CV

Education

• Ph.D in Machine Learning, Georgia Institute of Technology, 2029 (expected)
• B.S. in Economics & Computer Science, Seoul National University, 2024

Work experience

• Graduate Research Assistant (Fall ‘24 - Spring ‘25)
  • Georgia Institute of Technology (Supervisor: Prof. Celine Lin)
• Undergraduate Research Assistant (Fall ‘22 - Summer ‘23)
  • Seoul National University (Supervisor: Prof. Jae W. Lee)
• Undergraduate Research Assistant (Summer ‘22)
  • Seoul National University (Supervisor: Prof. Yongsoo Song)

Publications

KLIP: Localized Distribution Shift Detection via KL-Divergence with Diffusion Priors in Inverse Problems

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control

LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels

PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation

LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering

LongMamba: Enhancing Mamba’s Long-Context Capabilities via Training-Free Receptive Field Enlargement

3D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning

VGA: Hardware Accelerator for Scalable Long Sequence Model Inference

A Memory-Efficient Edge Inference Accelerator with XOR-based Model Compression