AIST5040 PhysAI and GenAI for Natural Science
(a.k.a. AI for Science)

  • Department of Computer Science and Engineering
    The Chinese University of Hong Kong
    2026-2027 Term 1

Description

This course introduces PhysAI and GenAI as complementary approaches to natural scientific discovery. PhysAI refers to physics-inspired AI models that embed domain knowledge, physical laws, and invariances into learning frameworks, enabling models to achieve greater robustness, accuracy, and interpretability. In contrast, GenAI leverages generative modeling to create hypotheses, design candidates, and explore novel scientific paradigms beyond the limits of existing data. Together, PhysAI and GenAI form a powerful synergy: PhysAI accelerates and strengthens established paradigms, while GenAI opens pathways to entirely new directions of research. Through this integration, PhysAI and GenAI hold the potential to transform discovery in chemistry, materials science, and biology.

Advisory: Students are expected to have taken AIST1000 or AIST3120 or AIST4010 or AIST4030 or AIST5030 or CSCI3230 or CSCI3320.

Reference Materials

Course Staff

Instructor

Dr. Shengchao Liu
  • Office: SHB 1016
  • Office Hour: By Appointment
  • Contact: scliu@cuhk.edu.hk

Teaching Assistant

Syllabus

Date Topics References & Presentation Topics
Week 1 Sep 11th Overview of AI for Science
Week 2 Sep 18th AI & Physics Foundation:
GenAI (1) 		AR & Transformer-based AR, NCE, VAE, GAN, Flow-based Model, Diffusion, Flow Matching, K-Flow
Week 3 Sep 25th AI & Physics Foundation:
GenAI (2)
PhysAI 		AR & Transformer-based AR, NCE, VAE, GAN, Flow-based Model, Diffusion, Flow Matching, K-Flow
PINN, Neural Operator, Geom3D, InertialAR
Week 4 Oct 2nd AI & Physics Foundation:
Pretraining, Multi-modal Learning, Large Language Model, Foundation Model, and World Model (1) 		InfoNCE, SimCLR, BYOL, SimSiam, GraphMVP, JEPA and JEPA Series
Week 5 Oct 9th AI & Physics Foundation:
Pretraining, Multi-modal Learning, Large Language Model, Foundation Model, and World Model (2) 		InfoNCE, SimCLR, BYOL, SimSiam, GraphMVP, JEPA and JEPA Series
Week 6 Oct 16th PhysAI for Chemistry:
Energy and Force, AI MD

Guest Lecture (tentative):
Topics TBD 		Geom3D, SE(3)-Trans, EGNN, SEGNN, GraphMVP, GeoSSL, MoleculeSDE, xTB, Charge Density Prediction
Week 7 Oct 23rd GenAI for Chemistry:
Molecule Generation, Molecule Optimization, Reaction Mechanism

Guest Lecture (tentative):
Topics TBD 		MoleculeSTM, InertialAR, LLM for Small Molecule
Week 8 Oct 30th PhysAI for Biology:
Folding, Binding, Structure-based Drug Design

Guest Lecture by Yanjing Li:
Topics TBD 		AlphaFold2, AlphaFold3, ESM, RigidSSL, NucleusDiff
Week 9 Nov 6th GenAI for Biology:
Protein Design and Engineering, Structure Generation, Metabolism Pathway

Guest Lecture by Dr. Yuning You:
Topics TBD 		ProtTrans, Evo, Evo2, ProteinDT, ChatDrug, LLM for Protein, BioMatrix, LOGOS, ESM3
Week 10 Nov 13th PhysAI for Material Science:
Crystallization, Phase Detection

Guest Lecture by Dr. Zach Zheng:
Topic: Data-Driven Discovery of Metal-Organic Frameworks 		Long-range Interaction
Week 11 Nov 20th GenAI for Material Science:
Material Generation, Structure Generation

Guest Lecture (tentative):
Topics TBD 		DiffCSP, MatterGen, ChatBattery, MatterChat, LLM for material
Week 12 Nov 27th Project Presentation (1)
Week 13 Dec 4th Project Presentation (2)