectures are utilized in an integrated access backhaul (IAB) network, an open-radio access network (0-RAN) network, or a virtualized radio access network (vRAN) which may also be referred to a cloud radio access network (C-RAN). Disaggregation may include distributing functionality across the two or more units at various physical locations, as well as distributing functionality for at least one unit virtually, which can enable flexibility’ in network designs. The various units of the disaggregated base station architecture, or the disaggregated RAN architecture, can be configured for wired or wireless communication with at least one other unit. For example, the CU 110a communicates with the DUs 108a-108b via respective midhaul links 162 based on Fl interfaces. The DUs 108a-108b may respectively communicate with the RU 106a and the RUs 106b-106c via respective fronthaul links 160. The RUs 106a-106c may communicate with respective UEs 102a- 102c and 102s via one or more radio frequency (RF) access links based on a Uu interface. In examples, multiple RUs 106 and/or base stations 104 may simultaneously serve the UEs 102, such as the UE 102a of the cell 190a that the access links for the RU 106a of the cell 190a and the base station 104c of the cell 190e simultaneously serve. [0019] One or more CUs 110, such as the CU 110a or the CU HOd, may communicate directly with a core network 120 via a backhaul link 164. For example, the CU HOd communicates with the core network 120 over a backhaul link 164 based on a next generation (NG) interface. The one or more CUs 110 may also communicate indirectly with the core network 120 through one or more disaggregated base station units, such as a near-real time RAN intelligent controller (RIC) 128 via an E2 link and a service management and orchestration (SMO) framework 116, which may be associated with a non-real time RIC 118. The near-real time RIC 128 might communicate with the SMO framework 116 and/or the non-real time RIC 118 via an Al link. The SMO framework 116 and/or the non-real time RIC 118 might also communicate with an open cloud (O-cloud) 130 via an 02 link. The one or more CUs 110 may further communicate with each other over a backhaul link 1 4 based on an Xn interface. For example, the CU HOd of the base station 104c communicates with the CU 110a of the base station 104b over the backhaul link 164 based on the Xn interface. Similarly, the base station 104c of the cell 190e may communicate with the CU 110a of the base station 104b over a backhaul link 164 based on the Xn interface. [0020] The RUs 106, the DUs 108. and the CUs 110, as well as the near-real time RIC 128, the non-real time RIC 118, and/or the SMO framework 116, may include (or may be coupled to) one or more interfaces configured to transmit or receive information/signals via a w ired or wireless transmission medium. A base station 104 or any of the one or more disaggregated base station units can be configured to communicate with one or more other base stations 104 or one or more other disaggregated base station units via the wired or wireless transmission medium. In examples, a processor, a memory, and/or a controller associated with executable instructions for the interfaces can be configured to provide communication between the base stations 104 and/or the one or more disaggregated base station units via the wired or wireless transmission medium. For example, a wired interface can be configured to transmit or receive the information/signals over a wired transmission medium, such as for the fronthaul link 160 between the RU 106d and the baseband unit (BBU) 112 of the cell 190d or, more specifically, the fronthaul link 160 between the RU 106d and DU 108d. The BBU 112 includes the DU 108d and a CU 1 lOd, which may also have a wired interface configured between the DU 108d and the CU 1 lOd to transmit or receive the information/signals between the DU 108d and the CU HOd based on a midhaul link 162. In further examples, a wireless interface, which may include a receiver, a transmitter, or a transceiver (such as an RF transceiver), can be configured to transmit or receive the information/signals via the wireless transmission medium, such as for information communicated between the RU 106a of the cell 190a and the base station 104c of the cell 190e via cross-cell communication beams of the RU 106a and the base station 104c.

[0021] One or more higher layer control functions, such as function related to radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP). and the like, may be hosted at the CU 110. Each control function may be associated with an interface for communicating signals based on one or more other control functions hosted at the CU 110. User plane functionality such as central unit-user plane (CU-UP) functionality', control plane functionality such as central unit-control plane (CU-CP) functionality, or a combination thereof may be implemented based on the CU 110. For example, the CU 110 can include a logical split between one or more CU-UP procedures and/or one or more CU-CP procedures. The CU- UP functionality may be based on bidirectional communication with the CU-CP functionality via an interface, such as an El interface (not shown), when implemented in an O-RAN configuration. [0022] The CU 110 may communicate with the DU 108 for network control and signaling. The DU 108 is a logical unit of the base station 104 configured to perform one or more base station functionalities. For example, the DU 108 can control the operations of one or more RUs 106. One or more of a radio link control (RLC) layer, a medium access control (MAC) layer, or one or more higher physical (PHY) layers, such as forward error correction (FEC) modules for encoding/decoding, scrambling, modulation/demodulation, or the like can be hosted at the DU 108. The DU 108 may host such functionalities based on a functional split of the DU 108. The DU 108 may similarly host one or more lower PHY layers, where each lower layer or module may be implemented based on an interface for communications with other layers and modules hosted at the DU 108, or based on control functions hosted at the CU 110.

[0023] The RUs 106 may be configured to implement lower layer functionality. For example, the RU 106 is controlled by the DU 108 and may correspond to a logical node that hosts RF processing functions, or lower layer PHY functionality, such as execution of fast Fourier transform (FFT). inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc. The functionality of the RUs 106 may be based on the functional split, such as a functional split of lower layers.

[0024] The RUs 106 may transmit or receive over-the-air (OTA) communication with one or more UEs 102. For example, the RU 106b of the cell 190b communicates with the UE 102b of the cell 190b via a first set of communication beams 132 of the RU 106b and a second set of communication beams 134b of the UE 102b, which may correspond to inter-cell communication beams or cross-cell communication beams. For example, the UE 102b of the cell 190b may communicate with the RU 106a of the cell 190a via a third set of communication beams 134a of the UE 102b and an RU beam set 136 of the RU 106a. Both real-time and non-real-time features of control plane and user plane communications of the RUs 106 can be controlled by associated DUs 108. Accordingly, the DUs 108 and the CUs 110 can be utilized in a cloud-based RAN architecture, such as a vRAN architecture, whereas the SMO framework 116 can be utilized to support non-virtualized and virtualized RAN network elements. For non-virtualized network elements, the SMO framework 1 16 may support deployment of dedicated physical resources for RAN coverage, where the dedicated physical resources may be managed through an operations and maintenance interface, such as an 01 interface. For virtualized network elements, the SMO framework 116 may interact with a cloud computing platform, such as the O-cloud 130 via the 02 link (e.g., cloud computing platform interface), to manage the network elements. Virtualized netw ork elements can include, but are not limited to, RUs 106, DUs 108, CUs 110, near-real time RICs 128, etc.

[0025] The SMO framework 116 may be configured to utilize an 01 link to communicate directly with one or more RUs 106. The non-real time RIC 118 of the SMO framework 116 may also be configured to support functionalities of the SMO framew ork 116. For example, the non- real time RIC 118 implements logical functionality that enables control of non-real time RAN features and resources, features/applications of the near-real time RIC 128, and/or artificial intelligence/ machine learning (AI/ML) procedures. The non-real time RIC 118 may communicate with (or be coupled to) the near-real time RIC 128, such as through the Al interface. The near- real time RIC 128 may implement logical functionality' that enables control of near-real time RAN features and resources based on data collection and interactions over an E2 interface, such as the E2 interfaces between the near-real time RIC 128 and the CU 110a and the DU 108b.

[0026] The non-real time RIC 118 may receive parameters or other information from external servers to generate AI/ML models for deployment in the near-real time RIC 128. For example, the non-real time RIC 118 receives the parameters or other information from the O-cloud 130 via the 02 link for deployment of the AI/ML models to the real-time RIC 128 via the Al link. The near-real time RIC 128 may utilize the parameters and/or other information received from the non- real time RIC 118 or the SMO framework 116 via the Al link to perform near-real time functionalities. The near-real time RIC 128 and the non-real time RIC 118 may be configured to adjust a performance of the RAN. For example, the non-real time RIC 118 monitors patterns and long-term trends to increase the performance of the RAN. The non-real time RIC 118 may also deploy AI/ML models for implementing corrective actions through the SMO framework 116, such as initiating a reconfiguration of the 01 link or indicating management procedures for the Al link. [0027] Any combination of the RU 106, the DU 108, and the CU 110, or reference thereto individually, may correspond to a base station 104. Thus, the base station 104 may include at least one of the RU 106, the DU 108, or the CU 110. The base stations 104 provide the UEs 102 with access to the core network 120. That is, the base stations 104 might relay communications between the UEs 102 and the core network 120. The base stations 104 may be associated with macrocells for high-power cellular base stations and/or small cells for low-power cellular base stations. For example, the cell 190e corresponds to a macrocell, whereas the cells 190a-l 90d may correspond to small cells. Small cells include femtocells, picocells, microcells, etc. A cell structure that includes at least one macrocell and at least one small cell may be referred to as a "heterogeneous network.”

[0028] Transmissions from a UE 102 to abase station 104/RU 106 are referred to uplink (UL) transmissions, whereas transmissions from the base station 104/RU 106 to the UE 102 are referred to as downlink (DL) transmissions. Uplink transmissions may also be referred to as reverse link transmissions and downlink transmissions may also be referred to as forward link transmissions. For example, the RU 106d utilizes antennas of the base station 104c of cell 190d to transmit a downlink/forward link communication to the UE 102d or receive an uplink/reverse link communication from the UE 102d based on the Uu interface associated with the access link between the UE 102d and the base station 104c/RU 106d.

[0029] Communication links between the UEs 102 and the base stations 104/RUs 106 may be based on multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and/or transmit diversity. The communication links may be associated with one or more earners. The UEs 102 and the base stations 104/RUs 106 may utilize a spectrum bandwidth of Y MHz (e.g., 5, 10, 15, 20, 100, 400, 800, 1600, 2000, etc. MHz) per carrier allocated in a carrier aggregation of up to a total of Yx MHz, where x component carriers (CCs) are used for communication in each of the uplink and downlink directions. The carriers may or may not be adjacent to each other along a frequency spectrum. In examples, uplink and downlink carriers may be allocated in an asymmetric manner, more or fewer carriers may be allocated to either the uplink or the downlink. A primary component carrier and one or more secondary component carriers may be included in the component carriers. The primary component carrier may be associated with a primary cell (PCell) and a secondary component carrier may be associated with as a secondary cell (SCell).

[0030] Some UEs 102, such as the UEs 102a and 102s, may perform device-to-device (D2D) communications over sidelink. For example, a sidelink communication/D2D link utilizes a spectrum for a wireless wide area network (WWAN) associated with uplink and downlink communications. The sidelink communication/D2D link may also use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and/or a physical sidelink control channel (PSCCH), to communicate information between UEs 102a and 102s. Such sidelink/D2D communication may be performed through various wireless communications systems, such as wireless fidelity (Wi-Fi) systems, Bluetooth systems, Long Term Evolution (LTE) systems, New Radio (NR) systems, etc.

