Research roots. Entrepreneurial focus.
PhD at MBZUAI · Abu Dhabi, UAE
I’m a PhD student at Mohamed bin Zayed University of Artificial Intelligence, advised by Prof. Xiuying Chen and Prof. Xiaojun Chang. My research spans multimodal AI, embodied agents, and trustworthy models. Previously, I earned my bachelor’s degree in Software Engineering with First Class Honours from the University of Technology Sydney.
My focus is shifting toward entrepreneurship. I’m exploring how AI can understand and act in the physical world, starting with chemistry. My two bets are autonomous chemistry labs that turn model decisions into experiments, and simulation models that predict how chemical reactions unfold.
What I’m building
Chemistry is where I’m placing that bet: connecting what a model predicts with what happens in a real experiment. I’m pursuing two complementary routes toward that goal.
Act in the physical world
I want to build labs where AI can plan experiments, coordinate automated equipment, and learn from the results.
The Agentic Model would be the lab’s decision-making brain, turning scientific goals into experimental steps and adapting to observations. A catalysis foundation model would provide specialized knowledge for reasoning about catalysts and reaction conditions. Lab automation would connect those decisions to physical experiments.
Predict the physical world
My second bet is a Simulation Model that models chemical reactions and aims to predict their behavior under real experimental conditions.
The goal is to explore how changes in catalysts and reaction conditions affect outcomes before running an experiment. Predictions would guide what to test in the lab, while experimental observations would help evaluate and improve the model.
Together, these routes aim to connect prediction, experimentation, and learning: use simulation to guide experiments, then use physical evidence to improve the next prediction.
Selected work on embodied reasoning, multimodal AI, trustworthy models, and human-aligned evaluation.
Reinforcement learning for reasoning in embodied manipulation, aligning large vision-language models with affordance and trajectory rewards.
AnomalyGen builds virtual anomaly scenes without human annotation to make household robots more robust.
A comprehensive benchmark for the cross-style visual capability of LMMs. Toolkit & Code
WereBench, a human-verified multimodal Werewolf dataset, and WereAlign, a strategy-alignment framework that scores LLMs against human play instead of survival time.
An open, comprehensive benchmark exposing how large audio-language models can be jailbroken through the audio channel.
A taxonomy of domain knowledge injection: dynamic injection, static embedding, modular adapters, and prompt optimization.
* Equal contribution. See Google Scholar for the full publication list.
PhD student in NLP at MBZUAI, supported by the UAE Government Scholarship. Previously, Software Engineering at UTS with First Class Honours and the Dean’s List 2025 award.
Research experience at Alibaba, MBZUAI, UTS, and NTU, spanning multimodal AI, embodied agents, and trustworthy models.
PhD, Mohamed bin Zayed University of Artificial IntelligenceExpected · NLP Department · UAE Government Scholarship
B.E. (Honours), University of Technology SydneySoftware Engineering · First Class Honours · GPA 3.90/4.00 · Dean's List 2025 (Top 2%)
Alibaba GroupAlgorithm Engineer (Research Intern) · Supervised by Xiang Wang
MBZUAIVisiting student → PhD · Supervisor: Prof. Xiuying Chen · Trustworthy MLLMs
University of Technology SydneyResearch Intern · Prof. Ling Chen & Prof. Meng Fang · Multimodal Agents
Nanyang Technological UniversityResearch Intern · Supervisor: Prof. Alex Kot · Multimodal
Let’s connect
I’d love to hear from potential co-founders, researchers, and people working in chemistry labs who see opportunities for AI and automation. Tell me what you’re working on and where our interests might meet.
ziruisong2003@gmail.comBased in Abu Dhabi, United Arab Emirates.