Kaushik Sengupta
10 posts

Kaushik Sengupta
@KSG_Princeton
Princeton ECE Prof, Codirects Princeton NextG. Research on semiconductor chips for computing, wireless and health. Involved in a start-up. Commentary views mine
Princeton, New Jersey Katılım Eylül 2024
23 Takip Edilen135 Takipçiler
Kaushik Sengupta retweetledi

This paper has garnered quite a bit of interest in the community. We call this Dall-EM: Diffusion model to synthesize RF with designer scattering parameters.
This picture should explain. We do controlled synthesis of RF design varying from classical to maze (weird looped t-lines) to completely arbitrary looking as desired.
Synthesis time ~ 1 minute.

outside five sigma@jwt0625
ok it actually works, uggghhh
English

@jwt0625 Thanks @jwt0625 for verifying this. I lead this research group (and just joined twitter). Not surprised that they work--they can be super robust. Here is a non-intuitive RFIC paper that may be of interest: nature.com/articles/s4146…
English

ok it actually works, uggghhh




Vikram Sekar@vikramskr
Generative AI meets RF circuit design = game changer • Passive networks tailored by diffusion models. • Specify stop-band/pass-band; AI does the rest. • Pixel patterns are not intuitive to electrical response. Designs getting more abstract. Prepare for a cognitive shift.
English

@vikramskr Thanks @vikramskr for sharing the paper. I just joined twitter--- it seems the paper is a rage here
English
Kaushik Sengupta retweetledi
Kaushik Sengupta retweetledi

As everyone knows, EM simulations, can either be achieved through heuristic algorithms such as genetic algorithms (GA), simulated annealing or generative AI tools such as auto-encoders or tandem neural networks.
nature.com/articles/s4146…
English