[0031] The electromagnetic spectrum is often subdivided into different classes, bands, channels, etc., based on different frequencies/wavelengths associated with the electromagnetic spectrum. Fifth-generation (5G) NR is generally associated with two operating frequency ranges (FRs) referred to as frequency range 1 (FR1) and frequency range 2 (FR2). FR1 ranges from 410 MHz - 7.125 GHz and FR2 ranges from 24.25 GHz - 71.0 GHz, which includes FR2-1 (24.25 GHz - 52.6 GHz) and FR2-2 (52.6 GHz - 71.0 GHz). Although a portion of FR1 is actually greater than 6 GHz, FR1 is often referred to as the “sub-6 GHz” band. In contrast, FR2 is often referred to as the “millimeter wave” (mmW) band. FR2 is different from, but a near subset of, the “extremely high frequency” (EHF) band, which ranges from 30 GHz - 300 GHz and is sometimes also referred to as a "millimeter wave” band. Frequencies between FR1 and FR2 are often referred to as “mid-band” frequencies. The operating band for the mid-band frequencies may be referred to as frequency range 3 (FR3), which ranges 7.125 GHz - 24.25 GHz. Frequency bands within FR3 may include characteristics of FR1 and/or FR2. Hence, features of FR1 and/or FR2 may be extended into the mid-band frequencies. Higher operating frequency bands have been identified to extend 5G NR communications above 52.6 GHz associated with the upper limit of FR2. Three of these higher operating frequency bands include FR2-2, which ranges from 52.6 GHz - 71.0 GHz, FR4, which ranges from 71.0 GHz - 114.25 GHz, and FR5, which ranges from 114.25 GHz - 300 GHz. The upper limit of FR5 corresponds to the upper limit of the EHF band. Thus, unless otherwise specifically stated herein, the term “sub-6 GHz” may refer to frequencies that are less than 6 GHz, within FR1, or may include the mid-band frequencies. Further, unless otherwise specifically stated herein, the term “millimeter wave”, or mmW, refers to frequencies that may include the mid-band frequencies, may be within FR2-1, FR4, FR2-2, and/or FR5, or may be within the EHF band.

[0032] The UEs 102 and the base stations 104/RUs 106 may each include a plurality of antennas. The plurality of antennas may correspond to antenna elements, antenna panels, and/or antenna arrays that may facilitate beamforming operations. For example, the RU 106b transmits a downlink beamfonned signal based on a first set of beams 132 to the UE 102b in one or more transmit directions of the RU 106b. The UE 102b may receive the downlink beamformed signal based on a second set of beams 134b from the RU 106b in one or more receive directions of the UE 102b. In a further example, the UE 102b may also transmit an uplink beamformed signal to the RU 106b based on the second set of beams 134b in one or more transmit directions of the UE 102b. The RU 106b may receive the uplink beamformed signal from the UE 102b in one or more receive directions of the RU 1 6b. The UE 102b may perform beam training to determine the best receive and transmit directions for the beam formed signals. The transmit and receive directions for the UEs 102 and the base stations 104/RUs 106 might or might not be the same. In further examples, beamformed signals may be communicated between a first base station 104c and a second base station 104b. For instance, the RU 106a of cell 190a may transmit a beamformed signal based on the RU beam set 136 to the base station 104c of cell 190e in one or more transmit directions of the RU 106a. The base station 104c of the cell 190e may receive the beamformed signal from the RU 106a based on a base station beam set 138 in one or more receive directions of the base station 104c. Similarly, the base station 104c of the cell 190e may transmit a beamformed signal to the RU 106a based on the base station beam set 138 in one or more transmit directions of the base station 104c. The RU 106a may receive the beamformed signal from the base station 104c of the cell 190e based on the RU beam set 136 in one or more receive directions of the RU 106a.

[0033] The base station 104 may include and/or be referred to as a network entity. That is, “network entity" may refer to the base station 104 or at least one unit of the base station 104, such as the RU 106. the DU 108, and/or the CU 110. The base station 104 may also include and/or be referred to as a next generation evolved Node B (ng-eNB), a generation NB (gNB), an evolved NB (eNB), an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a TRP, a network node, network equipment, or other related terminology. The base station 104 or an entity at the base station 104 can be implemented as an I AB node, a relay node, a sidelink node, an aggregated (monolithic) base station with an RU 106 and a BBU that includes a DU 108 and a CU 110, or as a disaggregated base station 104b including one or more of the RU 106, the DU 108, and/or the CU 110. A set of aggregated or disaggregated base stations 104a-104b may be referred to as a next generation-radio access network (NG-RAN). In some examples, the UE 102b operates in dual connectivity (DC) with the base station 104a and the base station 104b. In such cases, the base station 104a can be a master node and the base station 104b can be a secondary node. In other examples, the UE 102b operates in DC with the DU 108a and the DU 108b. In such cases, the DU 108a can be the master node and the DU 108b can be the secondary node.

[0034] The core network 120 may include an Access and Mobility Management Function (AMF) 121, a Session Management Function (SMF) 122, a User Plane Function (UPF) 123, a Unified Data Management (UDM) 124, a Gateway Mobile Location Center (GMLC) 125, and/or a Location Management Function (LMF) 126. The core network 120 may also include one or more location servers, which may include the GMLC 125 and the LMF 126, as well as other functional entities. For example, the one or more location servers include one or more location/positioning servers, which may include the GMLC 125 and the LMF 126 in addition to one or more of a position determination entity' (PDE), a serving mobile location center (SMLC), a mobile positioning center (MPC), or the like.

[0035] The AMF 121 is the control node that processes the signaling between the UEs 102 and the core network 120. The AMF 121 supports registration management, connection management, mobility' management, and other functions. The SMF 122 supports session management and other functions. The UPF 123 supports packet routing, packet forwarding, and other functions. The UDM 124 supports the generation of authentication and key agreement (AKA) credentials, user identification handling, access authorization, and subscription management. The GMLC 125 provides an interface for clients/applications (e.g., emergency services) for accessing UE positioning information. The LMF 126 receives measurements and assistance information from the NG-RAN and the UEs 102 via the AMF 121 to compute the position of the UEs 102. The NG-RAN may utilize one or more positioning methods in order to determine the position of the UEs 102. Positioning the UEs 102 may involve signal measurements, a position estimate, and an optional velocity computation based on the measurements. The signal measurements may be made by the UEs 102 and/or the serving base stations 104/RUs 106.

[0036] Communicated signals may also be based on one or more of a satellite positioning system (SPS) 114. such as signals measured for positioning. In an example, the SPS 114 of the cell 190c may be in communication with one or more UEs 102, such as the UE 102c, and one or more base stations 104/RUs 106, such as the RU 106c. The SPS 114 may correspond to one or more of a Global Navigation Satellite System (GNSS), a global position system (GPS), a nonterrestrial network (NTN), or other satellite position/location system. The SPS 114 may be associated with LTE signals, NR signals (e.g.. based on round trip time (RTT) and/or multi-RTT), wireless local area network (WLAN) signals, a terrestrial beacon system (TBS), sensor-based information, NR enhanced cell ID (NR E-CID) techniques, downlink angle-of-departure (DL- AoD), downlink time difference of arrival (DL-TDOA), uplink time difference of arrival (UL- TDOA), uplink angle-of-arrival (UL-AoA). and/or other systems, signals, or sensors.

[0037] The UEs 102 may be configured as a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a GPS, a multimedia device, a video device, a digital audio player (e.g., moving picture experts group (MPEG) audio layer-3 (MP3) player), a camera, a game console, a tablet, a smart device, a wearable device, a vehicle, an utility meter, a gas pump, appliances, a healthcare device, a sensor/actuator, a display, or any other device of similar functionality. Some of the UEs 102 may be referred to as Internet of Things (loT) devices, such as parking meters, gas pumps, appliances, vehicles, healthcare equipment, etc. The UE 102 may also be referred to as a station (STA), a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communications device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a mobile client, a client, or other similar terminology. The term UE may also apply to a roadside unit (RSU). which may communicate with other RSU UEs, non-RSU UEs, a base station 104, and/or an entity at a base station 104, such as an RU 106.

[0038] Still referring to FIG. 1 , in certain aspects, the UE 102 may include a channel state information (CSI) report component 140 configured to receive, from a network entity based on a capability of the UE, at least one of a first configuration for a machine learning (ML)-based CSI report or a second configuration for a non-ML-based CSI report; measure one or more channel state information-reference signals (CSI-RSs) received from the network entity on dedicated CSI resources; generate, based on an ML model for CSI compression, the ML-based CSI report using a result of the measuring; and transmit, to the network entity, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration, the ML-based CSI report associated with an output of the ML model.

[0039] In certain aspects, the base station 104 or a network entity of the base station 104 may include a CSI report configuration component 150 configured to transmit, to a UE based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report; transmit, to the UE, one or more CSI-RSs on dedicated CSI resources; receive, from the UE, at least one of the ML-based CSI report based on the first configuration and the one or more CSI-RSs or the non-ML-based CSI report based on the second configuration and the one or more CSI-RSs. the ML-based CSI report being associated with a compressed output of an ML model.

[0040] Accordingly, FIG. 1 describes a wireless communication system that may be implemented in connection with aspects of one or more other figures described herein, such as aspects illustrated in FIGs. 2-3. Further, although the following description may be focused on 5G NR, the concepts described herein may be applicable to other similar areas, such as 5G- Advanced and future versions, LTE, LTE-advanced (LTE-A), and other wireless technologies, such as 6G.

[0041] FIG. 2 illustrates a diagram 200 of an example procedure for ML-based CSI compression at a UE 102 and ML-based CSI decompression at anetwork entity 104. The UE 102 and the network entity 104, such as a base station or an entity' of a base station, might perform MIMO communications, where the network entity' 104 can use CSI to select a digital precoder (e.g., precoding matrix) for the UE 102. The network entity 104 might configure CSI reporting from the UE 102 via RRC signaling (e.g., CSI-ReportConflg), where the UE 102 may use a first CSI-RS 245 as a channel measurement resource (CMR) for the UE 102 to measure a downlink channel. The network entity 104 may also configure a second CSI-RS 245 (e.g., via the CSI- ReportConfig) as an interference measurement resource (IMR) for the UE 102 to measure interference to the downlink channel. The first CSI-RS and the second CSI-RS can be a same CSI-RS(s) 245 or different CSI-RSs. Accordingly, the UE 102 may estimate 250 a channel between the UE 102 and the network entity 104 and obtains (e.g., determines and/or generates) raw CSI, based on the CSI-RS(s) 245. [0042] The UE 102 may use a neural network to perform 270a CSI compression (e.g., based on an ML-based CSI generator) of the raw CSI to obtain compressed CSI. The UE 102 includes the compressed CSI in a CSI report 285 and transmits 280a the CSI report 285 to the network entity' 104. In some implementations, the UE 102 includes in the CSI report 285 a rank indicator (RI), a precoder matrix indicator (PMI), a channel quality indicator (CQI). a layer indicator (LI), a layer 1 reference signal received power (Ll-RSRP), a layer 1 reference signal received quality (Ll-RSRQ), and/or a layer 1 signal-to-interference plus noise ratio (Ll-SINR). The CQI might be indicative of a SINR for determining a modulation and coding scheme (MCS). The LI might indicate a strongest layer, such as used for multi-user (MU)-MIMO paring of a low rank transmission with precoder selection 260. such for phase-tracking reference signals (PT-RSs). In other implementations, the UE 102 refrains from including the RI, the PMI, the CQI, the LI, the Ll-RSRP, the Ll-RSRQ, and/or the Ll-SINR in the CSI report 285.

