← All Research Themes

Scientific AI and Intelligent Simulation

Overview

Applying AI to scientific discovery and simulation, with emphasis on differentiable simulation, physics-informed learning, and AI for science.

Key Questions

  • How can AI accelerate scientific simulation without sacrificing physical fidelity?
  • What role can differentiable simulation play in end-to-end optimization of scientific models?
  • How can multimodal AI systems handle complex scientific documents and data?

Our Contributions

  • Developed multimodal AI systems for specialized document analysis
  • Explored AI applications in legal and scientific domains

Recommended Papers

Min Jiang, et al. · Preprint, 2025
Presents a multimodal AI system that combines visual and textual understanding for comprehensive legal document analysis, demonstrating the potential of AI in specialized domain applications.

Recent Work

Min Jiang, et al. · Preprint, 2025
Presents a multimodal AI system that combines visual and textual understanding for comprehensive legal document analysis, demonstrating the potential of AI in specialized domain applications.

Open Problems

  • Bridging the gap between data-driven and physics-based models
  • Ensuring interpretability and trustworthiness of AI in scientific applications
  • Scaling differentiable simulation to complex real-world systems

Prospective Student Projects

  • Differentiable simulation for engineering optimization
  • Physics-informed neural networks for dynamic system modeling
  • AI-assisted scientific literature mining and knowledge graph construction

Learn about joining us →