Virtual Materials & Processes Design Laboratory · UNIST

From Å to fab,
simulation × AI.

VDLab combines computational science and AI to virtually design and optimize materials, processes, and equipment. Semiconductor manufacturing is our primary testbed, with the same methods extending to functional materials. Digital twins and Physical AI connect these models back to the physical world.

ÅQuantumDFT · energetics
nmAtomisticMD · MLFF
µmFeatureDSMC · level-set
mReactorCFD · plasma transport
fabDigital twinPhysical AI · control

Engineering problems do not live at one scale.

Read the full vision

In the engineering problems around us, the behavior of materials and processes is determined across scales, from atoms to equipment. VDLab connects these scales, from first-principles calculation to continuum analysis, with AI-based scale bridging, and on that foundation studies how to design and optimize semiconductor materials, processes, and equipment in the virtual world first. Our ultimate destination is Advanced Manufacturing AI: digital twins and Physical AI linking virtual models with physical systems, a game changer for advanced manufacturing. Watch us make it real!

우리 주변에서 마주하는 다양한 공학 문제에서, 소재와 공정의 거동은 원자에서 장비까지 여러 스케일에 걸쳐 결정됩니다. VDLab은 제일원리 계산부터 연속체 해석까지 서로 다른 스케일을 AI 기반 스케일 브리징으로 연결하고자 합니다. 이를 기반으로 반도체 소재·공정·장비를 가상 환경에서 먼저 설계하고 최적화하는 접근을 연구합니다. VDLab의 궁극적인 지향점은 첨단제조 AI, 곧 가상 모델과 물리 시스템을 연결하는 디지털 트윈과 Physical AI로 첨단 제조 산업의 게임 체인저를 현실로 만드는 것입니다. 저희의 도전을 지켜봐 주세요!

All research →
01

Multiscale Computational Science

Many engineering systems are governed by phenomena that cross length, time, and physical domains. We connect first-principles, atomistic, mesoscale, feature-scale, and continuum models through physics-based and data-driven scale bridging, so mechanisms discovered at one scale can inform predictions and decisions at another.

More detail →
02

Virtual Design of Materials, Processes & Equipment

We turn computational understanding into design variables and decisions. Our work spans semiconductor surfaces and interfaces, etching and deposition, film growth, reactor transport, and equipment conditions, with AI and optimization used to explore spaces that are too large for trial and error. The same methodology extends to functional materials.

More detail →
03

Advanced Manufacturing AI

Digital twins integrate simulation with experiments, in-situ sensing, and physical equipment. Physical AI uses this shared, physics-grounded representation to interpret process states, predict outcomes, support optimization and control, and move advanced manufacturing toward a closed virtual–physical loop.

More detail →

Join the VDLab.

We are recruiting postdoctoral researchers, graduate students, and undergraduate interns in materials, mechanics, and AI. Contact Byungjo Kim for positions at the quantum–continuum interface.

PostdocGraduate · MS/PhDUndergraduate intern
[email protected]

Rm. 401-9, Bldg. 102, UNIST, Ulsan

VDLab circuit emblem