Asal Mehradfar

Asal Mehradfar

(she/her)

PhD Student

University of Southern California

About Me

Hi! I’m Asal Mehradfar, an engineer and researcher working at the intersection of Artificial Intelligence and Scientific Discovery. I recently earned my master’s in Electrical Engineering from USC, where I’m now continuing as a Ph.D. student in the research group of Professor Salman Avestimehr. My work focuses on applying machine learning to scientific problems in areas such as analog and RF circuit design and drug delivery systems. I’m especially passionate about building interdisciplinary methods that drive real-world impact. 🌱

Education

PhD Electrical Engineering (AI Focus)

University of Southern California

MSc Electrical Engineering

University of Southern California

BSc Computer Science

Sharif University of Technology

BSc Electrical Engineering

Sharif University of Technology

Interests

AI for Science Large Language Models Machine Learning
Featured Publications
🦅 FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design featured image

🦅 FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

We present FALCON, a fully automated machine learning framework for analog circuit design that selects topologies based on performance specifications and infers parameters to …

avatar
Asal Mehradfar
Read more
CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction featured image

CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction

CryptoMamba introduces a novel Mamba-based state space model architecture for Bitcoin price prediction, demonstrating superior forecasting accuracy and trading performance over …

Mohammad Shahab Sepehri
Read more
AICircuit: A Multi-Level Dataset and Benchmark for AI-Driven Analog Integrated Circuit Design featured image

AICircuit: A Multi-Level Dataset and Benchmark for AI-Driven Analog Integrated Circuit Design

We present a multi-level benchmark dataset for AI-driven analog and radio-frequency circuit design.

avatar
Asal Mehradfar
Read more
Recent Publications
(2025). 🦅 FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design. In NeurIPS 2025.
(2025). LANTERN: A Machine Learning Framework for Lipid Nanoparticle Transfection Efficiency Prediction.
(2025). Leveraging Uncertainty Estimation for Efficient LLM Routing. In CFAgentic @ ICML 2025.
(2025). CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price Prediction. In ICBC 2025.
(2025). Supervised Learning for Analog and RF Circuit Design: Benchmarks and Comparative Insights.