[0043] The network entity' 104 may configure (e.g., based on the CSI-ReportConfig) a time domain behavior, such as periodic, semi-persistent, or aperiodic reporting, for the transmission 280a of the CSI report 285 to the network entity 104. In examples, the network entity 104 may activate/deactivate a semi -persistent CSI report from the UE 102 using a MAC-control element (MAC-CE). The network entity 104 may trigger an aperiodic CSI report from the UE 102 based on transmission of downlink control information (DCI) to the UE 102. The network entity’ 104 may receive a periodic CSI report from the UE 102 on physical uplink control channel (PUCCH) resources (e.g., configured via the CSI-ReportConfig). The CSI-ReportConfig may also be used to configure PUCCH resources for transmission 280a of the semi-persistent CSI report to the network entity 104. In other examples, transmission 280a of the semi-persistent CSI report to the network entity 104 may be on physical uplink shared channel (PUSCH) resources triggered by the DCI. The UE 102 may likewise transmit 280a the aperiodic CSI report on the PUSCH resources triggered by the DCI.

[0044] For a first resource element (RE) k associated with the CSI-RS(s) 245, the received signal at the UE 102 may be detennined based on:

Y _k = H _k X _k + N _k yvhere H _k indicates an effective channel including an analog beamforming yveight yvith dimensions NRX by NTX, X _k corresponds to a CSI-RS 245 at RE k, N _k corresponds to the interference plus noise. NR _X corresponds to a first number of receiving ports, and NT _X corresponds to a second number of transmission ports.

[0045] For a second RE k associated yvith a physical doyvnlink shared channel (PDSCH), the signal received at the UE 102 may be determined based on: Y _k = H _k W _k X _k + N _k where W _k indicates the precoder. The network entity 104 might select 260 a same precoder for subcarriers within a subband (e.g., bundled in a physical resource block (PRB)).

[0046] The UE 102 can use a Type 2 CSI codebook for CSI measurement and reporting, where the precoder might be based on:

W = W^ W ₂ where W _± corresponds to a wideband precoder with dimension NTX by 2L, W ₂ corresponds to a subband precoder with dimensions 2L by v, L indicates a number of beams, and v indicates a number of layers, which may correspond to RI+1. W might be based on the codebook, while W ₂ might be based on a power and angle associated with each transmission. Since W ₂ is based on the subband and there may be multiple subbands for the CSI report 285, the UE 102 might experience a large overhead to transmit 280a the CSI report 285 to the network entity 104.

[0047] The CSI report 285 may be based on the bandwidth for the CSI-RS 245. In examples, the codebook that the network entity might use for precoder selection 260 of W1 may be based on: where ® corresponds to a Kronecker product, L indicates the number of beams, which may be configured via RRC signaling, Ni and N2 correspond to the number of ports, Oi and O2 correspond to an oversampling factor in a horizontal and vertical domain, which may be configured via the RRC signaling. Candidate values for the oversampling factor may be based on the number of CSI-RS ports indicated via Ni and N2. The codebook might include precoders with different values m and n. In some examples, the candidate values may be predefined based on standardized protocols.

[0048] The network entity 104 receives 280b the CSI report 285 transmitted 280a from the UE 102 and decodes the CSI report 285 including the compressed CSI. The decoded CSI report 285 including the compressed CSI may be input to a neural network at the network entity 104 for CSI decompression 270b. That is, the neural network at the network entity 104 may decompress 270b the compressed CSI 270a to obtain a decompressed CSI 270b. The network entity 104 may select 260 a precoder based on the CSI decompression 270b. In some implementations, such as cases where the CSI report 285 includes the RI, the PMI, the CQI, the LI, and/or the Ll-RSRP, the network entity 104 can use the decompressed CSI 270b, the RI, the PMI, the CQI, the LI, and/or the Ll-RSRP to jointly determine the digital precoder (e.g.. precoding matrix) or perform the precoder selection 260.

[0049] In some implementations, the UE 102 transmits CSI report capabilities to the network entity' 104 to indicate that the UE 102 supports CSI reporting for periodic CSI reports, aperiodic CSI reports, and/or semi-persistent CSI reports. The network entity 104 configures the UE 102 to transmit 280a CSI reports 285 based on the CSI report capabilities. In some implementations, the CSI report capabilities correspond to a csi-ReportFramewor parameter, a csi- ReportFrameworkExt parameter, and/or capabilities associated with the csi-ReportFramework parameter and/or the csi-ReportFrameworkExt.

[0050] The csi-ReportFramewor parameter indicates whether the UE 102 supports the CSI report framework. Capability signalling for the CSI report framework can include parameters, such as a mcixNumberPeriodicCSI-PerBWP-ForCSI-Report that indicates a maximum number of periodic CSI report settings per bandwidth part (BWP) for the CSI report 285; a maxNumberPe odlcCSI-PerBWP-ForBeamReport that indicates a maximum number of periodic CSI report settings per BWP for a beam report; a maxNumberAperiodicCSI-PerBWP-ForCSI- Report that indicates a maximum number of aperiodic CSI report settings per BWP for the CSI report 285; a maxNumberAperiodicCSI-PerBWP-ForBeamReport that indicates a maximum number of aperiodic CSI report settings per BWP for beam report; a maxNumberAperiodicCSI- triggeringStatePerCC that indicates a maximum number of aperiodic CSI triggering states in a CSI-AperiodicTriggerStatelAst per CC; a maxNumberSemiPersistentCSI-PerBWP-ForCSI- Report that indicates a maximum number of semi-persistent CSI report settings per BWP for the CSI report 285; a maxNumberSemiPersistentCSI-PerBWP-ForBeamReport that indicates a maximum number of semi-persistent CSI report settings per BWP for the beam report; and/or a simultaneousCSI-ReportsPerCC that indicates a number of CSI report(s) 285 for which the UE 102 can measure and process reference signals simultaneously in a CC of a band associated with the capability. The CSI report 285 may be associated with periodic, semi-persistent and/or aperiodic CSI, latency classes, and different codebook types. The CSI report 285 associated with the simultaneousCSI-ReportsPerCC may correspond to beam reporting and CSI reporting. The UE 102 may report csi-ReportFramework to the network entity' 104. [0051] The csi-ReportFramewor and/or the csi-ReportFrameworkExt indicated to the network entity 104 might not be indicative of ML-based CSI reporting capabilities and/or non- ML-based CSI reporting capabilities. For example, the UE 102 may support a first maximum number of periodic ML-based CSI report settings (e.g., per BWP for the CSI report 285) and a second maximum number of periodic non-ML-based CSI report settings (e.g., per BWP for the CSI report 285). Hence, the network entity 104 may be unable to determine how the UE 102 implements the maxNumberPeriodicCSI-PerBWP-ForCSI-Report to the first maximum number, the second maximum number, or a sum of the first maximum number and the second maximum number. Similar ambiguities may also occur for other CSI report capabilities associated with the csi-ReportFramewor and/or the csi-ReportFrameworkExt, as described above. FIG. 2 describes CSI compression/decompression using an ML model. FIG. 3 describes CSI reports transmitted to the network entity 104, both with and without implementation of the techniques described in FIG. 2.

[0052] FIG. 3 is a signaling diagram 300 that illustrates ML-based CSI reporting. The UE 102 transmit 306 UE capability’ information (e.g., a UEC apability Information message or capabilities in the UEC apability Information message) to the network entity' 104. The UE capability information may indicate CSI report capabilities of the UE 102. The UE 102 may also indicate other capabilities in the UE capability infonnation. In some implementations, the UE 102 receives a UE capability enquiry message (e.g., UECapabilityEnquiry message) from the network entity 104. In response to the UE capability enquiry message, the UE 102 may transmit 306 the UE capability information including the CSI report capabilities to the network entity 104. The UE 102 may generate a container information element (IE) including the CSI report capabilities and/or other capabilities, and the container may be included in the UE capability information. The container IE may be a UE-NR-Capability IE or a UE-6G-C apability IE, in some examples. Alternatively, the network entity 104 may receive 308 the UE capability information from a different network node than the UE 102. For example, the network entity 104 may receive 308 the CSI report capabilities or the container IE from another network entity/base station, which may be similar to the network entity 104, or a core network or core network entity, such as an AMF, as described with respect to FIG. 1.

[0053] The CSI report capabilities may include ML-based CSI report capabilities and/or non- ML-based CSI report capabilities. For example, the UE 102 may indicate capabilities for non- ML-based CSI reports in the non-ML-based CSI report capabilities. Based on the non-ML-based CSI report capabilities, the UE 102 and the network entity 104 may perform a non-ML-based CSI reporting procedure 310. The network entity' 104 transmits 312, to the UE 102, a non-ML-based CSI report configuration to configure the UE 102 for non-ML-based CSI reporting. The non-ML- based CSI report configuration may include CSI-ReportConfig IE(s).

[0054] After transmitting 312 the non-ML-based CSI report configuration, the network entity 104 may transmit 314, to the UE 102, a trigger for the non-ML-based CSI report, followed by transmission 316 of one or more CSI-RS(s) to the UE 102 in accordance with the non-ML-based CSI report configuration. The UE 102 receives 316 the CSI-RS(s) from the network entity 104 and performs channel estimation and/or measurements on the CSLRS(s) in accordance with the configuration. The UE 102 generates a non-ML-based CSI report based on the channel estimation and/or the measurement, and transmits 318 the non-ML-based CSI report to the network entity 104. In some implementations, the UE 102 includes non-ML-based CSI in the non-ML-based CSI report. The non-ML-based CSI may correspond to a RI, a PMI, a CQI, a LI, a Ll-RSRP, a Ll-RSRQ, and/or a Ll-SINR.

[0055] In some implementations, the network entity 104 can transmit 312 one or more RRC messages with the configuration for the non-ML-based CSI report. The one or more RRC messages may include an RRCReconfiguration message. In response to each RRC message, the UE 102 can transmit an RRC response message (e.g., RRCReconfigurationComplete message) to the network entity 104. In some cases, the UE 102 may be in dual connectivity' with the network entity 104 (e.g., operating as a secondary node (SN)) and another network entity’ (e.g., operating as a master node (MN); not shown in FIG. 3) that is similar to the network entity ⁷ 104. The SN may transmit an RRC message to the UE 102, as described above. The SN may ⁷ also transmit an RRC message to the UE 102 via the MN.

