Changran Xu

PhD Student, The Chinese University of Hong Kong

I am a PhD student in Computer Science at The Chinese University of Hong Kong. My research interests include LLMs, graph neural networks, machine learning, and circuit intelligence. I earned a BSc with First Class Honours from CUHK in 2024 and welcome research discussions and collaboration.

crxu(at)link.cuhk.edu.hk Google Scholar GitHub

News

2026

We launched ArbiterOS, a governance kernel for LLM agents.

May 10

2025

One paper accepted by ACL 2025 Findings.

May 16

One paper accepted by LAD'25.

May 09

One paper accepted by DAC'25.

Feb 15

One paper accepted by ICLR'25 as a Spotlight.

Jan 23

2024

One paper accepted by Advanced Science.

Dec 29

Education

The Chinese University of Hong Kong

PhD in Computer Science 2025.08 - 20??.??

The Chinese University of Hong Kong

BSc Computer Science, First Class Honours 2020.09 - 2024.08

Johns Hopkins University

Visiting Student 2024.06 - 2024.08

Peking University

Summer School 2021.06 - 2021.07 & 2022.06 - 2022.07

Experience

National Center of Technology Innovation for EDA, Nanjing

Algorithm Engineer 2024.05 - 2025.08

Flourish Entertainment Agent Company, Hong Kong

Web Developer Assistant 2023.07 - 2023.08

Legal Expression, Hong Kong

Full-Stack Developer (Entrepreneurship) 2023.05 - 2023.08

Hongtai Water Resources Information Technology Co, Ltd, Ningbo

Front-End Engineer Trainee 2022.05 - 2022.08

Research

Large Circuit Model

Research Assistant, supervised by Prof. XU Qiang 2024.05 - 2025.08

Medical Imaging Analysis

Research Intern, supervised by Prof. Alan Yuille and Dr. Zhou Zongwei 2024.06 - 2024.08

SmartNIC Performance Profiling and Prediction

Research Assistant, supervised by Prof. XU Hong 2023.06 - 2023.08

Honors & Awards

Honorable Mention Award of LLM4HWDesign @ ICCAD 2024 2024

Dean's List of Faculty of Engineering, CUHK 2024

Selected Publications

View all

From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers

Xiangyu Wen, Yuang Zhao, Xiaoyu Xu, Lingjun Chen, Changran Xu, Shu Chi, Jianrong Ding, Zeju Li, Haomin Li, Li Jiang, Fangxin Liu, Qiang Xu

arXiv 2026 Preprint

Paper Code

Speculative Decoding for Verilog: Speed and Quality, All in One

Changran Xu*, Yi Liu*, Yunhao Zhou, Shan Huang, Ningyi Xu, Qiang Xu (* equal contribution)

ACM/IEEE Design Automation Conference (DAC) 2025 DAC

Paper

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

Yi Liu, Changran Xu, Yunhao Zhou, Zeju Li, Qiang Xu

International Conference on Learning Representations (ICLR) 2025 ICLRSpotlight

Paper Code

Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis

Muxi Chen*, Yi Liu*, Jian Yi, Changran Xu, Qiuxia Lai, Hongliang Wang, Tsung-Yi Ho, Qiang Xu (* equal contribution)

arXiv 2024 Preprint

Paper Code