Thank you for your interest in the AI4PhysSci Lab! We welcome questions, collaborations, and inquiries from researchers and students who share our passion for AI4Science and quantum chemistry.

We look forward to hearing from you and exploring ways to collaborate or share ideas!

We are affiliated with the Department of Chemistry and the Department of Chemical and Biological Engineering at The Hong Kong University of Science and Technology. As an interdisciplinary research group working at the intersection of AI and the physical sciences, we are actively seeking talented and motivated researchers from science-related fields (chemistry, physics, materials science, etc.) as well as AI-focused disciplines (computer science, mathematics, statistics, etc.). Interested candidates are encouraged to reach out to our group directly via email or through any of our group social media channels (X, BlueSky, etc.).

🎯 Specific opening: AI for Quantum Computing, Neural Network Ansatz, Electronic Structure Theory, Quantum Many-body Simulations
We are currently looking for motivated researchers to work on AI for quantum computing or neural network ansatz design (simulator layer). This direction focuses on developing intelligent approaches to enhance quantum simulation capabilities, including but not limited to neural network quantum states, variational quantum algorithms, and ML-accelerated quantum computing workflows.

Research directions:
• Prof. Lixue Cheng (HKUST): AI for quantum computing, neural network ansatz design, and their applications in quantum chemistry simulations.
• Dr. Jiace Sun (Caltech): Stochastic tensor contraction (STC) for quantum chemistry, Tensor Network methods for quantum many-body simulations, and quantum computing for quantum chemistry.

This project will be conducted in joint collaboration with Dr. Jiace Sun from Caltech (Google Scholar). Preferred academic backgrounds: Physics, Chemistry, or Materials Science, particularly those with a strong foundation in quantum mechanics and condensed matter theory / theoretical chemistry.

Position type: This opening is available for both Research Assistant (RA) and PhD student positions.

Suggested readings:
Prof. Lixue Cheng:
• Quantum Approximate Optimization via Learning-based Adaptive Optimization (Commun. Phys. 2024)
• An ab initio Foundation Model of Wavefunctions that Accurately Describes Chemical Bond Breaking (arXiv:2506.19960)
• TenCirChem: An Efficient Quantum Computational Chemistry Package for the NISQ Era (JCTC 2023)

Dr. Jiace Sun:
• Stochastic Tensor Contraction for Quantum Chemistry (arXiv:2602.17158)
• Stabilizer Ground State: Theory, Algorithms and Applications (Quantum 2025)
• Towards Chemical Accuracy with Shallow Quantum Circuits: A Clifford-Based Hamiltonian Engineering Approach (JCTC 2024)

Additional relevant papers:
• Highly Accurate Real-space Electron Densities with Neural Networks (J. Chem. Phys. 2025)
Application note: See the "How to Apply" section below for detailed application instructions and interview process.

⌛ Current openings:

We have one current opening for the AI for Quantum Computing & Neural Network Ansatz direction (see details above). Besides this, we temporarily have no other openings for the 2027 Spring, 2027 Fall, 2028 Spring, 2028 Fall, or 2029 Spring PhD admission cycles. However, we welcome inquiries from prospective students interested in future cycles (2029 Fall and beyond). If you are highly motivated to apply for one of the closed intakes, please include a personal statement describing the specific directions you hope to pursue, why you are committed to them, and how your background fits those directions. Exceptions may be considered based on the contents of the letter of intention.

Please feel free to reach out to our lab to discuss potential research opportunities and to learn more about our group's work.

🚀 Long-term openings:

As part of our commitment to fostering better education in the AI era, we warmly welcome younger generations to join our group. High school and undergraduate students are especially encouraged to participate in our AI for Science research initiatives.

🌱 A supportive and collaborative environment: We will work together as partners and colleagues, not just as students and supervisors.

💡 Cultivate your own scientific style and taste: Develop your own approach to AI for Science and scientific problem solving.

🛠️ Build a versatile AI-era skill set: Learn to bridge theory and experiment with ML and data science via industry-standard coding practices.

🔬 Tailored growth for diverse goals: Sherry returned from industry (MSR & Tencent) and cares about your career goals. We encourage students to pursue careers in either academia or industry. For different career paths, we provide research opportunities that help you the most and actively support participation in industry internships.

🌍 Opportunities to connect and collaborate: Collaborate with computer scientists, physicists, chemists, and materials scientists from both academia (e.g., Caltech, Westlake U, HKUST, NUS, etc.) and industry.

Before applying, we suggest candidates consider the following courses and related topics, which will be extremely helpful for understanding the core research objectives of the AI for Physical Sciences Lab. Please also consider checking the Mini Tests and submitting multiple test results to show your enthusiasm for AI4S.

1. CS/Math: Linear Algebra, Probability and Statistics, Data Structures, Introduction to Machine Learning/AI, Mathematical Modeling, Stochastic Processes and Markov Chains, Linear Programming, Convex Optimization, Statistical Learning Theory, Information Theory, Functional Analysis, Numerical Analysis/Linear Algebra/PDE, Stochastic DE, Differentiable Manifolds, Lie Algebra, Computational Complexity, Topics in ML (Gaussian Processes, Graph Neural Networks, Reinforcement Learning, Generative Models, Language Models). Abstract Algebra, Topology, and Computational Graphics are not required but are a plus.
2. Physics/Chemistry/Materials: Quantum Mechanics, Statistical Mechanics, Atomic Physics, Electronic Structure Theory, Computational Physics, Group Representation Theory (note: not just group theory; chemistry students may encounter this in inorganic or structural chemistry courses), Solid-State Physics, Quantum Field Theory, Polymer Chemistry/Physics, Introduction to Quantum Computing.
3. Other foundational skills: GitHub (open-sourcing spirit), Python (NumPy, SciPy, Scikit-learn, Pandas, etc.), PyTorch, JAX. Proficiency in using the Linux operating system, command line, Slurm, Docker/Conda for environment setup, and the ability to collaborate effectively with AI agents (e.g., vibe coding, automation pipeline for your Gaussian calculations, auto-matching paper formulas with code, etc.). C++ and Julia are not required but a plus. Java is not required and not a plus.

For the "AI for Quantum Computing & Neural Network Ansatz" opening: Please do NOT fill out the Google Form. Instead, directly email both Prof. Lixue Cheng and Dr. Jiace Sun with your CV, unofficial transcript, and a brief research statement. Interviews will be conducted jointly by both researchers, including:

• Technical discussions on quantum computing (e.g., Stabilizer Ground State), neural network ansatz (e.g., Orbformer), or electronic structure theory (e.g., STC-CC) based on the suggested readings
• Assessment of basic math knowledge (Linear algebra & probability)
• Brief coding demonstration or discussion of computational skills
• Assessment of foundational knowledge in quantum mechanics, statistical mechanics, and electronic structure theory

For other general inquiries: To express your interest in joining our lab, please:

1. Draft an email to ai4qchkust@gmail.com describing your interest in our research and how your background aligns with our lab's focus on AI for Physical Sciences.
2. Fill out our Google Form to provide additional information about yourself and your research interests.

After we review your application, we will respond directly to your email.