[0056] The non-ML-based CSI report configuration may include a CSI resource configuration for the CSI-RS(s) 316. The CSI-RS(s) 316 may correspond to periodic CSI-RS, semi-persistent CSI-RS, or aperiodic CSI-RS. Thus, the CSI resource configuration can configure CSI resources for the periodic CSI-RS, the semi-persistent CSI-RS, or the aperiodic CSI-RS. The network entity ⁷ 104 transmits 316 the periodic CSI-RS on a periodic basis in accordance with the CSI resource configuration for the periodic CSI-RS. The network entity 104 transmits 316 the semi-persistent CSI-RS on a semi-persistent basis in accordance with the CSI resource configuration for the semi- persistent CSI-RS. The network entity 104 transmits 316 the aperiodic CSI-RS on a one-shot basis for the UE 102 to transmit 318 an aperiodic non-ML-based CSI report in accordance with the aperiodic CSI resource configuration.

[0057] The network entity 104 may transmit 316 the CSLRS(s) from N _R antenna ports, where N _R corresponds to a maximum number of downlink layers configured via the non-ML-based CSI report configuration or the CSI resource configuration. The network entity 104 may transmit 316 the CSI-RS(s), or a subset of the CSI-RS(s), with a precoder. In other implementations, the network entity 104 may transmit 316 the CSI-RS(s), or the subset of the CSI-RS(s), without the precoder.

[0058] The non-ML -based CSI report configuration and report may be semi-persistent and configure a semi-persistent non-ML-based CSI report. The UE 102 refrains from transmitting 318 semi-persistent non-ML-based CSI reports until receiving 314 a trigger command from the network entity 104 triggering the UE 102 to transmit 318 the semi-persistent non-ML-based CSI report in accordance with the semi -persistent non-ML-based CSI report configuration. After or in response to receiving 314 the trigger command 314 from the network entity 104, the UE 102 performs channel estimation and/or measurements on the CSI-RS(s), generates the semi-persistent non-ML-based CSI report, and transmits 318 the semi-persistent non-ML-based CSI report to the network entity ⁷ 104. In some implementations, the UE 102 transmits 318 the semi -persistent non- ML-based CSI reports on PUCCH resources configured via the non-ML-based CSI report configuration. In other implementations, the UE 102 transmits 318 the semi-persistent non-ML- based CSI report on PUSCH resources configured via the non-ML-based CSI report configuration and/or the trigger command. The trigger command may be a MAC-CE or a DCI.

[0059] For semi-persistent CSI-RS, the network entity 104 may transmit an activation command to the UE 102 to indicate that the semi-persistent CSI-RS is activated. After receiving the activation command, the UE 102 determines that transmission of the semi-persistent CSI-RS is activated. The network entity 104 may transmit the activation command before or after transmitting 314 the trigger command. Alternatively, the network entity ⁷ 104 may transmit, to the UE 102, a MAC protocol data unit (PDU) including the activation command and the trigger command. The activation command may be a MAC-CE. The UE 102 may perform channel estimation and/or measurements based on the CSI-RS or a portion of the CSI-RS in response to receiving 314 the trigger command. In other implementations, the UE 102 may perform the channel estimation and/or measurements based on the CSI-RS or a portion of the CSI-RS in response to the semi-persistent non-ML-based CSI report configuration and before receiving 314 the trigger command.

[0060] The non-ML-based CSI report configuration and report may be for periodic non-ML- based CSI reporting, such that the UE 102 may perform the channel estimation and/or measurements based on the CSI-RS, generate non-ML-based CSI reports based on the channel estimation and/or measurements, and transmits 318 the periodic non-ML-based CSI report to the network entity 104. The UE 102 may perform channel estimation and/or measurements based on the CSI-RS(s) or a portion of the CSI-RS, generate periodic non-ML-based CSI reports based on the channel estimation and/or measurements, and transmits 318 the periodic non-ML-based CSI report to the network entity 104 after receiving 312 the periodic non-ML-based CSI report configuration. Thus, the network entity 104 does not transmit 314 a trigger command to the UE 102 to trigger transmission of the periodic non-ML-based CSI report. The UE 102 transmits 318 the periodic non-ML-based CSI report on PUCCH resources configured via the non-ML-based CSI report configuration. In other implementations, the UE 102 transmits 318 the periodic non- ML-based CSI report on PUSCH resources configured via the non-ML-based CSI report configuration and/or the DCI that the UE 102 receives from the network entity 104. The DCI may include an uplink grant for the UE 102 to transmit user data, such that the DCI does not serve as a triggering command.

[0061] The non-ML-based CSI report configuration and report may be for aperiodic non-ML- based CSI reporting. For aperiodic non-ML-based CSI reporting, the UE 102 refrains from transmitting 318 an aperiodic non-ML-based CSI report until the UE 102 receives 314, from the network entity 104, the trigger command for triggering the UE 102 to transmit 318 the aperiodic non-ML-based CSI report in accordance with the aperiodic non-ML-based CSI report configuration. After transmitting the aperiodic non-ML-based CSI report configuration, the network entity 104 transmits 314 the trigger command to the UE 102 for triggering the aperiodic non-ML-based CSI report in accordance with the aperiodic non-ML-based CSI report configuration. In response to receiving 314 the trigger command, the UE 102 performs channel estimation and/or measurements on the CSI-RS, generates a single aperiodic non-ML-based CSI report, and transmits 318 the aperiodic non-ML-based CSI report to the network entity 104 in accordance with the aperiodic non-ML-based CSI report configuration. The trigger command may be a MAC-CE or a DCI.

[0062] The events 312, 314, 316, and 318 are collectively referred to in FIG. 3 as a non-ML- based CSI reporting procedure 310.

[0063] In some implementations, the CSI report capabilities include ML-based CSI report capabilities. That is. the UE 102 indicates capabilities for ML-based CSI reporting. Based on the ML-based CSI report capabilities, the UE 102 and the network entity 104 may perform an ML- based CSI reporting procedure 320. The UE 102 transmits 322 an ML-based CSI report configuration to the UE 102 that configures the UE 102 to transmit 328 an ML-based CSI report to the network entity 104. For example, the ML-based CSI report configuration may include information, such as CSI-ReportConfl IE(s) or other RRC IE(s).

[0064] After transmitting 322 the ML-based CSI report configuration, the network entity 104 transmits 316 one or more CSLRSs to the UE 102 in accordance with the ML-based CSI report configuration. The UE 102 receives 316 the CSI-RS(s) and performs channel estimation and/or measurements based on the CSI-RS(s). The UE 102 generates an ML-based CSI report based on the channel estimation and/or measurements, as well as an ML model, and transmits 328 the ML- based CSI report to the network entity 104. The network entity 104 may include an indication of the ML model in the ML-based CSI report configuration. The indication can be an ML model identifier (ID) identifying the ML model. In other implementations, the network entity 104 does not configure the ML model in the ML-based CSI report configuration. The UE 102 may determine the ML model based on a predetermined configuration stored at the UE 102. The network entity 104 enables/configures ML-based CSI compression for the UE 102 via the ML- based CSI report configuration, and the UE 102 generates compressed CSI based on the ML model. The 102 transmits the compressed CSI in the ML-based CSI report, as described with respect to FIG. 2.

[0065] The network entity 104 may transmit 323 RRC message(s) to the UE 102, which may include the ML-based CSI report configuration for ML-based CSI report. The ML-based CSI report configuration may include CSI-ReportConfig IE(s). The ML-based CSI report configuration may also include configuration parameters to rel ease/ reconfigure the configuration for the ML-based CSI report. For example, after applying the configuration parameters for the ML-based CSI report configuration, the UE 102 may switch to non-ML-based CSI reporting. Similarly, after applying the configuration parameters for the non-ML-based CSI report configuration, the UE 102 may switch back to ML-based CSI reporting. In examples, RRC message(s) transmitted 323 from the network entity ⁷ 104 to the UE 102 may include an RRCReconfigurcition message or a CSI report configuration release message. In response to each RRC message, the UE 102 may transmit an RRC response message (e.g., RRCReconfigurationComplete message) to the network entity 104. In some cases, the UE 102 may be in dual connectivity with the network entity' 104 (e.g., operating as a SN) and another network entity (e.g., operating as a MN: not shown in FIG. 3) that is similar to the network entity 104. The SN 104 may transmit 323 the RRC messages to the UE 102, as described above, or the SN 104 may transmit the RRC messages to the UE 102 via the MN.

[0066] The ML-based CSI report configuration may indicate or include a CSI resource configuration for the CSI-RS(s). The CSI-RS(s) may correspond to periodic CSI-RS, semi- persistent CSI-RS, and/or aperiodic CSI-RS. The CSI resource configuration may be for configuring the penodic CSI-RS, the semi-persistent CSI-RS, and/or the aperiodic CSI-RS. The netw ork entity 104 transmits 316 the periodic CSI-RS on a periodic basis in accordance with the CSI resource configuration for the periodic CSI-RS. The network entity' 104 transmits 316 the semi-persistent CSI-RS on a semi-persistent basis in accordance with the CSI resource configuration for the semi-persistent CSI-RS. The network entity 104 transmits 316 the aperiodic CSI-RS on a one-shot basis for the UE 102 to transmit 328 an aperiodic ML-based CSI report in accordance with the aperiodic CSI resource configuration.

[0067] The network entity 104 may transmit 316 the CSI-RS from N _R antenna ports, where N _R corresponds to a maximum number of downlink layers configured in the ML-based CSI report configuration or the CSI resource configuration. In some implementations, the network entity 104 may transmit 316 the CSI-RS(s), or a subset of the CSI-RS(s), with a precoder. In other implementations, the network entity 104 may transmit the CSI-RS(s). or the subset of the CSI- RS(s), without the precoder.

[0068] The ML-based CSI report configuration and report may correspond to a semi- persistent ML-based CSI report configuration for semi-persistent ML-based CSI reporting, such that the UE 102 may refrain from transmitting 328 the semi-persistent ML-based CSI report until the UE 102 receives 324, from the network entity 104, a trigger command for triggering the UE 102 to transmit 328 the semi-persistent ML-based CSI report in accordance with the semi- persistent CSI report configuration. The network entity 104 transmits 324 the trigger command to the UE 102 for triggering the semi-persistent ML-based CSI report, after transmitting 322 the ML-based CSI report configuration to the UE 102. In response to receiving 324 the trigger command 320 from the network entity 104, the UE 102 performs channel estimation and/or measurements on the CSI-RS, generates the semi-persistent ML-based CSI report, and transmits 328 the semi-persistent ML-based CSI report to the network entity 104.

