arXiv subjects

Junghwan Park

Publications and source records attributed to Junghwan Park.

15 recordsLinked to original sources

arXiv2026

ELMZip: Onboard Satellite Image Compression via Extreme Learning Machines for Efficient Downlink

The acquisition of multispectral imagery via small satellites (e.g., CubeSats) presents significant data downlink challenges due to high data volumes and restricted communication windows. While onboard image compression is critical to address this bottleneck, traditional methods often struggle to adapt to the nonlinear statistics of multi-band, multi-resolution data. To overcome these limitations, we propose ELMZip, a novel framework based on Extreme Learning Machines (ELM) and domain decomposition strategies for efficient, resolution-free onboard neural representation. ELMZip formulates the fitting process as a convex least-squares problem using random-feature single-layer networks, thereby eliminating the need for computationally expensive backpropagation. By adopting an asymmetric transmission protocol that sends only the compact output weights, the proposed method significantly reduces the downlink payload. Unlike previous neural representation approaches that rely on iterative optimization and require transmitting full network parameters, ELMZip achieves significant compression efficiency while maintaining high reconstruction fidelity. This capability enables immediate image reconstruction for analysis, allowing resource-constrained platforms to maximize data return and advancing real-time AI-powered Earth observation.

cs.LG↗

arXiv2026

Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation

Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downlink capacity remains a critical bottleneck -- often causing significant latency or the loss of valuable observations within limited contact windows. We propose a "Summarize First, Download Later" paradigm that exploits recent advances in onboard edge computing and Vision-Language Models (VLMs). Rather than indiscriminately downlinking raw imagery, the system follows a three-phase interaction protocol: the satellite first transmits concise natural language summaries generated by a quantized onboard VLM; ground operators then issue targeted Visual Question Answering (VQA) queries to verify scene relevance (e.g., wildfires or maritime anomalies); and full-resolution images are downloaded only when critical information is confirmed. This transforms the downlink from passive bulk transfer into an active, semantics-aware dialogue. We implement and evaluate the system on a resource-constrained NVIDIA Jetson platform, and experiments on diverse remote sensing scenes show that the proposed strategy substantially reduces bandwidth consumption while accelerating time-to-insight for time-sensitive missions.

cs.CV↗

arXiv2026

Few-Shot Open-Vocabulary Remote Sensing Segmentation via Textual Inversion

Open-vocabulary segmentation labels arbitrary categories from a text query without per-class training, yet on remote sensing imagery it underperforms on categories it handles reliably elsewhere. We find that much of this gap traces to the text query rather than to the segmentation model. Because these models are not specialized for overhead imagery, the class name that serves as the query is often a weak address into the vision-language embedding space. We show that a better name repairs part of the gap, while the remaining failures call for an address that the tested natural-language rephrasings do not provide. We recover that address from a few examples through textual inversion on a frozen model, keeping inference text only. On a representative benchmark this raises the mean intersection over union on the affected categories from 3.9 to 39.4, and across eight remote sensing datasets it improves over few-shot methods that instead inject visual prompts at inference.

cs.CV↗

arXiv2026

FROST: Training-Free Few-Shot Segmentation with Frozen Features and Nonparametric Statistics

Few-shot segmentation asks a model to delineate a target class in a query image from only a handful of annotated examples, a setting most acute in remote sensing, where labels are scarce and the imagery departs sharply from the natural images on which vision backbones are pretrained. Prevailing approaches either train a segmenter on labelled episodes, which raises accuracy within the training distribution but binds the model to it, or reduce each class to a lossy summary of frozen features, a single prototype, a few cluster prototypes, or a discrete clustering, none of which preserves the internal structure of a multimodal class. We argue that a class is better described by a distribution than by a point, and that frozen self-supervised features already carry enough structure to estimate that distribution directly. We introduce FROST, a training-free few-shot segmenter that treats the reference foreground and background as two point clouds on the unit sphere of frozen DINOv3 features and labels each query token by a nonparametric density ratio, with a threshold the Bayes rule fixes at zero under equal priors. Because the variance of a density estimate shrinks as its sample grows, the decision sharpens as references accumulate, and every remaining quantity from the kernel bandwidth to the spatial gate is read from the support set rather than tuned. We develop FROST for overhead imagery, where a class is typically a scatter of many small and dissimilar instances that a density tracks but a lossy summary blurs. Across seventeen remote-sensing benchmarks FROST surpasses both training-free and learning-based methods, leading by 5.6 mIoU from a single annotated example and widening its lead as the support set grows, all while remaining among the smallest models compared. Code is available at https://github.com/jhpark-ai/FROST.

cs.CV↗

arXiv2026

FLAME: Physics-Guided Neural Operators for Onboard Satellite Methane Detection in Hyperspectral Imagery

