Yaxin Luo

Yaxin Luo

Native Multimodal Foundation Models, Multimodal Agentic Models

Hi there! ๐Ÿ‘‹ I am Yaxin Luo.

ไธญๆ–‡
About Me
Decorative animated background
Hello! I am a First-Year Machine Learning PhD student at MBZUAI, advised by Prof. Zhiqiang Shen. I am also closely working with my friend Xiaofu Chen. Currently, my research explores Native Multimodal Foundation Models and Multimodal Agentic Models as tightly coupled directions: building models that unify understanding, generation, reasoning, planning, and action across diverse modalities, and using those capabilities to support long-horizon interactive tasks.
Previously, I earned my Bachelorโ€™s degree from Technical University of Denmark, where I was fortunate to be supervised by Prof. Dim P. Papadopoulos. Meanwhile, I was lucky to be collaborating with Dr.Gen Luo and Prof.Rongrong Ji on efficient deep learning research during my bachelor.
More about my earlier journey...
I spent an intense and rewarding year at the University of Edinburgh studying pure mathematics and physicsโ€”an experience that sparked my passion for science and technology, deepened my curiosity about the unknown, I was curious and wanted to explore String Theory at that time, this one year ultimately shaped who I am today. Before Edinburgh, while enrolled in a Bio-Medicine program at the University of Queensland and preparing for the UCAT test to be admitted into the university's medical school, I failed at the end. As I only focused on managing a high-street multi-brand boutique which was located in Brisbane's Southbank near the casino, and was far more focused on business than on study and research; that Edinburgh year changed my priorities and set me on a research path, thanks to the advice, encouragement and support of my academic personal tutor Prof.Ana Rita Pires when I was at Edinburgh. Anyway, all those past experiences have made me who I am today.

My research interests focus on:

  • Native Multimodal Foundation Models and Multimodal Agentic Models : I view native multimodal foundation models and multimodal agentic models as a connected research agenda. Native multimodal foundation models provide unified representations and capabilities for multimodal understanding, generation, reasoning, planning, and action; multimodal agentic models further test and extend these capabilities through long-horizon interaction, memory, execution, and self-correction. I am especially interested in concrete long-horizon tasks such as Agentic Design, Agentic Game Crafting, and Application Crafting.
Recently, I am focusing on long-horizon multimodal agentic foundation models and systems, especially for Agentic Design, Agentic Game Crafting, and Application Crafting.
Experience
Research Intern, Meituan LongCat Team
Apr 2026 โ€“ Present ยท Beijing, China
Working on Unified Multimodal Foundation Model Projects(LongCat-Next Team).
  • Long-Horizon Multimodal Interactive Tasks for Unified Multimodal Models: Agentic Design System.
  • Unified Discrete Vision Encoder for both understanding and generation.
Research Assistant, MBZUAI
Jan 2025 โ€“ Aug 2025 ยท Abu Dhabi, UAE
Advised by Prof. Zhiqiang Shen at the VILA Lab.
  • Investigated language-pretraining-induced bias as a strong foundation for general vision tasks, showing LLM priors transfer to pure-vision learning โ€” published in TMLR 2026.
  • Explored reasoning and agentic behaviors in multimodal large language models (MLLMs), leading the OpenCaptchaWorld benchmark (NeurIPS 2025).

News

[2026-02-10] ๐Ÿš€ Next-Gen CAPTCHAs is now available on arXiv! A defense framework leveraging cognitive gaps against MLLM-based GUI agents.
[2025-09-18] ๐Ÿš€ OpenCaptchaWorld has been accepted by NeurIPS 2025.

Selected Publications

( * indicate equal contribution)

For full and up-to-date publication list, please refer to my Google Scholar page.

Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense
arXiv 2026
Jiacheng Liu *, Yaxin Luo *, Jiacheng Cui, Xinyi Shang, Xiaohan Zhao, Zhiqiang Shen
๐Ÿ“„ Paper ๐Ÿ’ป Code ๐Ÿš€ Demo ๐ŸŒ Project
OpenCaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
NeurIPS 2025
Yaxin Luo *, Zhaoyi Li *, Jiacheng Liu, Jiacheng Cui, Xiaohan Zhao, Zhiqiang Shen
๐Ÿ“„ Paper ๐Ÿ’ป Code ๐Ÿš€ Demo
APL: Anchor-Based Prompt Learning for One-Stage Weakly Supervised Referring Expression Comprehension
ECCV 2024
Yaxin Luo, Jiayi Ji, Xiaofu Chen, Yuxin Zhang, Tianhe Ren, Gen Luo
๐Ÿ“„ Paper ๐Ÿ’ป Code
ฮณ-MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
ICLR 2025
Yaxin Luo, Gen Luo, Jiayi Ji, Yiyi Zhou, Xiaoshuai Sun, Zhiqiang Shen, Rongrong Ji
๐Ÿ“„ Paper ๐Ÿ’ป Code