Education & Experience
For a one-page printable summary, see my CV (PDF).
Education
- The Hong Kong University of Science and Technology (HKUST) — Sep 2024 – present
- BSc — Double Major in Computer Science and Mathematics; Extended Major in Artificial Intelligence
- GPA: 4.03 / 4.3
- Honors:
- University’s Scholarship Scheme for Continuing Undergraduate Students (Top 1%), 2024 & 2025
- S.S. Chern Class — Honor for top academic performance across all mathematics coursework.
- Dean’s List Honor (GPA above 3.7), 2024 & 2025
- Relevant coursework: Algorithms, Statistical Inference, Machine Learning, Linear Algebra, Probability Theory (A+ in all CS/Math courses)
Research Experience
- HKUST KnowComp Group, advised by Prof. Yangqiu Song — 2025 – present
- Research on reasoning and evaluation of large language models and vision-language models.
- Focus on abductive and multimodal reasoning.
Publications
Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song. (2026). "DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay." Proceedings of ACL 2026 (Main Conference).
Zhaoyang Liu, Jingjing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Xuan Dong, Yue Yu, Chenyu Lu, Yunxiang Mo, Yao Yan, Zeyue Tian, Xiao Zhang, Yuan Huang, Yiqian Liu, Weijie Su, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang. (2026). "ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data." ICLR 2026 (Oral).
Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song. (2025). "DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay." EMNLP 2025 Workshop (Spotlight).
Internship Experience
- Beijing Ingenic Semiconductor Co., Ltd. — Machine Learning Engineer Intern, Jun 2025 – Aug 2025
- Developed and optimized ML models for embedded / on-chip AI scenarios.
- Built model training, evaluation, and inference pipelines in PyTorch.
- Deployed models to edge devices under tight latency and memory constraints.
- Worked across algorithm and hardware teams to align model design with chip-level constraints.
- Benchmark Architectural Design Co., Ltd — Jan 2025
- Built front-end modules with the MFC framework for an internal mini-program.
- UI design, event handling, and system debugging in a small team.
Competitions
- National Mathematical Olympiad (China) — Second Prize, 2023
- National Informatics Competition (China) — Second Prize, 2022
Technical Skills
- Machine Learning & NLP: Transformer architectures, multimodal reasoning, abductive inference, prompt engineering, fine-tuning
- Frameworks & Tools: PyTorch, Hugging Face Transformers, OpenAI API
- Programming Languages: Python, C++, MATLAB
- Languages: Chinese (native), English (fluent)
