vivo · 5

vivo argues that it is not feasible for the UE to determine applicable functionalities without NW-side providing associated IDs first, emphasizing that ensuring consistency of NW-side additional conditions across training and inference is crucial to avoid unpredictable performance degradation. They require that associated IDs in Step 3 be separate from inference configuration, which is reserved for Step 5 within the CSI framework (including report configuration and Set A/Set B). vivo supports the position that inference configuration in Step 3 is unnecessary because it does not activate functionality immediately; instead, activation depends on the time-domain type of the beam report, utilizing existing MAC CE or DCI signaling for semi-persistent or aperiodic reports. They propose that Step 4 reporting should include associated IDs supported by the UE and potentially cell IDs to align understanding of training data sources. Finally, vivo presents a working assumption that associated IDs should be configurable within the CSI framework, while leaving the definition of similar properties for DL Tx beams and alternative signaling methods as FFS.

vivo presents a technical case against Option 1, arguing it leads to significant wastage of NW signaling, communication resources, and UE storage resources due to invalid inference configurations. They oppose Option 1 because it contradicts the existing CSI framework, where resource measurement cannot be executed immediately upon receiving configuration. vivo requires that Associated IDs be provided by the NW before the UE determines applicable functionalities, citing that consistency of NW-side additional conditions across training and inference is crucial to prevent performance degradation. They propose that Associated IDs in Step 3 are separate from inference configuration, and that information such as preferred Set B patterns can be included in Step 3 but does not constitute inference configuration. vivo prioritizes Option 2 and Option 3, which allow the NW to understand supported models before configuring CSI reports, thereby aligning with the current CSI framework and avoiding futile configurations.

Vivo advocates FOR mandatory associated IDs as essential for maintaining consistency between AI/ML training and inference phases, pushing for FG-specific granularity in functionality definition. They are advocating AGAINST providing inference configuration in early steps, preferring a separation of concerns where associated IDs and inference configurations are handled separately to avoid premature activation.