BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Minseok Kim

Minseok Kim contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
cond-mat.str-elMachine LearningArtificial IntelligenceInformation Retrievalphysics.opticsComputer Visioncond-mat.mtrl-scicond-mat.supr-coneess.ASGraphicsmath.NAmath.OCphysics.app-phphysics.chem-phphysics.ins-detquant-phSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
11works
0followers
17topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

11 published item(s)

preprint2026arXiv

Stabilized neural Hamilton--Jacobi--Bellman solvers: Error analysis and applications in model-based reinforcement learning

Physics-informed neural solvers offer a promising route to model-based reinforcement learning in continuous time, where optimal feedback synthesis is governed by Hamilton--Jacobi--Bellman (HJB) equations. Practical implementations often occupy a regime that is neither a classical grid method nor a continuous-PDE PINN: the value function is represented by a neural network, finite-difference HJB policy-evaluation operators are evaluated by network queries at shifted points, and residuals are minimized by random continuous collocation. This regime preserves the stabilized finite-difference policy-evaluation structure while avoiding grid-based value unknowns. We develop an error theory for this hybrid regime. Interpreting finite differences as shift operators acting on neural networks, we prove a population $L^2$ stability estimate for one policy-evaluation step with learned dynamics. The bound separates residual error, initial and exterior-collar mismatch, policy mismatch, and model-identification error, with an explicit gradient amplification factor for learned dynamics, while the underlying linear evaluation stability remains free of hidden inverse-viscosity blow-up. We further give a finite-sample collocation certificate and a conditional multi-step propagation result through greedy policy improvement. Experiments on compact-control LQR upto 64 dimensions, Allen--Cahn control, pendulum, Hopper, and 3D quadrotor benchmarks compare against representative model-based and model-free RL baselines, demonstrating the predicted residual, policy-mismatch, and learned-model error trends.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems

Graph neural networks (GNNs) have achieved remarkable success in recommender systems by representing users and items based on their historical interactions. However, little attention was paid to GNN's vulnerability to exposure bias: users are exposed to a limited number of items so that a system only learns a biased view of user preference to result in suboptimal recommendation quality. Although inverse propensity weighting is known to recognize and alleviate exposure bias, it usually works on the final objective with the model outputs, whereas GNN can also be biased during neighbor aggregation. In this paper, we propose a simple but effective approach, neighbor aggregation via inverse propensity (Navip) for GNNs. Specifically, given a user-item bipartite graph, we first derive propensity score of each user-item interaction in the graph. Then, inverse of the propensity score with Laplacian normalization is applied to debias neighbor aggregation from exposure bias. We validate the effectiveness of our approach through our extensive experiments on two public and Amazon Alexa datasets where the performance enhances up to 14.2%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning from Noisy Labels with Deep Neural Networks: A Survey

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies. All the contents will be available at https://github.com/songhwanjun/Awesome-Noisy-Labels.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Meta-Learning for Online Update of Recommender Systems

Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over time, the update strategy should be flexible to quickly catch users' current interest from continuously generated new user-item interactions. Existing update strategies focus either on the importance of each user-item interaction or the learning rate for each recommender parameter, but such one-directional flexibility is insufficient to adapt to varying relationships between interactions and parameters. In this paper, we propose MeLON, a meta-learning based novel online recommender update strategy that supports two-directional flexibility. It is featured with an adaptive learning rate for each parameter-interaction pair for inducing a recommender to quickly learn users' up-to-date interest. The procedure of MeLON is optimized following a meta-learning approach: it learns how a recommender learns to generate the optimal learning rates for future updates. Specifically, MeLON first enriches the meaning of each interaction based on previous interactions and identifies the role of each parameter for the interaction; and then combines these two pieces of information to generate an adaptive learning rate. Theoretical analysis and extensive evaluation on three real-world online recommender datasets validate the effectiveness of MeLON.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Music Demixing Challenge 2021

Music source separation has been intensively studied in the last decade and tremendous progress with the advent of deep learning could be observed. Evaluation campaigns such as MIREX or SiSEC connected state-of-the-art models and corresponding papers, which can help researchers integrate the best practices into their models. In recent years, the widely used MUSDB18 dataset played an important role in measuring the performance of music source separation. While the dataset made a considerable contribution to the advancement of the field, it is also subject to several biases resulting from a focus on Western pop music and a limited number of mixing engineers being involved. To address these issues, we designed the Music Demixing (MDX) Challenge on a crowd-based machine learning competition platform where the task is to separate stereo songs into four instrument stems (Vocals, Drums, Bass, Other). The main differences compared with the past challenges are 1) the competition is designed to more easily allow machine learning practitioners from other disciplines to participate, 2) evaluation is done on a hidden test set created by music professionals dedicated exclusively to the challenge to assure the transparency of the challenge, i.e., the test set is not accessible from anyone except the challenge organizers, and 3) the dataset provides a wider range of music genres and involved a greater number of mixing engineers. In this paper, we provide the details of the datasets, baselines, evaluation metrics, evaluation results, and technical challenges for future competitions.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Functionality-Driven Musculature Retargeting

