BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:MediaTek: Towards Efficient Prediction of Communication Channels U
 sing AI - Sattar Vakili and Masoud Attarifar
DTSTART:20250310T130500Z
DTEND:20250310T135500Z
UID:TALK221086@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Abstract: AI has demonstrated unprecedented performance in var
 ious application domains\, including robotics\, image processing\, and lan
 guage processing. We aim to showcase its application to modern communicati
 on systems. Specifically\, we employ a transformer-based foundation model 
 and multimodal time series representing communication system data to solve
  various downstream tasks. We develop methodologies to address challenges 
 such as tokenization\, positional embedding\, multimodality\, features of 
 varying sizes\, and normalization. Our results show comparable performance
  with benchmarks on all tasks\, including CSI feedback\, Doppler spectrum\
 , and delay spread estimates.\n\nSpeakers:\n\nSpeaker 1:\n\nSattar Vakili 
 is a Principal AI Research manager at MediaTek Research\, the research arm
  of MediaTek — a globally renowned semiconductor company. He specializes
  in problems involving sequential decision-making in uncertain environment
 s\, with a focus on optimization\, reinforcement learning\, kernel-based m
 odeling\, and neural networks. Before joining MediaTek Research\, Sattar w
 orked at Second mind\, a research lab in Cambridge\, led by Professor Carl
  Rasmussen\, Cambridge University. There\, he gained expertise in kernel-b
 ased and Gaussian process models. Prior to that\, he was a postdoc at Prin
 ceton University. Sattar earned his PhD at Cornell University in 2017 with
  a dissertation on sequential methods for learning and optimization. \n\nS
 peaker 2:\n\nMasoud Attarifar is a senior wireless software engineer at Me
 diaTek. His expertise lies in wireless communication\, communication theor
 y\, and signal processing. \nPrior to joining MediaTek\, he was a postdoct
 oral researcher at UPF University under the supervision of Professor Angel
  Lozano. \nMasoud earned his PhD from Tehran University in 2019 with a dis
 sertation on cell-free massive MIMO networks.
LOCATION:FW26\, William Gates Building
END:VEVENT
END:VCALENDAR