arXiv subjects

Jiyoung Kim

Publications and source records attributed to Jiyoung Kim.

At least 19 recordsLinked to original sources

arXiv2026

Development and demonstration of the Korea ALICE Telescope using electron beams at KEK PF-AR

The development of ultra-low-mass, high-precision vertex detectors is a key requirement for future collider experiments and motivates extensive research and development of novel silicon tracking technologies. In this work, we present the development and beam-test demonstration of the Korea ALICE Telescope (KATS), a silicon-tracking telescope designed to support R&D on next-generation cylindrical vertex detectors, such as the proposed ALICE ITS3 upgrade. The telescope consists of six ALPIDE Monolithic Active Pixel Sensors (MAPS) used as reference tracking planes, a bent ALPIDE sensor serving as the device under test, and a scintillating-fiber-based trigger system, all housed in a light-tight modular enclosure. This setup enables precise track reconstruction and detailed performance studies of both planar and curved silicon sensors. Beam tests were carried out using high-energy electron beams at the KEK Photon Factory Advanced Ring (PF-AR). The telescope system operated stably under realistic beam conditions, and its tracking performance was successfully validated. The bent ALPIDE sensor was operated at a bending radius of approximately 18 mm, consistent with ITS3's design goals, without any observable degradation in detection performance. The measured results confirm that the KATS provides a versatile and reliable platform for studies of curved MAPS technologies, alignment precision, and tracking performance. These results provide important experimental validation of key technologies for future low-mass cylindrical silicon vertex detectors and establish KATS as a valuable facility for ongoing and future detector R&D.

physics.ins-det↗

arXiv2026

A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis

Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional investigations. However, SEM imaging remains constrained by task-specific models and labor-intensive acquisition processes that limit its scalability across diverse applications. Here, we introduce the first foundation model for SEM images, pretrained on a large corpus of multi-instrument, multi-condition scientific micrographs, enabling generalization across diverse material systems and imaging conditions. Leveraging a self-supervised transformer architecture, our model learns rich and transferable representations that can be fine-tuned or adapted to a wide range of downstream tasks. As a compelling demonstration, we focus on defocus-to-focus image translation-an essential yet underexplored challenge in automated microscopy pipelines. Our method not only restores focused detail from defocused inputs without paired supervision but also outperforms state-of-the-art techniques across multiple evaluation metrics. This work lays the groundwork for a new class of adaptable SEM models, accelerating materials discovery by bridging foundational representation learning with real-world imaging needs.

cs.LG↗

arXiv2026

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.

cs.CV↗

arXiv2026

Anomalous Thermal Transport Reveals Weak First-Order Melting of Charge Density Waves in 2H-TaSe2

How ordered phases melt in low-dimensional quantum materials remain difficult to resolve because the relevant fluctuations are dynamic and charge neutral. In this work, we show that thermal transport provides a sensitive probe of these hidden fluctuations in the layered transition metal dichalcogenide 2H-TaSe2. We observe a striking V-shaped temperature dependence of the thermal conductivity that cannot be explained by conventional phonon-phonon scattering. Instead, it originates from scattering by persistent local charge-density-wave (CDW) correlations, consistent with our phenomenological model linking thermal transport to spatial CDW fluctuation. Electron diffraction reveals short-range periodic lattice distortions persisting to at least 300 K, while X-ray diffraction shows thermal hysteresis of the CDW wavevector. Together, these results reveal a dislocation- and fluctuation-driven weak first-order melting of the CDW state.

cond-mat.str-el↗

arXiv2026

CORAL: Correspondence Alignment for Improved Virtual Try-On

Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required. These methods do not explicitly enforce person-garment alignment and fail to explain how correspondence emerges within Diffusion Transformers (DiTs). In this paper, we first analyze full 3D attention in DiT-based architecture and reveal that the person-garment correspondence critically depends on precise person-garment query-key matching within the full 3D attention. Building on this insight, we then introduce CORrespondence ALignment (CORAL), a DiT-based framework that explicitly aligns query-key matching with robust external correspondences. CORAL integrates two complementary components: a correspondence distillation loss that aligns reliable matches with person-garment attention, and an entropy minimization loss that sharpens the attention distribution. We further propose a VLM-based evaluation protocol to better reflect human preference. CORAL consistently improves over the baseline, enhancing both global shape transfer and local detail preservation. Extensive ablations validate our design choices.

cs.CV↗

arXiv2025

Characterisation of the first wafer-scale prototype for the ALICE ITS3 upgrade: the monolithic stitched sensor (MOSS)

This paper presents the characterisation and testing of the first wafer-scale monolithic stitched sensor (MOSS) prototype developed for the ALICE ITS3 upgrade that is to be installed during the LHC Long Shutdown 3 (2026-2030). The MOSS chip design is driven by the truly cylindrical detector geometry that imposes that each layer is built out of two wafer-sized, bent silicon chips. The stitching technique is employed to fabricate sensors with dimensions of 1.4 $\times$ 25.9 cm, thinned to 50 $\mu$m. The chip architecture, in-pixel front-end, laboratory and in-beam characterisation, susceptibility to single-event effects, and series testing are discussed. The testing campaign validates the design of a wafer-scale stitched sensor and the performance of the pixel matrix to be within the ITS3 requirements. The MOSS chip demonstrates the feasibility of the ITS3 detector concept and provides insights for further optimisation and development.