[0069] The UE 102 may (periodically) transmit 328 the semi-persistent ML-based CSI report on PUCCH resources configured via the ML-based CSI report configuration. In other implementations, the UE 102 may (periodically) transmit 328 the semi-persistent ML-based CSI report on PUSCH resources configured via the ML-based CSI report configuration and/or the trigger command. The trigger command may be a MAC-CE or a DCI. For semi-persistent CSI- RS, the network entity 104 can transmit an activation command to the UE 102 to indicate that the semi -persistent CSI-RS is activated. After receiving the activation command, the UE 102 determines that transmission of the semi -persistent CSI-RS is activated. The network entity 104 may transmit the activation command before or after transmitting 324 the trigger for the ML-based CSI report. Alternatively, the network entity 104 may transmit, to the UE 102. a MAC PDU including the activation command and the trigger command. The activation command may be a MAC-CE. The UE 102 performs the channel estimation and/or measurements based on the CSI- RSs, or a portion of the CSI-RS, in response to receiving 324 the trigger command. In other implementations, the UE 102 performs the channel estimation and/or measurements based on the CSI-RS, or a portion of the CSI-RS, in response to the semi-persistent ML-based CSI report configuration and before receiving 324 the trigger command.

[0070] The ML-based CSI report configuration and report may be for periodic ML-based CSI reporting, such that the UE 102 may perform the channel estimation and/or measurements based on the CSI-RS, generates the ML-based CSI report based on the channel estimation and/or measurements, and transmits 328 the periodic ML-based CSI report to the network entity 104 based on the periodic ML-based CSI report configuration. The UE 102 may perform the channel estimation and/or measurements based on the CSI-RS, or a portion of the CSI-RS, generates the periodic ML-based CSI report based on the channel estimation and/or measurements, and transmits 328 the periodic ML-based CSI report to the network entity 104 after receiving 322 the periodic ML-based CSI report configuration. Thus, the network entity 104 does not transmit 324 a trigger command to the UE 102 to trigger transmission of the periodic ML-based CSI report. The UE 102 may transmit 328 the periodic ML-based CSI report on PUCCH resources configured via the ML-based CSI report configuration. In other implementations, the UE 102 may transmit the periodic ML-based CSI report on PUSCH resources configured via the ML-based CSI report configuration and/or DCI that the UE 102 receives from the network entity 104. The DCI may include an uplink grant for the UE 102 to transmit user data, such that the DCI does not serve as a triggering command.

[0071] The ML-based CSI report configuration and report may be for aperiodic ML-based CSI reporting. For each aperiodic ML-based CSI report configuration, the UE 102 refrains from transmitting 328 an aperiodic ML-based CSI report until after the UE 102 receives 324 the trigger command from the network entity 104 triggering the UE 102 to transmit 328 the aperiodic ML- based CSI report in accordance with the aperiodic ML-based CSI report configuration. The network entity ⁷ 104 may transmit 324 the trigger command to the UE 102 to trigger the aperiodic ML-based CSI report in accordance with the aperiodic ML-based CSI report configuration. In response to the trigger command, the UE 102 performs channel estimation and/or measurements on the CSI-RS, generates a single aperiodic ML-based CSI report, and transmits 328 the aperiodic ML-based CSI report in accordance with the aperiodic ML-based CSI report configuration. The trigger command may be a MAC-CE or DCI.

[0072] The events 322, 323, 324, 316. and 328 are collectively referred to in FIG. 3 as an ML-based CSI reporting procedure 320.

[0073] The non-ML-based CSI reporting procedure 310 may completely or partially overlap with the ML-based CSI reporting procedure 320. In other implementations, the non-ML-based CSI reporting procedure 310 does not overlap with the ML-based CSI reporting procedure 320. The non-ML-based CSI report configuration and the ML-based CSI report configuration may include at least one identical configuration/parameter. For example, the CSI-RS(s) may be identical/same CSI-RS(s) or different CSI-RS(s). To configure the UE 102 to generate the ML- based CSI report and the non-ML-based CSI report based on the same CSI-RS(s). the network entity 104 may transmit a CSI resource configuration (e.g., in one or more single instances) that includes a CSI resource configuration (ID for configuring the CSI-RS(s). The CSI resource configuration ID may be included in the non-ML-based CSI report configuration and the ML- based CSI report configuration. The UE 102 may determine the CSI resource configuration based on the (same) CSI resource configuration ID. Thus, the UE 102 receives 316 the CSI-RS(s) configured in the CSI resource configurations, performs the channel estimation and/or measurements on the CSI-RS(s), and transmits 318, 328 the non-ML-based CSI report and the ML-based CSI report based on the channel estimation and/or measurements. The network entity- 104 may obtain ML-based CSI (e.g., compressed CSI) from each ML-based CSI report and reconstruct the CSI (e.g., decompressed CSI) based on an ML model. For each non-ML-based CSI report, the network entity 104 may obtain non-ML-based CSI.

[0074] If the network entity 104 determines to configure the UE 102 to transmit 328 ML- based CSI reports, the network entity 104 may transmit 323 an RRC message (e.g., RRCReconflguration message) to the UE 102 to release a configuration for the non-ML-based CSI report. In examples, the network entity 104 may transmit 323 the RRC message to the UE 102, if the ML-based CSI report configuration or report and the non-ML-based CSI report configuration or report exceed the CSI reporting capabilities of the UE 102. If the ML-based CSI report configuration or report and non-ML-based CSI report configuration or report do not exceed the CSI reporting capabilities of the UE 102, the network entity 104 may not transmit the RRC message to the UE 102. However, the network entity 104 may still transmit 323 the release indication because ML-based CSI reports configured in the ML-based CSI report configuration can replace non-ML-based CSI reports configured in the non-ML-based CSI report configuration. [0075] If the network entity 104 determines to configure the UE 102 to transmit 328 ML- based CSI reports, the network entity 104 may transmit 323 an RRC message (e.g., RRCReconflguration message) to reconfigure the non-ML-based CSI report configuration. The RRC message reconfigures the non-ML-based CSI report configuration to prevent the UE 102 from transmitting non-ML-based CSI reports configured for the ML-based CSI report configuration. The CSI report configuration(s) and report(s) may be configured for periodic CSI reporting, where the network entity ⁷ 104 may reconfigure the CSI report configuration(s) and report(s) for semi-persistent CSI reporting or aperiodic CSI reporting. If the ML-based CSI report configuration or report and the non-ML-based CSI report configuration or report exceed the CSI reporting capabilities of the UE 102, the network entity 104 may transmit 323 the RRC message to reconfigure the ML-based CSI report configuration and the non-ML-based CSI report configuration, so that the CSI reporting capabilities of the UE 102 are not exceeded. If the ML- based CSI report configuration or report and the non-ML-based CSI report configuration or report do not exceed the CSI report capabilities of the UE 102, the network entity 104 might not transmit the RRC message. However, the network entity 104 may transmit 323 the RRC message when the ML-based CSI report configured in the ML-based CSI report configuration can replace the non-ML-based CSI report configured in the non-ML-based CSI report configuration.

[0076] If the network entity 104 determines to configure the UE 102 to transmit 328 the ML- based CSI report, the network entity 104 may transmit 323 the RRC message to the UE 102 to modify the non-ML-based CSI report configuration. In some implementations, the RRC message modifies the non-ML-based CSI report configuration so that the UE 102 transmits 318 non-ML- based CSI reports less frequently. That is, the network entity 104 may determine to use ML-based CSI reports configured by the ML-based CSI report configuration in place of one or more non- ML-based CSI reports configured by the non-ML-based CSI report configuration. FIG. 3 illustrates ML-based and non-ML-based CSI reporting procedures 310, 320. FIGs. 4A-4C show implementations by the UE 102 of the one or more aspects of FIG. 3. FIGs. 5A-5E show implementations by the network entity 104 of the one or more aspects of FIG. 3.

[0077] FIGs. 4A-4C illustrate flowcharts 400, 420, 440 of a method of wireless communication at a UE. With reference to FIGs. 1-3 and 6, the method may be performed by the UE 102. the UE apparatus 602. etc., which may include the memory 626', 606', 616, and which may correspond to the entire UE 102 or the entire UE apparatus 602, or a component of the UE 102 or the UE apparatus 602, such as the wireless baseband processor 626 and/or the application processor 606.

[0078] Referring to FIG. 4A, elements 402a, 404, 406, and 408a may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0079] The UE 102 transmits 402a, to a network (e.g., RAN), a first UE capability indicating a first maximum number (e.g., M) of total ML-based and non-ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 transmits 306, to the network entity 104, UE capability information (e.g., CSI report capabilities) that may indicate a total maximum number of (e g., combined number of) ML-based CSI reports and non-ML-based CSI reports supported by the UE 102.

[0080] The UE 102 transmits 404, to the network, a second UE capability indicating a second maximum number (e.g., N) of ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 transmits 306, to the network entity 104, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of ML-based CSI reports supported by the UE 102.

[0081] The UE 102 receives 406, from the network, ML-based CSI report configuration(s), where a number (e.g.. K) of the ML-based CSI report (s) does not exceed the second maximum number (e.g., K < N), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 receives 322, from the network entity' 104, ML-based CSI report configuration(s), where a number of the ML-based CSI report(s) does not exceed the maximum number of ML-based CSI reports supported by the UE 102.

[0082] The UE 102 receives 408a, from the network, non-ML-based CSI report configuration(s), where a number (e.g., L) of the non-ML-based CSI report(s) does not exceed M - K (e.g., L < (M - K)), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 receives 312, from the network entity 104, non-ML- based CSI report configuration(s), where a number of the non-ML-based CSI report(s) does not exceed a number of non-ML-based CSI reports supported by the UE 102.

[0083] The UE 102 transmits 410, to the network, an ML-based CSI report in accordance with the ML-based CSI report configuration. For example, referring to FIG. 3, the UE 102 transmits 328. to the network entity 104. an ML-based CSI report based on the ML-based CSI report configuration that the UE 102 receives 322 from the network entity 104.

[0084] The UE 102 transmits 412, to the network, a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration. For example, referring to FIG. 3, the UE 102 transmits 318, to the network entity 104, a non-ML-based CSI report based on the non-ML-based CSI report configuration that the UE 102 receives 312 from the network entity 104.

[0085] FIG. 4B is similar to FIG. 4A, except that FIG. 4B includes elements 402b and 408b instead of elements 402a and 408a. Elements 404, 406, 410, and 412 have already been described with respect to FIG. 4A. Elements 402b, 404. 406, and 408b may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0086] The UE 102 transmits 402b, to a network (e.g., RAN), a first UE capability indicating a first maximum number (e.g., M) of non-ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 transmits 306, to the network entity 104, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102.

[0087] The UE 102 receives 408b, from the network, non-ML-based CSI report configuration(s). where a number (e.g., L) of the non-ML-based CSI report(s) does not exceed M (e.g.. L < M). such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 receives 312 non-ML-based CSI report configuration(s), which may not exceed a number of non-ML-based CSI repot configurations relative to a maximum number of non-ML-based CSI reports.

