Tu2G: AI-Enabled RF: Design and Linearization 

Back to IMS Schedule
Tue 9 Jun | 10:10 - 11:50
157AB
Chenhao Chu
ETH Zurich
Aditya Dave
Samsung Research America
This session explores the transformative integration of AI into the design and linearization of next-generation RF front-ends, addressing critical challenges for 6G and mmWave systems. The presentations highlight the shift from traditional analytical engineering to data-driven methodologies in developing high-efficiency, intelligent radio components.
10:10 - 10:30
Tu2G-1 KEYNOTE: AI/machine learning technologies for electromagnetic /multiphysics based modeling and optimization
Qi-Jun Zhang
Carleton Univ.
10:30 - 10:50
Tu2G-2 Residual Structure-Based Multi-Model Neural Network with Physical Inspired Core for Digital Predistortion in 6G Intelligent Radio
ABSTRACT
Xin Wei, Xin Liu, Huanhuan Jia, Tong Shen, Ting Feng, Yang Lu, Xiaohua Ma, Wenhua Chen
Xidian Univ., Xidian Univ., Xidian Univ., Xidian Univ., Xidian Univ., Xidian Univ., Xidian Univ., Tsinghua Univ.
10:50 - 11:10
Tu2G-3 Mamba Based Digital Predistortion for Wideband Doherty PowerAmplifiers
ABSTRACT
Shehroze Amir, Mohammad Hossein Khazani, Mohamed Helaoui, Fadhel Ghannouchi
Univ. of Calgary, Univ. of Calgary, Univ. of Calgary, Univ. of Calgary
11:10 - 11:30
Tu2G-4 AI-enabled Inverse Design of Planar RF Passives Under Arbitrary Footprint Constraints
ABSTRACT
Juho Park, Zijian Shao, Jonathan Zhou, Kaushik Sengupta
Princeton Univ., Princeton Univ., Princeton Univ., Princeton Univ.
11:30 - 11:50
Tu2G-5 AI-enabled Inverse Design of Harmonic Terminated mmWave PAs and Frequency Doublers
ABSTRACT
Emir Ali Karahan, Jonathan Zhou, Sherif Ghozzy, KAUSHIK Sengupta
Princeton Univ., Princeton Univ., Princeton Univ., Princeton Univ.