Source author record

Minjun Kim

Minjun Kim appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence astro-ph.HE Computation and Language eess.IV Machine Learning Social and Information Networks

Catalog footprint

What is connected

5works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

preprint2026arXiv

A Target-Free Harmonization Method for MRI

In MRI, variations in scan parameters, sequence, or hardware can lead to discrepancies in image appearance, even for the same subject. These inconsistencies, known as domain shifts, can hinder image analysis and degrade the performance of deep learning models trained on data from specific target domains. MRI image harmonization aims to address these issues by aligning source domain images to the target domain images while preserving biological information such as anatomical structures. However, most existing harmonization approaches require access to both source and target domain data in training or test time. This dependence induces data sharing between institutions, raising concerns about patient privacy and substantially limiting the harmonization approaches that can be practically deployed in clinical settings. To overcome these limitations, we introduce TgtFreeHarmony, the harmonization framework tailored for target-free scenarios, eliminating the need for target domain data and any data sharing, enabling privacy-preserving harmonization directly within the source institution. Our approach estimates the target domain style by searching the manifold of MRI domain style constructed via a disentanglement-based generator using Bayesian optimization guided by the performance of a downstream task model, which is trained on target domain data. We evaluated our method on the brain tissue segmentation task across multiple institutes and demonstrated that it effectively harmonizes source images into target images, leading to improved downstream task performance. By enabling harmonization without any access to target-domain data, TgtFreeHarmony establishes a new direction of harmonization preserving data privacy that can be realistically deployed within clinical environments.

preprint2026arXiv

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.

preprint2022arXiv

Neuro CROSS exchange: Learning to CROSS exchange to solve realistic vehicle routing problems

CROSS exchange (CE), a meta-heuristic that solves various vehicle routing problems (VRPs), improves the solutions of VRPs by swapping the sub-tours of the vehicles. Inspired by CE, we propose Neuro CE (NCE), a fundamental operator of learned meta-heuristic, to solve various VRPs while overcoming the limitations of CE (i.e., the expensive $\mathcal{O}(n^4)$ search cost). NCE employs a graph neural network to predict the cost-decrements (i.e., results of CE searches) and utilizes the predicted cost-decrements as guidance for search to decrease the search cost to $\mathcal{O}(n^2)$. As the learning objective of NCE is to predict the cost-decrement, the training can be simply done in a supervised fashion, whose training samples can be prepared effortlessly. Despite the simplicity of NCE, numerical results show that the NCE trained with flexible multi-depot VRP (FMDVRP) outperforms the meta-heuristic baselines. More importantly, it significantly outperforms the neural baselines when solving distinctive special cases of FMDVRP (e.g., MDVRP, mTSP, CVRP) without additional training.

preprint2022arXiv

Visualizing Collective Idea Generation and Innovation Processes in Social Networks

Collective idea generation and innovation processes are complex and dynamic, involving a large amount of qualitative narrative information that is difficult to monitor, analyze, and visualize using traditional methods. In this study, we developed three new visualization methods for collective idea generation and innovation processes and applied them to data from online social network experiments. The first visualization is the Idea Cloud, which helps monitor collective idea posting activity and intuitively tracks idea clustering and transition. The second visualization is the Idea Geography, which helps understand how the idea space and its utility landscape are structured and how collaboration was performed in that space. The third visualization is the Idea Network, which connects idea dynamics with the social structure of the people who generated them, displaying how social influence among neighbors may have affected collaborative activities and where innovative ideas arose and spread in the social network.

preprint2020arXiv

Characterizing X-ray properties of the gamma-ray pulsar PSR J1418$-$6058 in the Rabbit pulsar wind nebula

We report on X-ray studies of the gamma-ray pulsar PSR J1418$-$6058 in the Rabbit pulsar wind nebula (PWN) carried out using archival Chandra and XMM-Newton observations. A refined timing analysis performed with the 120-ks XMM-Newton data finds significant ($p\approx10^{-7}$) pulsation at $P\approx110$ ms which is consistent with that measured with the Fermi large area telescope (LAT). In the Chandra image, we find extended emission around the pulsar similar to those seen around other pulsars in young PWNe, which further argues for association between PSR J1418$-$6058 and the Rabbit PWN. The X-ray spectrum of the pulsar is hard and similar to those of soft-gamma pulsars. Hence PSR J1418$-$6058 may add to the list of soft-gamma pulsars.