Hao-Hsiang (Thomas) Hsiao

Member of Technical Staff, Ricursive Intelligence
Ph.D. Candidate, Georgia Institute of Technology

I am a Member of Technical Staff at Ricursive Intelligence, while completing my Ph.D. at the Georgia Tech Computer-Aided Design Lab (GTCAD) under the supervision of Prof. Sung Kyu Lim.

My research advances Electronic Design Automation (EDA) for 2D and 3D integrated circuits by combining machine learning, LLM-driven optimization, and accelerated computing — toward faster, smarter physical design flows. I received my B.S. in Electrical Engineering from National Taiwan University and my M.S. in Electrical Engineering and Computer Science from the University of California, Irvine.

Experience

Industry & research appointments

Member of Technical Staff · Ricursive Intelligence, Palo Alto, CA

June 2026 – Presentcurrent

Graduate Research Assistant · Georgia Institute of Technology

August 2022 – Presentcurrent

AI-based Physical Design Automation for 2D and 3D ICs (Samsung, 2024–27)
Physical Design Using Reinforcement Learning (NSF, 2023–25)
Physical Design Closure with Machine Learning (Synopsys, 2024–25)
Routability Prediction and Optimization for 3D ICs (Nvidia, 2024–25)

PhD Research Intern, Design Automation · NVIDIA, Santa Clara, CA

Spring 2026

Technical Intern, R&D Team, EDA Group · Synopsys Inc., Sunnyvale, CA

Summer 2025

PhD Research Intern, Design Automation · NVIDIA, Santa Clara, CA

Spring 2025

Technical Intern, R&D Team, EDA Group · Synopsys Inc., Sunnyvale, CA

May 2024 – December 2024

Developed an Intelligent Recipe Recommendation System for Fusion Compiler

Technical Intern, R&D Team, Silicon Realization Group · Synopsys Inc., Sunnyvale, CA (remote)

Summer 2022

Developed a Reinforcement Learning AI agent for Physical Design global placement

Publications

Selected peer-reviewed work

2026

AI-Assisted IC Design with Accelerated Computing and LLM-Driven Optimization

Yi-Chen Lu, Hao-Hsiang Hsiao*, Rongjian Liang, and Haoxing Ren

IEEE Solid-State Circuits Magazine (MSSC), 2026 · * Corresponding author

PDF Link Cite

MapTuner: Multimodal Recipe Recommendation for Physical Design with Layout Maps and Design Insights

Hao-Hsiang Hsiao, Sudipto Kundu, Wei-Ting Jonas Chan, Chitralekha Dasgupta, and Sung Kyu Lim

IEEE International Conference on LLM-Aided Design (ICLAD), 2026

PDF Cite

A Hybrid Reinforcement Learning Framework for Efficient Physical Design Parameter Tuning

Hao-Hsiang Hsiao, Yi-Chen Lu, Pruek Vanna-Iampikul, and Sung Kyu Lim

ACM Transactions on Design Automation of Electronic Systems (TODAES)

Link Cite

C3PO: Commercial-Quality Global Placement via Coherent, Concurrent Timing, Routability, and Wirelength Optimization

Yi-Chen Lu, Hao-Hsiang Hsiao, Rongjian Liang, Wen-Hao Liu, and Haoxing Ren

31st IEEE/ACM Asia and South Pacific Design Automation Conference (ASP-DAC), 2026. Best Paper Award

PDF Link Cite

Differentiable Tier Assignment for Timing and Congestion-Aware Routing in 3D ICs

Yuan-Hsiang Lu, Hao-Hsiang Hsiao, Yi-Chen Lu, Haoxing Ren, and Sung Kyu Lim

31st IEEE/ACM Asia and South Pacific Design Automation Conference (ASP-DAC), 2026

PDF Link Cite

2025

LLM-Enhanced GPU-Optimized Physical Design at Scale (Invited)

Yi-Chen Lu, Hao-Hsiang Hsiao, and Haoxing Ren

44th IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2025

Link Cite

BUFFALO: PPA-Configurable, LLM-based Buffer Tree Generation via Group Relative Policy Optimization

Hao-Hsiang Hsiao, Yi-Chen Lu, Sung Kyu Lim, and Haoxing Ren

44th IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2025

PDF Link Cite

DCO-3D: Differentiable Congestion Optimization in 3D ICs

Hao-Hsiang Hsiao, Yi-Chen Lu, Pruek Vanna-iampikul, Anthony Agnesina, Rongjian Liang, Yuan-Hsiang Lu, Haoxing Ren, and Sung Kyu Lim

62nd ACM Design Automation Conference (DAC), 2025

PDF Link Cite

InsightAlign: A Transferable Physical Design Recipe Recommender Based on Design Insights

Hao-Hsiang Hsiao, Sudipto Kundu, Wei Zeng, Wei-Ting Jonas Chan, Deyuan Guo, and Sung Kyu Lim

62nd ACM Design Automation Conference (DAC), 2025

PDF Link Cite

2024

ML-based Physical Design Parameter Optimization for 3D ICs: From Parameter Selection to Optimization

Hao-Hsiang Hsiao, Pruek Vanna-iampikul, Yi-Chen Lu, and Sung Kyu Lim

61st ACM Design Automation Conference (DAC), 2024

PDF Link Cite

GAN-Place: Advancing Open-Source Placers to Commercial-Quality using Generative Adversarial Networks and Transfer Learning

Yi-Chen Lu, Haoxing Ren, Hao-Hsiang Hsiao, and Sung Kyu Lim

ACM Transactions on Design Automation of Electronic Systems (TODAES)

PDF Link Cite

FastTuner: Transferable Physical Design Parameter Optimization using Fast Reinforcement Learning

Hao-Hsiang Hsiao, Yi-Chen Lu, Pruek Vanna-Iampikul, and Sung Kyu Lim

28th ACM International Symposium on Physical Design (ISPD), 2024

PDF Link Cite

2023

DREAM-GAN: Advancing DREAMPlace towards Commercial-Quality using Generative Adversarial Learning

Yi-Chen Lu, Haoxing Ren, Hao-Hsiang Hsiao, and Sung Kyu Lim

27th ACM International Symposium on Physical Design (ISPD), 2023

PDF Link Cite