Methane is a major driver of near-term climate change, and rapidly identifying its emission sources is a critical climate intervention. Spaceborne hyperspectral imagery is the primary tool for this task, but the volume of data produced by each sensor makes ground-based detection impractical and necessitates onboard detection. Classical methods incur prohibitive computational cost on onboard hardware, while deep learning models are fast but fall short on detection quality. We propose FLAME, a physics-guided neural operator that builds the physics of methane absorption directly into its architecture. On the methane detection benchmark, FLAME achieves the highest detection accuracy among all evaluated methods, reduces the pixel-level false positive rate by nearly $3\times$ over the strongest neural baseline, uses the fewest parameters among learned baselines, and runs within the latency budget of onboard satellite hardware.

cs.CV↗

arXiv2026

Local Knots, $\nu^+$-Sharp Knots, and Rational Slice Genus

Hom and Wu introduced the knot concordance invariant $\nu^{+}$ for knots in $S^{3}$ and proved that it gives a lower bound for the slice genus. Wu and Yang extended $\nu^{+}$ to knots in rational homology $3$-spheres, where it gives a lower bound for the rational slice genus, an analogue of the slice genus for knots in rational homology $3$-spheres. We call a knot $\nu^{+}$-sharp if this bound is realized as an equality. An open question asks whether a local knot in a $3$-manifold $Y$, that is, a knot contained in a $3$-ball, can bound a surface of smaller genus in $Y\times I$ than in $S^{3}\times I$. Using the Heegaard Floer invariant $\nu^+$, we show that this does not occur for local knots arising from $\nu^+$-sharp knots: if $K\subset S^3$ is $\nu^+$-sharp and $Y$ is a rational homology $3$-sphere, then the induced local knot in $Y$ has rational slice genus equal to the slice genus of $K$. The proof proceeds by establishing an additivity result for the rational slice genus.

math.GT↗

arXiv2026

Escaping Spectral Bias without Backpropagation: Fast Implicit Neural Representations with Extreme Learning Machines

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 exhibits highly non-uniform frequency content. We propose ELM-INR, a backpropagation-free INR that decomposes the domain into overlapping subdomains and fits each local problem using an Extreme Learning Machine (ELM) in closed form, replacing iterative optimization with stable linear least-squares solutions. This design yields fast and numerically robust reconstruction by combining local predictors through a partition of unity. To understand where approximation becomes difficult under fixed local capacity, we analyze the method from a spectral Barron norm perspective, which reveals that global reconstruction error is dominated by regions with high spectral complexity. Building on this insight, we introduce BEAM, an adaptive mesh refinement strategy that balances spectral complexity across subdomains to improve reconstruction quality in capacity-constrained regimes.

cs.LG↗

arXiv2025

Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks, incur high training cost, and can be unstable. At the same time, the number of task-specific pre-trained models continues to grow, yet the question of how to transfer them to new tasks with minimal additional training remains relatively underexplored. We propose BOLT (Basis-Oriented Low-rank Transfer), a framework that reuses existing fine-tuned models not by merging weights, but instead by extracting an orthogonal, task-informed spectral basis and adapting within that subspace. In the offline phase, BOLT collects dominant singular directions from multiple task vectors and orthogonalizes them per layer to form reusable bases. In the online phase, we freeze these bases and train only a small set of diagonal coefficients per layer for the new task, yielding a rank-controlled update with very few trainable parameters. This design provides (i) a strong, training-free initialization for unseen tasks, obtained by pooling source-task coefficients, along with a lightweight rescaling step while leveraging the shared orthogonal bases, and (ii) a parameter-efficient fine-tuning (PEFT) path that, in our experiments, achieves robust performance compared to common PEFT baselines as well as a representative meta-learned initialization. Our results show that constraining adaptation to a task-informed orthogonal subspace provides an effective alternative for unseen-task transfer.

cs.CV↗

arXiv2025

PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting

Precipitation nowcasting, key for early warning of disasters, currently relies on computationally expensive and restrictive methods that limit access to many countries. To overcome this challenge, we propose precipitation nowcasting using satellite imagery with physics constraints for improved accuracy and physical consistency. We use a novel physics-informed dual neural operator (PIANO) structure to enforce the fundamental equation of advection-diffusion during training to predict satellite imagery using a PINN loss. Then, we use a generative model to convert satellite images to radar images, which are used for precipitation nowcasting. Compared to baseline models, our proposed model shows a notable improvement in moderate (4mm/h) precipitation event prediction alongside short-term heavy (8mm/h) precipitation event prediction. It also demonstrates low seasonal variability in predictions, indicating robustness for generalization. This study suggests the potential of the PIANO and serves as a good baseline for physics-informed precipitation nowcasting.

cs.LG↗

arXiv2021

Doping effects on the valence bond solid of Li$_{2}$RuO$_{3}$ with Mn substitution

$Li_{2}RuO_{3}$ with a honeycomb structure undergoes a drastic transition from a regular honeycomb lattice with the $C2/m$ space group to a valence bond solid state of the $P2_{1}/m$ space group with an extremely strong dimerization at 550 K. We synthesized $Li_{2}Ru_{1-x}Mn_{x}O_{3}$ with a full solid solution and investigated doping effects on the valence bond solid state as a function of Mn content. The valence bond solid state is found to be stable up to $x = 0.2$, based on our extensive experiments: structural studies, resistivity, and magnetic susceptibility. On the other hand, the extended x-ray absorption fine structure analyses show that the dimer local structure remains robust even above $x = 0.2$ with a minimal effect on the dimer bond length. This indicates that the locally-disordered dimer structure survives well into the Mn-rich phase even though the thermodynamically stable average structure has the $C2/m$ space group. Our results prove that the dimer formation in $Li_{2}RuO_{3}$ is predominantly a local phenomenon driven by the formation of orbitally-assisted metal-metal bonds and that these dimers are relatively robust against doping-induced disorder.