[0088] FIG. 4C is similar to FIG. 4A, except that FIG. 4C includes elements 402c, 405, and 408c instead of elements 402a and 408a. Elements 404, 406, 410, and 412 have already been described with respect to FIG. 4A. Elements 402c, 404, 405, 406, and 408c may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0089] The UE 102 transmits 402c, to a network (e.g., RAN), a first UE capability' indicating a first maximum number (e.g., M) of non-ML-based CSI reports supported by the UE when ML- based CSI reporting is not configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 transmits 306, to the network entity 104, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102 when the ML-based CSI reporting is not configured.

[0090] The UE 102 transmits 405, to the network, a third UE capability indicating a third maximum number (e.g., P) of non-ML-based CSI reports supported by the UE when ML-based CSI reporting is configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 transmits 306, to the network entity 104. UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102 when the ML-based CSI reporting is configured. [0091] The UE 102 receives 408c, from the network, non-ML-based CSI report configuration(s), where a number (e.g., L) of non-ML-based CSI reports does not exceed P (e.g., L < P), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the UE 102 receives 312 non-ML-based CSI report configuration(s), which may not exceed a number of non-ML-based CSI reports relative to a maximum number of non-ML-based CSI reports.

[0092] FIGs. 5 A-5E illustrates flowcharts 500, 520, 540, 560, and 580 of a method of wireless communication at a network entity. With reference to FIGs. 1-3 and 7, the method may be performed by one or more network entities 104, which may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, the CU 110, an RU processor 706, a DU processor 726, a CU processor 746, etc. The one or more network entities 104 may include memory 70677267746’, which may correspond to an entirety of the one or more network entities 104, or a component of the one or more network entities 104, such as the RU processor 706, the DU processor 726, or the CU processor 746.

[0093] Referring to FIG. 5A, elements 502a, 504, 506, and 508a may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0094] The network entity’ 104 receives 502a a first UE capability indicating a first maximum number (e.g., M) of total ML-based and non-ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, 308, from the UE 102 or another network node, such as a core network or a second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a total maximum number of (e.g., combined number of) ML-based CSI reports and non-ML-based CSI reports supported by the UE 102.

[0095] The network entity 104 receives 504 a second UE capability indicating a second maximum number (e.g., N) of ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity' 104 receives 306, 308 from the UE 102, or another network node, such as the core network or second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of ML-based CSI reports supported by the UE 102.

[0096] The network entity 104 transmits 506, to the UE, ML-based CSI report configuration(s), where a number (e.g., K) of the ML-based CSI report(s) does not exceed the second maximum number (e.g., K < N), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 322, to the UE 102, ML-based CSI report configuration(s), where a number of the ML-based CSI report(s) does not exceed the maximum number of ML-based CSI reports supported by the UE 102.

[0097] The network entity 104 transmits 508a, to the UE, non-ML-based CSI report configuration(s), where a number (e.g., L) of the non-ML-based CSI report(s) does not exceed M - K (e.g., L < (M - K)), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 312, to the UE 102, non-ML-based CSI report configuration(s), where a number of the non-ML-based CSI report(s) does not exceed a number of non-ML-based CSI reports supported by the UE 102.

[0098] The network entity 104 receives 510, from the UE, an ML-based CSI report in accordance with the ML-based CSI report configuration. For example, referring to FIG. 3, the network entity 104 receives 328, from the UE 102, an ML-based CSI report based on the ML- based CSI report configuration that the network entity 104 transmits 322 to the UE 102.

[0099] The network entity 104 receives 512, from the UE, a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration. For example, referring to FIG. 3, the network entity 104 receives 318, from the UE 102, a non-ML-based CSI report based on the non-ML-based CSI report configuration that the network entity 104 transmits 312 to the UE 102. [0100] FIG. 5B is similar to FIG. 5A, except that FIG. 5B includes elements 502b and 508b instead of elements 502a and 508a. Elements 504, 506, 510, and 512 have already been described with respect to FIG. 5A. Elements 502b, 504, 506, and 508b may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact anumber of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0101] The netw ork entity 104 receives 502b a first UE capability indicating a first maximum number (e.g., M) of non-ML-based CSI report configurations supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, 308, from the UE 102 or another network node, such as a core netw ork or a second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI report configurations supported by the UE 102.

[0102] The network entity' 104 transmits 508b, to the UE, non-ML-based CSI report configuration(s), where a number (e.g., L) of the non-ML-based CSI report configuration(s) does not exceed M (e.g., L < M). such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 312 non-ML-based CSI report configuration(s), which may not exceed a number of non-ML-based CSI report configurations relative to a maximum number of non-ML-based CSI report configurations.

[0103] FIG. 5C is similar to FIG. 5A, except that FIG. 5C includes elements 502c. 505 and 508c instead of elements 502a and 508a. Elements 504, 506, 510, and 512 have already been described with respect to FIG. 5A. Elements 502c, 504, 505, 506, and 508c may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML -based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0104] The network entity 104 receives 502c a first UE capability indicating a first maximum number (e g., M) of non-ML-based CSI report configurations supported by the UE when ML- based CSI reporting is not configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, 308, from the UE 102 or another network node, such as a core network or a second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI report configurations supported by the UE 102 when the ML-based CSI report configuration is not configured.

[0105] The network entity 104 receives 505 a third UE capability indicating a third maximum number (e.g., P) of non-ML-based CSI report configurations supported by the UE when ML-based CSI report is configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3. the network entity 104 receives 306. 308, from the UE 102 or another network node, such as a core network or a second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI report configurations supported by the UE 102 when the ML-based CSI report configuration is configured.

[0106] The network entity 104 transmits 508c, to the UE, non-ML-based CSI report configuration(s), where a number (e.g., L) of non-ML-based CSI report configuration(s) does not exceed P (e.g., L < P), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3. the network entity 104 transmits 312 non-ML-based CSI report configuration(s), where a number of the non-ML-based CSI report configuration(s) does not exceed a number of non-ML-based CSI report configurations relative to a maximum number of non-ML-based CSI report configurations. [0107] Referring to FIG. 5D, elements 502c. 504d, 506. 508b, and 508d may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML-based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0108] The network entity 104 receives 502c a first UE capability indicating a first maximum number (e.g., M) of non-ML-based CSI reports supported by the UE when ML-based CSI reporting is not configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3. the network entity 104 receives 306, 308, from the UE 102 or another network node, such as a core network or a second network entity. UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102 when ML-based CSI reporting is not configured.

[0109] The network entity' 104 receives 504d a second UE capability of the UE indicating a second maximum number (e.g.. N) of total ML-based and non-ML-based CSI reports supported by the UE when ML-based CSI reporting is configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, 308, from the UE 102 or another network node, such as the core network or second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a total maximum number of (e.g., combined number of) ML-based CSI reports and non-ML-based CSI reports supported by the UE 102 when ML-based CSI reporting is configured.

[0110] The network entity 104 determines 507 whether to configure the UE with an ML- based CSI report configuration. For example, referring to FIG. 3, the network entity 104 may determine whether to transmit 322 the ML-based CSI report configuration to the UE 102 based on the UE capability information (e g., CSI report capabilities) that the network entity 104 receives 306, 308, from the UE 102 or another network node, such as the core network or second network entity.

[OHl] If the network entity 104 determines not to configure 507 the UE 102 with an ML- based CSI report configuration (e.g., the network entity 104 determines to configure 507 the UE 102 with anon-ML-based CSI report configuration), the network entity transmits 508b, to the UE, a non-ML-based CSI report configuration, where a number (e.g., L) of non-ML-based CSI report does not exceed M (e.g., L < M), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 312 to the UE 102 a non-ML- based CSI report configuration, which may not cause a total number of non-ML-based CSI reports to exceed a maximum number of non-ML-based CSI reports supported by the UE 102. [0112] The network entity 104 receives 512, from the UE. a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration. For example, referring to FIG. 3, the network entity 104 receives 318, from the UE 102, a non-ML-based CSI report based on the non-ML-based CSI report configuration that the network entity 104 transmits 312 to the UE 102. [0113] If the network entity 104 determines to configure 507 the UE 102 with an ML-based CSI report configuration, the network entity 104 transmits 506, to the UE, an ML-based CSI report configuration, where a total number (e.g., K) of ML-based CSI reports does not exceed the second maximum number (e.g., K < N), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 322, to the UE 102, an ML- based CSI report configuration, which may not cause a total number of ML-based CSI reports to exceeds the maximum number of ML-based CSI reports supported by the UE 102.

[0114] The network entity 104 transmits 508d, to the UE, non-ML-based CSI report configuration(s), where a number (e.g., L) of the non-ML-based CSI reports does not exceed N - K (e.g., L < (N - K)). such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity' 104 transmits 312 non-ML-based CSI report configuration(s), where a number of the non-ML-based CSI report(s) does not exceed a number of non-ML-based CSI reports relative to a number of ML-based CSI reports.

[0115] The network entity 104 receives 510. from the UE. an ML-based CSI report in accordance with the ML-based CSI report configuration. For example, refernng to FIG. 3, the network entity' 104 receives 328, from the UE 102, an ML-based CSI report based on the ML- based CSI report configuration that the network entity' 104 transmits 322 to the UE 102. The network entity 104 may also receive 512, from the UE, a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration, as described above.

[0116] Referring to FIG. 5E, elements 502c, 504, 505, 506, 508b, and 508c may or may not be implemented based on simultaneous CSI-RS measurement and processing. That is, the ML- based CSI reporting procedure 320 and the non-ML-based CSI reporting procedure 310 in FIG. 3 may or may not be performed simultaneously, which may impact a number of ML-based report configurations and/or non-ML-based report configurations that the UE supports.

[0117] The network entity’ 104 receives 502c a first UE capability indicating a first maximum number (e.g., M) of non-ML-based CSI reports supported by the UE when ML-based CSI reporting is not configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, thenetwork entity 104 receives 306, 308, from the UE 102 or another network node, such as a core network or a second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102 when the ML-based CSI reporting configuration is not configured.

[0118] The network entity 104 receives 504 a second UE capability indicating a second maximum number (e.g., N) of ML-based CSI reports supported by the UE, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, from the UE 102 or another network node, such as the core network or second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of ML-based CSI reports supported by the UE 102.

[0119] The network entity 104 receives 505 a third UE capability indicating a third maximum number (e.g., P) of non-ML-based CSI reports supported by the UE when ML-based CSI report is configured, such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 receives 306, 308, from the UE 102 or another network node, such as the core network or second network entity, UE capability information (e.g., CSI report capabilities) that may indicate a maximum number of non-ML-based CSI reports supported by the UE 102 when the ML-based CSI reporting configuration is configured.

[0120] The network entity 104 determines 507 whether to configure the UE with an ML- based CSI report configuration. For example, referring to FIG. 3, the network entity ⁷ 104 may determine whether to transmit 322 the ML-based CSI report configuration to the UE 102 based on the UE capability information (e.g., CSI report capabilities) that the network entity 104 receives 306, 308, from the UE 102 or another network node, such as a core network or a second network entity.

