1 citations · 1 across the 9 of their papers we have counts for
5 papers · 1 filter
Platonic Task Arithmetic
Junghwan Park, Woojin Cho
Distinct pre-trained models specialized for the same task converge to closely similar behavior, yet the parameter updates that produce it share no common coordinate system. Weight-…
Beyond Simulation: Retain-and-Repair Neural Operators for Real-World Adaptation
Woojin Cho, Junghwan Park
Neural operators increasingly benefit from pretraining on numerical simulations, yet adapting them for real-world prediction remains challenging. We introduce the Retain-and-Repair…
ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink
Woojin Cho, Junghwan Park, Sangcheol Sim +3
The acquisition of multispectral imagery via small satellites (e.g., CubeSats) presents significant data downlink challenges due to high data volumes and restricted communication w…
Escaping Spectral Bias without Backpropagation: Fast Implicit Neural Representations with Extreme Learning Machines
Woojin Cho, Junghwan Park
Training implicit neural representations (INRs) to capture fine-scale details typically relies on iterative backpropagation and is often hindered by spectral bias when the target e…
PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting
Seokhyun Chin, Junghwan Park, Woojin Cho
Precipitation nowcasting, key for early warning of disasters, currently relies on computationally expensive and restrictive methods that limit access to many countries. To overcome…