avatar

Hangyu Ran

MPhil Student, Data Science and Analytics Thrust
The Hong Kong University of Science and Technology (Guangzhou)

About Me

I am currently a first-year MPhil student at The Hong Kong University of Science and Technology (Guangzhou), where I am fortunate to be advised by Prof. Zhijiang Guo. I received my B.Eng. degree in Computer Science and Technology from Central South University, where I was fortunate to be advised by Prof. Jinpeng Wang and Dr. Kevin Lin.

My research interests include multimodal large language models, reinforcement learning and recursive self-improvement. My recent work focuses on visual code generation.

News

Aug. 2026
One paper was accepted by EMNLP 2026 Findings.
Aug. 2026
Honored to join LARK Lab, advised by Prof. Zhijiang Guo.
May 2026
Congratulations! VCode was selected as an oral presentation at the CVPR 2026 Visual Concepts Workshop.
Apr. 2026
Honored to be named an Outstanding Graduate of Central South University.
Feb. 2026
Grateful to receive the CSU-JPG Lab Annual Award.
Nov. 2025
We released VCode, a multimodal coding benchmark with SVG as symbolic visual representation.
Feb. 2025
Luckily joined CSU-JPG Lab as an undergraduate research assistant.

Publications

  1. arXiv
    Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
    Liaoyuan Fan*, Yuhao Zheng*, Dongxing Mao*, Hangyu Ran*, Siyuan Hu*, Weijia Mao, Rui Zhao, Weijia Wu, Guian Fang, Yanzhe Chen, Zeyu Zhu, Yuxin Jiang, Yiren Song, Yuchao Gu, Junchao Yi, Qi Hu, Dan Kong, Alex Jinpeng Wang, Kevin Qinghong Lin, Mike Zheng Shou, Wei Liu (*Equal contribution)
    arXiv preprint, 2026
    [Project] [Paper] [Code] [HF Daily Paper]

  2. EMNLP
    RULER: Instance-aware Rubric Rewards for SVG Generation
    Hangyu Ran*, Yuhao Zheng*, Yingying Zhang, Kevin Qinghong Lin, Han Peng (*Equal contribution)
    EMNLP 2026 Findings #1 HF Daily Paper
    [Project] [Paper] [Code] [Dataset]

  3. CVPRW
    VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
    Kevin Lin*, Yuhao Zheng*, Hangyu Ran*, Dantong Zhu, Dongxing Mao, Linjie Li, Philip Torr, Alex Jinpeng Wang (*Equal contribution)
    CVPR 2026 Visual Concepts Workshop Oral
    [Project] [Paper] [Code] [Demo] [Twitter]

Experiences

Aug. 2026 - Present

LARK Lab

MPhil Student

Fortunate to be advised by Prof. Zhijiang Guo. Research interests include multimodal large language models, reinforcement learning, and recursive self-improvement.

Dec. 2025 - Present

Inclusion AI, Ant Group

Research Intern

Focus on multimodal generation and reasoning, and participate in visual code generation research.

Feb. 2025 - Jul. 2026

CSU-JPG Lab, Central South University

Undergraduate Research Assistant

Advised by Prof. Jinpeng Wang and Dr. Kevin Lin.

Honors & Awards


Many thanks to Yaoyao for sharing this great template yaoyao-liu/minimal-light.