Lixin Liu

Ph.D.

 

Department of Computer Science and Engineering
The Chinese University of Hong Kong

 

kerryliu1997 [at] gmail.com

 

[Github] | [Google Scholar] | [Linkedin]

Biography

I am currently working on LLM algorithm-system co-optimization. I obtained my Ph.D. in 2023 from The Chinese University of Hong Kong under the supervision of Prof. Evangeline F.Y. Young, where I also served as a Postdoctoral Fellow. While my early research focused on GPU-accelerated VLSI EDA, I now work on bridging the gap between high-performance system and large-scale model.

Selected Works

Orbit: Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs

Zeju Qiu*, Le Chen*, Lixin Liu*, Tim Z. Xiao, Yao Feng, Yangyi Huang, Zhen Liu, Han Shi, Yandong Wen, Zhouliang Yu, Bernhard Schölkopf, Weiyang Liu

Open-source Project

[Code] | [Project]

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation

Zeju Qiu, Lixin Liu, Adrian Weller, Han Shi, Weiyang Liu

International Conference on Machine Learning (ICML) 2026 (Oral)

[Code] | [Project]

ExactMap: Enhancing Delay Optimization in Parallel ASIC Technology Mapping

Zhenxuan Xie, Lixin Liu, Tianji Liu, Evangeline F.Y. Young

International Conference On Computer Aided Design (ICCAD) 2025 (Best Paper Award Nomination)

[Project]

Hybrid Modeling and Weighting for Timing-driven Placement with Efficient Calibration

Bangqi Fu, Lixin Liu, Martin D.F. Wong, Evangeline F.Y. Young

International Conference On Computer Aided Design (ICCAD) 2024

[Code]

Parmesan: Efficient Partitioning and Mapping Flow for DNN Training on General Device Topology

Lixin Liu, Tianji Liu, Bentian Jiang, Evangeline F.Y. Young

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 2024

[Code] | [Additional Results]

Xplace: An Extremely Fast and Extensible Placement Framework

Lixin Liu, Bangqi Fu, Shiju Lin, Jinwei Liu, Evangeline F.Y. Young, Martin D.F. Wong

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 2024

[Code]

CoPlace: Coherent Placement Engine with Layout-aware Partitioning for 3D ICs

Bangqi Fu, Lixin Liu, Yang Sun, Wing-Ho Lau, Martin D.F. Wong, Evangeline F.Y. Young

ACM/IEEE Asia and South Pacific Design Automation Conference Technical Program (ASP-DAC) 2024 (Best Paper Award Nomination)

[Slides]

Xplace: An Extremely Fast and Extensible Global Placement Framework

Lixin Liu, Bangqi Fu, Martin D.F. Wong, Evangeline F.Y. Young

ACM/IEEE Design Automation Conference (DAC) 2022

[Code] | [Slides]

Neural-ILT: Migrating ILT to Neural Networks for Mask Printability and Complexity Co-optimization

Bentian Jiang, Lixin Liu, Yuzhe Ma, Hang Zhang, Bei Yu, Evangeline F.Y. Young

International Conference On Computer Aided Design (ICCAD) 2020

[Code] | [Slides]

Thesis

When Placement Meets GPU: GPU-Accelerated VLSI Placement and Device Placement for GPUs [Thesis]

Honors & Awards