From the 2 of 8 linked papers with an AI index.
8 papers
Spicing up Genetic Netlist Generation with LLMs
Stefan Uhlich, Yağız Gençer, Andrea Bonetti +4
Analog circuit topology synthesis remains challenging because useful designs occupy a tiny fraction of a combinatorial search space, and small structural changes can induce highly…
SPECS: Speciated Evolutionary Circuit Synthesis
YaÄız Gençer, Stefan Uhlich, Andrea Bonetti +3
The paper introduces SPECS, a genetic algorithm that automatically designs analog circuits by jointly optimizing their topology and component sizes, using ideas from neuroevolution…
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
Mustafa Emre Gürsoy, Stefan Uhlich, Ryoga Matsuo +6
The paper presents Lighthouse RL, a reinforcement‑learning method that improves sample efficiency for analog circuit sizing by periodically resetting episodes to high‑performing co…
SPICEMixer - Netlist-Level Circuit Evolution
Stefan Uhlich, Andrea Bonetti, Arun Venkitaraman +5
We present SPICEMixer, a genetic algorithm that synthesizes circuits by directly evolving SPICE netlists. SPICEMixer operates on individual netlist lines, making it compatible with…
GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identification
Phuoc Pham, Arun Venkitaraman, Chia-Yu Hsieh +8
Analog subcircuit identification is a core task in analog design, essential for simulation, sizing, and layout. Traditional methods often require extensive human expertise, rule-ba…
Schemato -- An LLM for Netlist-to-Schematic Conversion
Ryoga Matsuo, Stefan Uhlich, Arun Venkitaraman +7
Machine learning models are advancing circuit design, particularly in analog circuits. They typically generate netlists that lack human interpretability. This is a problem as human…