Hi 👋, I’m Zirui Song(/ˈziːˌruː.i/ /sɔːŋ/), I am a first-year PhD student in the NLP department at MBZUAI, supervised by Prof. Xiuying Chen and Prof. Xiaojun Chang . I received my Bachelor of Engineering (Honours) in Software Engineering with first-class honours from the University of Technology Sydney (UTS). Also I got the Dean’s List 2025 prize(Top 2% of students) from UTS. Before that, I was a member of UTS-NLP since Oct 2023 where I was fortuante to be advised by Prof. Ling Chen, and be mentored by Prof. Meng Fang. I am deeply appreciative of my mentor, Prof. Dayan Guan, who guided me into scientific research.
💻 News
2026-04-29: 2 papers were accepted by ICML 2026.
2026-04-07: 6 papers (1 oral) were accepted by ACL 2026.
2025-11-08: One paper was accepted by AAAI 2026.
2025-09-19: One paper was accepted by NeurIPS 2026.
2025-08-21: 3 papers (1 oral) were accepted by EMNLP 2025.
2025-07-25: I was admitted to the degree of Bachelor of Engineering (Honours) in Software Engineering with First Class Honours
2025-07-06: I won the Dean's List 2025 prize(Top 2% of students) from UTS
2025-07-02: One paper was accepted by ECAI 2026.
2025-05-16: One paper was accepted by ACL 2025.
2025-04-20: One paper was accepted by Nature Computational Science.
2025-03-01: “ MBZUAI, where I will commence my PhD studies in August 2025 here.”
2025-01-23: One paper was accepted by NAACL 2025.
2025-01-02: One paper was accepted by Communications Chemistry.
2024-09-25: First day as a visiting student at MBZUAI under the supervision of Prof. Xiuying Chen.
2024-09-20: One paper was accepted by EMNLP 2024.
2024-07-01: One paper was accepted by ECCV 2024.
Click to expand
2023-11-29: Prof. Ling Chen had accepted me as an undergraduate research assistant at Australia Artificial Intelligence Institute(AAII).
2023-07-01: I am honored to be selected as an international exchange student majoring in Softawre Engineering at UTS.
2023-05-18: Prof. Dayan Guan had accepted me as a remote undergraduate research assistant at ROSE Lab.
Academic Service
- Conference Reviewer: EACL 2026, ICLR 2026, AAAI 2026, EMNLP 2025, COLM 2025, ACM MM 2025, NeurIPS 2025, ACL 2025, NAACL 2025, ICME 2025,IJCAI 2025, EMNLP 2024,
- Journal Reviewer: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),IEEE Transactions on Artificial Intelligence (TAI)
💡 Research Interest
- Multimodal AI: My current research goal is to integrate multimodal information to improve the performance of large language models, at the same time, I am also seek for applications of multimodal models in Geolocation and Embodied AI domains.
- Trustworthy AI: I am also highly interested and experienced in exploring the Jailbreak and attack issues of Multimodal Language Models, particularly in the Vision and Audio modalities.
📖 Educations
-
2025.08->2029.05 (Expected) :PhD,
Mohamed Bin Zayed University of Artificial Intelligence(MBZUAI) -
2021.06->2025.05: B.E.,
University of Technology Sydney(UTS) QS Ranking: 88, U.S. News Ranking: 85. GPA: 3.90/4.00
Now
First year of the PhD. The desert keeps its own hours, and so do I.
Lately I have been circling one question: what does it mean for a model to understand the world it has been shown. Not the act of prediction (we have plenty of that), but the quieter thing underneath. Whether it knows where it stands. Whether it can tell when it is wrong. Whether, given a photograph of a street it has never seen, it can reason its way home.
Most of what I work on lives near this question. Multimodal reasoning. Geolocation. Embodied agents that must act in places they have never been. The trust we extend, or refuse, to what a model claims it sees. I keep walking into the same room through different doors.
I read more than I write. I rewrite more than I publish. Some of the papers listed under my name belong to a younger version of me, and I am still learning how to be honest about that.
I have never loved being alive this much. New cities. New languages overheard on the bus. New collaborators who became friends before they became coauthors. I owe the courage of this season to the UAE Government Scholarship, which let me walk through doors I had only read about. I do not take that lightly.
What I am holding this season:
- a draft I do not yet know how to finish
- a suspicion that our benchmarks have been answering the wrong question
- a quiet thank-you to the people who wrote back to me when I was an undergraduate and unsure of everything
The plan, if it can be called one, is to stay here long enough to plant something. The desert is not empty; it is patient. I would like to grow a small oasis on it, the slow kind, one paper, one student, one honest conversation at a time.
If you are working on something you cannot let go of, I would like to hear about it. My inbox is mostly quiet after midnight.
Last updated: May 2026.
💼 Experiences
- [2024.09 - now] MBZUAI (Supervisor: Prof.Xiuying Chen,topic:Trustworthy MLLMs)
- [2023.10 - 2025.02] University of Technology Sydney, Research Intern (Supervisor: Prof.Ling Chen and Prof.Meng Fang,topic: Multimodal Agents)
- [2023.03 - 2024.01]
Nanyang Technological University, Research Intern (Supervisor: Prof.Dayan Guan,topic: Multimodal LLMs)
🏆 Honors and Awards
- 🥈 Silver Medal, Kaggle - LLM Science Exam [51/2664], 2024
- 🥇 School Second Class Scholarship，2022
📚 Resources
Blogs
- [05/24] [Chinese] National Undergraduate Innovation Project Documentation. [Link]
- [03/24] [Chinese] Negative Transfer. [Link]
- [03/24] [Chinese] Mixture of Experts Explained. [Link]
- [01/24] [Chinese] EMNLP2020 Tutorial Notes (Topic: Explainable AI). [Link]
📜 References
You can find my full CV here (Latest update: Oct 14th, 2024).