Chair(s): Peichen Zhong (NUS), Kai Guo (A*STAR)
Co-Chair(s): Chenru Duan (Deep Principles, Inc., China)
Symposium Scope/Topics
This symposium convenes researchers at the forefront of computational materials science to explore the convergence of artificial intelligence, generative modeling, and laboratory automation. While rooted in advances in atomistic simulations and machine learning potentials, this scope expands to encompass the entire materials lifecycle. We will examine how agentic AI and autonomous workflows are transcending traditional scale barriers, accelerating discovery not only in chemical synthesis but also in mechanical property optimization, processing, and manufacturing. By bridging the gap between theoretical generative design and practical real-world application, this forum aims to define the next generation of closed-loop, AI-driven materials science.
- Generative & Agentic AI: Development of generative models (VAEs, diffusion, flow-based), scientific LLMs, and multi-agent systems for materials design.
- Atomistic to Mesoscale Simulation: Machine learning interatomic potentials and statistical mechanical modeling for high-accuracy, large-scale simulations.
- Domain-Specific Acceleration: AI applications in optimizing mechanical, thermal, and electronic properties across diverse material classes (e.g., polymers, alloys, biomaterials).
- AI in Manufacturing & Processing: Integrating machine learning into process optimization, quality control, and scalable manufacturing workflows.
- Autonomous Experimentation: Self-driving laboratories, synthesizability prediction, and automated synthesis planning.
- Data & Benchmarking: Novel datasets, standardized benchmarks, and integration frameworks for closed-loop discovery.
Invited Speakers
To be confirmed
