Hi! My name is In Huh, and I am a second-year Ph.D. student in Electrical and Computer Engineering at Purdue University, working under the supervision of Prof. Muhammad Ashraful Alam.

My research aims to develop machine learning (ML) methods for identifying the intrinsic structure of physical systems beyond surface-level statistical patterns. I focus on quotient representation learning, which separates physically meaningful structure from extrinsic, description-dependent variations in data. Methodologically, I pursue two complementary routes. One is invariant-driven: defining the intrinsic structures that should remain unchanged across physically equivalent systems, and learning representations that preserve them. The other is symmetry-driven: defining the transformations that generate equivalence relations, and learning representations that factor out the corresponding variations.

Practically, my work targets data-driven modeling of nonlinear dynamical systems, with an emphasis on preserving qualitative dynamical features such as invariant sets, stability, and bifurcations. I also study semiconductor device physics through data-driven scaling laws, viewing scaling relations as symmetry-induced descriptions that reveal invariant physical mechanisms across materials, geometries, and operating regimes.

News

[Jun. 2026] Our paper “A Scaling Theory for the Nonlinear Subthreshold Behavior of Cryogenic UTB MOSFETs” is accepted to IEEE EDL.

[May 2026] I was selected as an ICML 2026 Gold Reviewer.

[Apr. 2026] Our paper “Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality” is accepted to ICML 2026.

[Apr. 2026] Our paper “Thickness Scaling and Roughness-Induced Mobility Cliff in Ultra-thin-body MOSFETs” is accepted to IEEE EDL.

[May 2025] Our paper “Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré-Hopf Theorem” is accepted to ICML 2025.

[Feb. 2025] Our paper “ML-Driven Compact Models for RRAMs: Addressing Variability and Simulation Efficiency” is accepted to IEEE EDL.

[Aug. 2024] I have started the Ph.D. program in Electrical and Computer Engineering at Purdue University.