We present a novel retargeting algorithm that transfers the musculature of a reference anatomical model to new bodies with different sizes, body proportions, muscle capability, and joint range of motion while preserving the functionality of the original musculature as closely as possible. The geometric configuration and physiological parameters of musculotendon units are estimated and optimized to adapt to new bodies. The range of motion around joints is estimated from a motion capture dataset and edited further for individual models. The retargeted model is simulation-ready, so we can physically simulate muscle-actuated motor skills with the model. Our system is capable of generating a wide variety of anatomical bodies that can be simulated to walk, run, jump and dance while maintaining balance under gravity. We will also demonstrate the construction of individualized musculoskeletal models from bi-planar X-ray images and medical examinations.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Optical excitation of electromagnons in hexaferrite

Understanding ultrafast magnetization dynamics on the microscopic level is of strong current interest due to the potential for applications in information storage. In recent years, the spin-lattice coupling has been recognized to be essential for ultrafast magnetization dynamics. Magnetoelectric multiferroics of type II possess intrinsic correlations among magnetic sublattices and electric polarization (P) through spin-lattice coupling, enabling fundamentally coupled dynamics between spins and lattice. Here we report on ultrafast magnetization dynamics in a room-temperature multiferroic hexaferrite possessing ferrimagnetic and antiferromagnetic sublattices, revealed by time-resolved resonant x-ray diffraction. A femtosecond above-bandgap excitation triggers a coherent magnon in which the two magnetic sublattices entangle and give rise to a transient modulation of P. A novel microscopic mechanism for triggering the coherent magnon in this ferrimagnetic insulator based on the spin-lattice coupling is proposed. Our finding opens up a novel but general pathway for ultrafast control of magnetism.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Ultrafast renormalization of the onsite Coulomb repulsion in a cuprate superconductor

Ultrafast lasers are an increasingly important tool to control and stabilize emergent phases in quantum materials. Among a variety of possible excitation protocols, a particularly intriguing route is the direct light-engineering of microscopic electronic parameters, such as the electron hopping and the local Coulomb repulsion (Hubbard $U$). In this work, we use time-resolved x-ray absorption spectroscopy to demonstrate the light-induced renormalization of the Hubbard $U$ in a cuprate superconductor, La$_{1.905}$Ba$_{0.095}$CuO$_4$. We show that intense femtosecond laser pulses induce a substantial redshift of the upper Hubbard band, while leaving the Zhang-Rice singlet energy unaffected. By comparing the experimental data to time-dependent spectra of single- and three-band Hubbard models, we assign this effect to a $\sim140$ meV reduction of the onsite Coulomb repulsion on the copper sites. Our demonstration of a dynamical Hubbard $U$ renormalization in a copper oxide paves the way to a novel strategy for the manipulation of superconductivity, magnetism, as well as to the realization of other long-range-ordered phases in light-driven quantum materials.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Design and experimental demonstration of impedance-matched circular polarization selective surfaces with spin-selective phase modulations

This paper presents the design and experimental demonstration of an impedance-matched circular polarization selective surface which also offers spin-selective phase modulations at microwave frequencies. We achieve this by leveraging the theory of Pancharatnam-Berry phase and cascading four tensor impedance layers, each comprising an array of crossed meander lines. These meander lines are precisely tuned and rotated to implement particular tensor surface impedance values to satisfy the impedance-matching condition for the transmitted right-handed circularly-polarized field while inducing Pancharatnam-Berry phase shift for the reflected left-handed circularly-polarized field. We present a detailed numerical synthesis technique to obtain the required impedance values for satisfying the impedance matching condition, and demonstrate spin-selective phase modulations based on Pancharatnam-Berry phase shifts. To verify the proposed idea, we experimentally demonstrate nearly-reflectionless transmission of right-handed circular polarization at broadside and reflection of left-handed circular polarization at 30 degrees off broadside at 12 GHz. For this purpose, a free-space quasi-optical set up and a near-field measurement system are respectively employed for measuring the transmitted and reflected circularly-polarized fields.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

How does Early Stopping Help Generalization against Label Noise?

Noisy labels are very common in real-world training data, which lead to poor generalization on test data because of overfitting to the noisy labels. In this paper, we claim that such overfitting can be avoided by "early stopping" training a deep neural network before the noisy labels are severely memorized. Then, we resume training the early stopped network using a "maximal safe set," which maintains a collection of almost certainly true-labeled samples at each epoch since the early stop point. Putting them all together, our novel two-phase training method, called Prestopping, realizes noise-free training under any type of label noise for practical use. Extensive experiments using four image benchmark data sets verify that our method significantly outperforms four state-of-the-art methods in test error by 0.4-8.2 percent points under existence of real-world noise.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Time-resolved resonant elastic soft X-ray scattering at Pohang Accelerator Laboratory X-ray Free Electron Laser

Resonant elastic X-ray scattering has been widely employed for exploring complex electronic ordering phenomena, like charge, spin, and orbital order, in particular in strongly correlated electronic systems. In addition, recent developments of pump-probe X-ray scattering allow us to expand the investigation of the temporal dynamics of such orders. Here, we introduce a new time-resolved Resonant Soft X-ray Scattering (tr-RSXS) endstation developed at the Pohang Accelerator Laboratory X-ray Free Electron Laser (PAL-XFEL). This endstation has an optical laser (wavelength of 800 nm plus harmonics) as the pump source. Based on the commissioning results, the tr-RSXS at PAL-XFEL can deliver a soft X-ray probe (400-1300 eV) with a time resolution about ~100 fs without jitter correction. As an example, the temporal dynamics of a charge density wave on a high-temperature cuprate superconductor is demonstrated.

0 citations0 reviewsNo code linkedOpen access