[0121] If the network entity 104 determines not to configure 507 the UE 102 with an ML- based CSI report configuration (e.g., the network entity 104 determines to configure 507 the UE 102 with anon-ML-based CSI report configuration), the network entity transmits 508b, to the UE, a non-ML-based CSI report configuration, where a number (e.g., L) of non-ML-based CSI reports does not exceed M (e.g., L < M), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 312 to the UE 102 a non-ML- based CSI report configuration, which may not cause a total number of non-ML-based CSI reports to exceed a maximum number of non-ML-based CSI reports supported by the UE 102.

[0122] The network entity 104 receives 512, from the UE, a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration. For example, referring to FIG. 3, the network entity 104 receives 318, from the UE 102, a non-ML-based CSI report based on the non-ML-based CSI report configuration that the network entity ⁷ 104 transmits 312 to the UE 102. [0123] If the network entity 104 determines to configure 507 the UE 102 with an ML-based CSI report configuration, the network entity 104 transmits 506, to the UE, an ML-based CSI report configuration, where a total number (e.g., K) of ML-based CSI reports does not exceed the second maximum number (e.g., K < N), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 322. to the UE 102, an ML- based CSI report configuration, which may not cause a total number of ML-based CSI reports exceeds the maximum number of ML-based CSI reports supported by the UE 102.

[0124] The network entity 104 transmits 508c, to the UE, non-ML-based CSI report configuration(s). where a number (e.g., L) of the non-ML-based CSI report(s) does not exceed P (e.g.. L < P), such as for simultaneous CSI-RS measurement and processing. For example, referring to FIG. 3, the network entity 104 transmits 312 non-ML-based CSI report configuration(s), where a number of the non-ML-based CSI report(s) does not exceed a number of non-ML-based CSI reports relative to a maximum number of non-ML-based CSI reports.

[0125] The network entity 104 receives 510. from the UE. an ML-based CSI report in accordance with the ML-based CSI report configuration. For example, referring to FIG. 3, the network entity 104 receives 328, from the UE 102, an ML-based CSI report based on the ML- based CSI report configuration that the network entity 104 transmits 322 to the UE 102. The network entity 104 may also receive 512, from the UE, a non-ML-based CSI report in accordance with the non-ML-based CSI report configuration, as described above. A UE apparatus 602, as described in FIG. 6, may perform the methods of flowcharts 400, 420, and 440. The one or more network entities 104, as described in FIG. 7, may perform the methods of flowcharts 500, 520, 540, 560, and 580.

[0126] FIG. 6 is a diagram 600 illustrating an example of a hardware implementation for a UE apparatus 602. The UE apparatus 602 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 602 may include an application processor 606, which may have on-chip memory 606'. In examples, the application processor 606 may be coupled to a secure digital (SD) card 608 and/or a display 610. The application processor 606 may also be coupled to a sensor(s) module 612, a power supply 614, an additional module of memory 616, a camera 618, and/or other related components. For example, the sensor(s) module 612 may control a barometric pressure sensor/altimeter, a motion sensor such as an inertial management unit (IMU), a gyroscope, accelerometer(s), a light detection and ranging (LIDAR) device, a radio-assisted detection and ranging (RADAR) device, a sound navigation and ranging (SONAR) device, a magnetometer, an audio device, and/or other technologies used for positioning. [0127] The UE apparatus 602 may further include a wireless baseband processor 626. which may be referred to as a modem. The wireless baseband processor 626 may have on-chip memory 626'. Along with, and similar to, the application processor 606, the wireless baseband processor 626 may also be coupled to the sensor(s) module 612, the power supply 614, the additional module of memory 616, the camera 618, and/or other related components. The wireless baseband processor 626 may be additionally coupled to one or more subscriber identity module (SIM) card(s) 620 and/or one or more transceivers 630 (e.g., wireless RF transceivers).

[0128] Within the one or more transceivers 630, the UE apparatus 602 may include a Bluetooth module 632, a WLAN module 634, an SPS module 636 (e g., GNSS module), and/or a cellular module 638. The Bluetooth module 632, the WLAN module 634, the SPS module 636, and the cellular module 638 may each include an on-chip transceiver (TRX), or in some cases, just a transmitter (TX) or just a receiver (RX). The Bluetooth module 632, the WLAN module 634, the SPS module 636, and the cellular module 638 may each include dedicated antennas and/or utilize antennas 640 for communication with one or more other nodes. For example, the UE apparatus 602 can communicate through the trans ceiver(s) 630 via the antennas 640 with another UE 102 (e.g., sidelink communication) and/or with a network entity 104 (e.g., uplink/downlink communication), where the network entity 104 may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, or the CU 110.

[0129] The wireless baseband processor 626 and the application processor 606 may each include a computer-readable medium / memory 626', 606', respectively. The additional module of memory 616 may also be considered a computer-readable medium / memory ⁷ . Each computer- readable medium / memory 626', 606', 616 may be non-transitory. The wireless baseband processor 626 and the application processor 606 may each be responsible for general processing, including execution of software stored on the computer-readable medium / memory 626', 606', 616. The software, when executed by the wireless baseband processor 626 / application processor 606, causes the wireless baseband processor 626 / application processor 606 to perform the various functions described herein. The computer-readable medium / memory may also be used for storing data that is manipulated by the wireless baseband processor 626 / application processor 606 when executing the software. The wireless baseband processor 626 / application processor 606 may be a component of the UE 102. The UE apparatus 602 may be a processor chip (e.g., modem and/or application) and include just the wireless baseband processor 626 and/or the application processor 606. In other examples, the UE apparatus 602 may be the entire UE 102 and include the additional modules of the apparatus 602. [0130] As discussed, the CSI reporting component 140 is configured to receive, from a network entity based on a capability of the UE, at least one of a first configuration for an ML- based CSI report or a second configuration for a non-ML-based CSI report; measure one or more CSI-RSs received from the network entity on dedicated CSI resources; input, for the ML -based CSI report, a result of the measuring to an ML model for CSI compression; and transmit, to the network entity, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration, the ML-based CSI report associated with an output of the ML model. The CSI reporting component 140 may be within the wireless baseband processor 626, the application processor 606, or both the wireless baseband processor 626 and the application processor 606. The CSI reporting component 140 may be one or more hardware components specifically configured to carry out the stated processes/algorithm, implemented by one or more processors configured to perform the stated processes/algorithm, stored within a computer-readable medium for implementation by the one or more processors, or a combination thereof.

[0131] The UE apparatus 602 may include a variety ⁷ of components configured for various functions. In examples, the UE apparatus 602, and in particular the wireless baseband processor 626 and/or the application processor 606, includes means for receiving, from a network entity ⁷ based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report; means for measuring one or more CSI- RSs received from the network entity on dedicated CSI resources; means for inputting, for the ML-based CSI report, a result of the measuring to an ML model for CSI compression; and means for transmitting, to the network entity, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration, the ML-based CSI report associated w ith an output of the ML model. The UE apparatus 602 further includes means for transmitting, to the network entity ⁷ , UE capability ⁷ information indicating the capability ⁷ of the UE for the ML-based CSI report, the first configuration for the ML-based CSI report being based on the UE capability ⁷ information. The UE apparatus 602 further includes means for transmitting, to the network entity ⁷ , the non-ML-based CSI report, the non-ML-based CSI report being based on a concurrent measurement of the one or more CSI-RSs with a measurement of the one or more CSI-RSs for the ML-based CSI report. The means may be the CSI reporting component 140 of the UE apparatus 602 configured to perform the functions recited by the means. [0132] FIG. 7 is a diagram 700 illustrating an example of a hardware implementation for one or more network entities 104. The one or more network entities 104 may be a base station, a component of a base station, or may implement base station functionality ⁷ . The one or more network entities 104 may include, or may correspond to, at least one of the RU 106, the DU. 108, or the CU 110. The CU 1 10 may include a CU processor 746, which may have on-chip memory 746'. In some aspects, the CU 110 may further include an additional module of memory 756 and/or a communications interface 748, both of which may be coupled to the CU processor 746. The CU 110 can communicate with the DU 108 through a midhaul link 162, such as an Fl interface between the communications interface 748 of the CU 110 and a communications interface 728 of the DU 108.

[0133] The DU 108 may include a DU processor 726, which may have on-chip memory 726'. In some aspects, the DU 108 may further include an additional module of memory 736 and/or the communications interface 728, both of which may be coupled to the DU processor 726. The DU 108 can communicate with the RU 106 through a fronthaul link 160 between the communications interface 728 of the DU 108 and a communications interface 708 of the RU 106.

[0134] The RU 106 may include an RU processor 706, which may have on-chip memory 706'. In some aspects, the RU 106 may further include an additional module of memory 716, the communications interface 708, and one or more transceivers 730, all of which may be coupled to the RU processor 706. The RU 106 may further include antennas 740, which may be coupled to the one or more transceivers 730, such that the RU 106 can communicate through the one or more transceivers 730 via the antennas 740 with the UE 102.

[0135] The on-chip memory 706', 726', 746' and the additional modules of memory 716, 736, 756 may each be considered a computer-readable medium / memory. Each computer-readable medium / memory' may be non-transitory. Each of the processors 706, 726, 746 is responsible for general processing, including execution of software stored on the computer-readable medium / memory. The software, when executed by the corresponding processor(s) 706. 726, 746 causes the processor(s) 706, 726, 746 to perform the various functions described herein. The computer- readable medium / memory may also be used for storing data that is manipulated by the processor(s) 706, 726, 746 when executing the software. In examples, the CSI report configuration component 150 may sit at the one or more network entities 104. such as at the CU 110; both the CU 110 and the DU 108; each of the CU 110, the DU 108, and the RU 106; the DU 108; both the DU 108 and the RU 106; or the RU 106.

[0136] As discussed, the CSI report configuration component 150 is configured to transmit, to a UE based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report; transmit, to the UE. one or more CSI-RSs on dedicated CSI resources; receive, from the UE, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration, the ML-based CSI report associated with a compressed output of an ML model; and decompress the ML-based CSI report associated with the compressed output of the ML model. The CSI report configuration component 150 may be within one or more processors of the one or more network entities 104, such as the RU processor 706, the DU processor 726, and/or the CU processor 746. The CSI report configuration component 150 may be one or more hardware components specifically configured to carry out the stated processes/algorithm, implemented by one or more processors 706, 726, 746 configured to perform the stated processes/algorithm, stored within a computer-readable medium for implementation by the one or more processors 706, 726, 746, or a combination thereof.