cond-mat.str-el↗

arXiv2019

Magnetic and electrical anisotropy with correlation and orbital effects in dimerized honeycomb ruthenate Li$_2$RuO$_3$

Li2RuO3 undergoes a structural transition at a relatively high temperature of 550 K with a distinct dimerization of Ru-Ru bonds on the otherwise isotropic honeycomb lattice. It exhibits a unique herringbone dimerization pattern with a largest ever reported value of the bond shrinkage of about ~ 0.5 Å. Despite extensive studies, both theoretical and experimental, however, its origin and its effect on physical properties still remain to be understood. In this work, using high quality single crystals we investigated the anisotropy of resistivity ($ρ$) and magnetic susceptibility ($χ$) to find a very clear anisotropy: $ρ$$_c*$ > $ρ$$_b$ > $ρ$$_a$ and $χ$$_b$ > $χ$$_a$ > $χ$$_c*$. For possible theoretical interpretations, we carried out density functional calculations to conclude that these anisotropic behavior is due to the correlation effects combined with the unique orbital structure and the dimerization of Ru 4d bands.

cond-mat.str-el↗

arXiv2016

Robust singlet dimers with fragile ordering in two-dimensional honeycomb lattice of Li$_2$RuO$_3$

When an electronic system has strong correlations and a large spin-orbit interaction, it often exhibits a plethora of mutually competing quantum phases. How a particular quantum ground state is selected out of several possibilities is a very interesting question. However, equally fascinating is how such a quantum entangled state breaks up due to perturbation. This important question has relevance in very diverse fields of science from strongly correlated electron physics to quantum information. Here we report that a quantum entangled dimerized state or valence bond crystal (VBC) phase of Li2RuO3 shows nontrivial doping dependence as we perturb the Ru honeycomb lattice by replacing Ru with Li. Through extensive experimental studies, we demonstrate that the VBC phase melts into a valence bond liquid phase of the RVB (resonating valence bond) type. This system offers an interesting playground where one can test and refine our current understanding of the quantum competing phases in a single compound.

cond-mat.str-el↗

arXiv2014

Experimental percolation studies of two-dimensional honeycomb lattice: Li2Mn1-xTixO3

Li2MnO3 with a S=3/2 two-dimensional Mn honeycomb lattice has a Neel-type antiferromagnetic transition at TN=36 K with a broad maximum in the magnetic susceptibility at TM=48 K. We have investigated site percolation effects by replacing Mn with nonmagnetic Ti, and completed a full phase diagram of Li2Mn1-xTixO3 solid solution systems to find that the antiferromagnetic transition is suppressed continuously without a clear sign of changes in the Neel-type antiferromagnetic structure. The magnetic ordering eventually disappears at a critical concentration of xc=0.7. This experimental observation is consistent with percolation theories for a honeycomb lattice when one considers up to 3rd nearest-neighbor interactions. This study highlights the importance of interaction beyond nearest neighbors even for Mn element with relative localized 3d electrons in the honeycomb lattice.

cond-mat.str-el↗

arXiv2013

Negative magnetostrictive magnetoelectric coupling of BiFeO3

How the magnetoelectric coupling actually occurs on a microscopic level in multiferroic BiFeO3 is not well known. By using the high-resolution single crystal neutron diffraction techniques, we have determined the electric polarization of each individual elements of BiFeO3, and concluded that the magnetostrictive coupling suppresses the electric polarization at the Fe site below TN. This negative magnetoelectric coupling appears to outweigh the spin current contributions arising from the cycloid spin structure, which should produce a positive magnetoelectric coupling.

cond-mat.str-el↗

arXiv1999

Photoemission Study of Rare-Earth Ditelluride Compounds (ReTe_2 : Re = La, Pr, Sm, and Gd)

We studied the electronic structure of rare-earth ditelluride (ReTe_2 : Re = La, Pr, Sm, and Gd) using photoemission spectroscopy. From the x-ray photoelectron spectroscopy (XPS) study of the 3d core levels of rare-earth elements, we found that all the rare earth elements are trivalent. We have also made theoretical calculations using the Gunnarsson and Schoenhammer approximation and multiplet calculations for the rare earth elements to find that the La and Gd~3d peaks are well explained using our calculations. There is no considerable change in the line-shape of the Te~3d peaks depending on different rare earth elements. On ther other hand, valence band spectra studied with the ultraviolet photoelectron spectroscopy (UPS) show a small change in the Te p band depending on rare-earth elements. According to the UPS data, LaTe_2 has very low carrier density at the Fermi level while SmTe_2 and PrTe_2 show strongly metallic band structure effects near the Fermi level.

cond-mat.str-el↗