R1-2410589 discussion

Discussion an AI/ML based CSI Compression

From IIT Kanpur
Status: not treated
WI: NR_AIML_air
Agenda: 9.1.4.1
Release: Rel-19
Source: 3gpp.org ↗

Summary

IIT Kanpur presents evaluation results for AI/ML-based CSI compression using temporal-spatial-frequency domain approaches, focusing on Case 2 (reconstruction with temporal correlation) and Case 3 (joint prediction). The document contains 2 key observations about the performance differences between reconstructive and predictive tasks under ideal and non-ideal UCI conditions.

Position

IIT Kanpur advocates for enhanced temporal correlation representation in AI/ML models for CSI compression, particularly emphasizing that joint prediction tasks (Case 3) require more sophisticated temporal modeling compared to reconstruction tasks (Case 2). They push for improvements in temporal diversity in datasets and better data pre-processing for training data to handle non-ideal UCI conditions effectively.

Key proposals

Your notes

Private to your account