[0137] The one or more network entities 104 may include a variety of components configured for various functions. In examples, the one or more network entities 104 include means for transmitting, to a UE based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report; means for transmitting, to the UE, one or more CSI-RSs on dedicated CSI resources; means for receiving, from the UE, at least one of the ML-based CSI report based on the first configuration or the non- ML-based CSI report based on the second configuration, the ML-based CSI report associated with a compressed output of an ML model; and means for decompressing the ML-based CSI report associated with the compressed output of the ML model. The one or more network entities 104 further include means for receiving, from a network node, UE capability information indicating the capability of the UE for the ML-based CSI report, the first configuration for the ML-based CSI report being based on the UE capability information. The one or more network entities 104 further include means for receiving, from the UE. the non-ML-based CSI report based on the transmitting the one or more CSI-RSs on the dedicated resources, the one or more CSI-RSs being same CSI-RSs for the ML-based CSI report. The means may be the CSI report configuration component 150 of the one or more network entities 104 configured to perform the functions recited by the means.

[0138] The specific order or hierarchy of blocks in the processes and flowcharts disclosed herein is an illustration of example approaches. Hence, the specific order or hierarchy of blocks in the processes and flowcharts may be rearranged. Some blocks may also be combined or deleted. Dashed lines may indicate optional elements of the diagrams. The accompany ing method claims present elements of the various blocks in an example order, and are not limited to the specific order or hierarchy presented in the claims, processes, and flowcharts.

[0139] The detailed description set forth herein describes various configurations in connection w ith the drawings and does not represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough explanation of various concepts. However, these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.

[0140] Aspects of wireless communication systems, such as telecommunication systems, are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and are illustrated in the accompanying drawings by various blocks, components, circuits, processes, call flows, systems, algorithms, etc. (collectively referred to as “‘elements”). These elements may be implemented using electronic hardware, computer software, or combinations thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.

[0141] An element, or any portion of an element, or any combination of elements may be implemented as a “processing system” that includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems-on-chip (SoC), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs). state machines, gated logic, discrete hardware circuits, and other similar hardware configured to perform the various functionality ⁷ described throughout this disclosure. One or more processors in the processing system may execute software, which may be referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof

[0142] If the functionality described herein is implemented in software, the functions may be stored on, or encoded as, one or more instructions or code on a computer-readable medium, such as a non-transitoiy computer-readable storage medium. Computer-readable media includes computer storage media and can include a random-access memory (RAM), a read-only memory ⁷ (ROM), an electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer. Storage media may be any available media that can be accessed by a computer.

[0143] Aspects, implementations, and/or use cases described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, the aspects, implementations, and/or use cases may come about via integrated chip implementations and other non-module-component based devices, such as enduser devices, vehicles, communication devices, computing devices, industrial equipment, retail/purchasing devices, medical devices, artificial intelligence (Al)-enabled devices, machine learning (ML)-enabled devices, etc. The aspects, implementations, and/or use cases may range from chip-level or modular components to non-modular or non-chip-level implementations, and further to aggregate, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more techniques described herein.

[0144] Devices incorporating the aspects and features described herein may also include additional components and features for the implementation and practice of the claimed and described aspects and features. For example, transmission and reception of wireless signals necessarily includes a number of components for analog and digital purposes, such as hardware components, antennas, RF-chains, power amplifiers, modulators, buffers, processor(s), interleavers, adders/summers, etc. Techniques described herein may be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of var ing configurations.

[0145] The description herein is provided to enable a person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not limited to the aspects described herein, but are to be interpreted in view of the full scope of the present disclosure consistent with the language of the claims.

[0146] Reference to an element in the singular does not mean “one and only one’' unless specifically stated, but rather “one or more.” Terms such as “if,” “when,” and “while” do not imply an immediate temporal relationship or reaction. That is, these phrases, e.g., “when,” do not imply an immediate action in response to or during the occurrence of an action, but simply imply that if a condition is met then an action will occur, but without requiring a specific or immediate time constraint for the action to occur. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C” or “one or more of A, B. or C” include any combination of A, B, and/or C, such as A and B, A and C, B and C, or A and B and C, and may include multiples of A, multiples of B, and/or multiples of C, or may include A only. B only, or C only. Sets should be interpreted as a set of elements where the elements number one or more.

[0147] Unless otherwise specifically indicated, ordinal terms such as “first” and “second” do not necessarily imply an order in time, sequence, numerical value, etc., but are used to distinguish between different instances of a term or phrase that follows each ordinal term.

[0148] Structural and functional equivalents to elements of the various aspects descnbed throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are encompassed by the claims. The words “module,” “mechanism,” “element,” “device," and the like may not be a substitute for the word “means.” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for.” As used herein, the phrase “based on” shall not be construed as a reference to a closed set of information, one or more conditions, one or more factors, or the like. In other words, the phrase “based on A”, where “A” may be information, a condition, a factor, or the like, shall be construed as “based at least on A” unless specifically recited differently.

[0149] The following examples are illustrative only and may be combined with other examples or teachings described herein, without limitation.

[0150] Example 1 is a method of wireless communication at a UE, including: receiving, from a network entity based on a capability of the UE, at least one of a first configuration for an ML- based CSI report or a second configuration for a non-ML-based CSI report; measuring one or more CSI-RSs received from the network entity on dedicated CSI resources; generating, based on an ML model for CSI compression, the ML-based CSI report using a result of the measuring; and transmitting, to the network entity, at least one of the ML-based CSI report based on the first configuration or the non-ML-based CSI report based on the second configuration, the ML-based CSI report being associated with an output of the ML model.

[0151] Example 2 may be combined with example 1 and further includes transmitting, to the network entity, UE capability infomiation indicating the capability of the UE for the ML-based CSI report, the first configuration for the ML-based CSI report being based on the UE capability information.

[0152] Example 3 may be combined with any of examples 1 -2 and includes that a first number of non-ML-based reports is less than or equal to a difference between a maximum total number of reports and a second number of ML-based reports, the maximum total number of reports corresponding to both the ML-based reports and the non-ML-based reports. [0153] Example 4 may be combined with any of examples 1 -2 and includes that a first number of non-ML-based reports is less than or equal to a first maximum number of non-ML-based reports, and wherein a second number of ML-based reports is less than or equal to a second maximum number of ML-based reports.

[0154] Example 5 may be combined with any of examples 1-2 and includes that a third maximum number of non-ML-based reports depends on a second number of ML-based reports, a first number of non-ML-based reports being less than or equal to the third maximum number of non-ML-based reports.

[0155] Example 6 may be combined with any of examples 1-5 and further includes transmitting, to the network entity, the non-ML-based CSI report, the non-ML-based CSI report being based on a concurrent measurement of the one or more CSI-RSs with a measurement of the one or more CSI-RSs for the ML-based CSI report.

[0156] Example 7 may be combined with example 6 and includes that the first configuration for the ML-based CSI report is based on a maximum total number of reports associated with the concurrent measurement of the one or more CSI-RSs, the maximum total number of reports corresponding to non-ML-based reports and ML-based reports.

[0157] Example 8 may be combined with example 7 and includes that the maximum total number of reports associated with the concurrent measurement of the one or more CSI-RSs depends on a second number of ML-based reports.

[0158] Example 9 may be combined with any of examples 6-8 and includes that the first configuration for the ML-based CSI report is based on a first concurrent maximum number of ML-based reports.

[0159] Example 10 may be combined with any of examples 6-9 and includes that the first configuration for the ML-based CSI report is based on a second concurrent maximum number of non-ML-based reports.

[0160] Example 11 may be combined with example 10 and includes that the second concurrent maximum number of non-ML-based reports depends on the second number of ML- based reports.

[0161] Example 12 is a method of wireless communication at a network entity, including: transmitting, to a UE based on a capability of the UE, at least one of a first configuration for an ML-based CSI report or a second configuration for a non-ML-based CSI report; transmitting, to the UE, one or more CSI-RSs on dedicated CSI resources; receiving, from the UE, at least one of the ML-based CSI report based on the first configuration and the one or more CSI-RSs or the non- ML-based CSI report based on the second configuration and the one or more CSI-RSs. the ML- based CSI report being associated with a compressed output of an ML model.

[0162] Example 13 may be combined with example 12 and further includes receiving, from a network node, UE capability information indicating the capability of the UE for the ML-based CSI report, the first configuration for the ML-based CSI report being based on the UE capability information; and decompressing the ML-based CSI report associated with the compressed output of the ML model.

[0163] Example 14 may be combined with any of examples 12-13 and further includes receiving, from the UE, the non-ML-based CSI report based on the transmitting the one or more CSI-RSs on the dedicated resources, the one or more CSI-RSs being same CSI-RSs for the ML- based CSI report.

[0164] Example 15 is a method of wireless communication at a user equipment (UE), including: (1) receiving, from a network entity, a configuration for a machine learning (ML)-based channel state information (CSI) report, the configuration indicating CSI resources for a measurement of one or more CSI-reference signals (CSI-RSs) based on one or more ML capabilities of the UE, the measurement of the one or more CSI-RSs associated with an input to an ML model that generates the ML-based CSI report; (2) receiving, from the network entity', the one or more CSI-RSs on the CSI resources for the measurement associated with the input to the ML model; and (3) transmitting, to the network entity, the ML-based CSI report, the ML-based CSI report based on the measurement of the one or more CSI-RSs associated with the input to the ML model. This method in example 15 may be combined with compatible features in examples 1-11.

[0165] Example 16 is a method of wireless communication at a network entity, the method including: (1) transmitting, to a user equipment (UE), a configuration for a machine learning (ML)-based channel state information (CSI) report, the configuration corresponding to one or more ML capabilities and indicating CSI resources for one or more CSI-reference signals (CSI- RSs) associated with the ML-based CSI report; (2) transmitting, to the UE, the one or more CSI- RSs on the CSI resources associated with the ML-based CSI report; and (3) receiving, from the UE, the ML-based CSI report, the ML-based CSI report based on the configuration corresponding to the one or more ML capabilities. The method in example 16 can be combined with compatible features specified in examples 12-14.

[0166] Example 17 is a method of wireless communication at a UE, including: receiving, from a network entity, a first configuration for an ML-based CSI report; measuring one or more CSI-RSs received from the network entity ⁷ ; inputting a result of the measuring to an ML model for CSI compression to obtain a CSI-related output; and transmitting, to the network entity, one or more ML-based CSI reports generated according to the first configuration based on the CSI- related output. This method in example 17 may be combined with compatible features in examples 1-11.

[0167] Example 18 is a method of wireless communication performed by a network entity, the method including: transmitting, to a UE a first configuration for an ML-based CSI report; transmitting, to the UE, one or more CSI-RSs; receiving, from the UE, an ML-based CSI report including a CSI-related output obtained by the UE using an ML model; and extracting the CSI- related output from the ML-based CSI report based on the first configuration. This method in example 18 may be combined with compatible features in examples 12-14.

[0168] Example 19 is an apparatus for wireless communication for implementing a method as in any of examples 1-18.

[0169] Example 20 is an apparatus for wireless communication including means for implementing a method as in any of examples 1-18.

[0170] Example 21 is a non-transitory computer-readable medium storing computer executable code, the code when executed by a processor causes the processor to implement a method as in any of examples 1-18.