physics.ins-det↗

arXiv2025

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.

cs.CV↗

arXiv2025

Emergent Temporal Correspondences from Video Diffusion Transformers

Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish and represent temporal correspondences across frames? We introduce DiffTrack, the first quantitative analysis framework designed to answer this question. DiffTrack constructs a dataset of prompt-generated video with pseudo ground-truth tracking annotations and proposes novel evaluation metrics to systematically analyze how each component within the full 3D attention mechanism of DiTs (e.g., representations, layers, and timesteps) contributes to establishing temporal correspondences. Our analysis reveals that query-key similarities in specific, but not all, layers play a critical role in temporal matching, and that this matching becomes increasingly prominent during the denoising process. We demonstrate practical applications of DiffTrack in zero-shot point tracking, where it achieves state-of-the-art performance compared to existing vision foundation and self-supervised video models. Further, we extend our findings to motion-enhanced video generation with a novel guidance method that improves temporal consistency of generated videos without additional training. We believe our work offers crucial insights into the inner workings of video DiTs and establishes a foundation for further research and applications leveraging their temporal understanding.

cs.CV↗

arXiv2025

K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean

Language detoxification involves removing toxicity from offensive language. While a neutral-toxic paired dataset provides a straightforward approach for training detoxification models, creating such datasets presents several challenges: i) the need for human annotation to build paired data, and ii) the rapid evolution of offensive terms, rendering static datasets quickly outdated. To tackle these challenges, we introduce an automated paired data generation pipeline, called K/DA. This pipeline is designed to generate offensive language with implicit offensiveness and trend-aligned slang, making the resulting dataset suitable for detoxification model training. We demonstrate that the dataset generated by K/DA exhibits high pair consistency and greater implicit offensiveness compared to existing Korean datasets, and also demonstrates applicability to other languages. Furthermore, it enables effective training of a high-performing detoxification model with simple instruction fine-tuning.

cs.CL↗

arXiv2025

Surface-dominant transport in Weyl semimetal NbAs nanowires for next-generation interconnects

Ongoing demands for smaller and more energy efficient electronic devices necessitate alternative interconnect materials with lower electrical resistivity at reduced dimensions. Despite the emergence of many promising candidates, synthesizing high quality nanostructures remains a major bottleneck in evaluating their performance. Here, we report the successful synthesis of Weyl semimetal NbAs nanowires via thermomechanical nanomolding, achieving single crystallinity and controlled diameters as small as 40 nm. Our NbAs nanowires exhibit a remarkably low room-temperature resistivity of 9.7 +/- 1.6 microOhm-cm, which is three to four times lower than their bulk counterpart. Theoretical calculations corroborate the experimental observations, attributing this exceptional resistivity reduction to surface dominant conduction with long carrier lifetime at finite temperatures. Further characterization of NbAs nanowires and bulk single crystals reveals high breakdown current density, robust stability, and superior thermal conductivity. Collectively, these properties highlight the strong potential of NbAs nanowires as next-generation interconnects, which can surpass the limitations of current copper-based interconnects. Technologically, our findings present a practical application of topological materials, while scientifically showcasing the fundamental properties uniquely accessible in nanoscale platforms.

cond-mat.mes-hall↗

arXiv2024

MT3DNet: Multi-Task learning Network for 3D Surgical Scene Reconstruction

In image-assisted minimally invasive surgeries (MIS), understanding surgical scenes is vital for real-time feedback to surgeons, skill evaluation, and improving outcomes through collaborative human-robot procedures. Within this context, the challenge lies in accurately detecting, segmenting, and estimating the depth of surgical scenes depicted in high-resolution images, while simultaneously reconstructing the scene in 3D and providing segmentation of surgical instruments along with detection labels for each instrument. To address this challenge, a novel Multi-Task Learning (MTL) network is proposed for performing these tasks concurrently. A key aspect of this approach involves overcoming the optimization hurdles associated with handling multiple tasks concurrently by integrating a Adversarial Weight Update into the MTL framework, the proposed MTL model achieves 3D reconstruction through the integration of segmentation, depth estimation, and object detection, thereby enhancing the understanding of surgical scenes, which marks a significant advancement compared to existing studies that lack 3D capabilities. Comprehensive experiments on the EndoVis2018 benchmark dataset underscore the adeptness of the model in efficiently addressing all three tasks, demonstrating the efficacy of the proposed techniques.

cs.CV↗

arXiv2024

Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild

Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like ControlNet, are limited as they rely solely on text prompts to control appearance and cannot utilize exemplar images as input. Recent tuning-free approaches address this by transferring local appearance via implicit cross-image matching in the augmented self-attention mechanism of pre-trained diffusion models. However, prior works are often restricted to single-object cases or foreground object appearance transfer, struggling with complex scenes involving multiple objects. To overcome this, we propose AM-Adapter (Appearance Matching Adapter) to address exemplar-based semantic image synthesis in-the-wild, enabling multi-object appearance transfer from a single scene-level image. AM-Adapter automatically transfers local appearances from the scene-level input. AM-Adapter alternatively provides controllability to map user-defined object details to specific locations in the synthesized images. Our learnable framework enhances cross-image matching within augmented self-attention by integrating semantic information from segmentation maps. To disentangle generation and matching, we adopt stage-wise training. We first train the structure-guidance and generation networks, followed by training the matching adapter while keeping the others frozen. During inference, we introduce an automated exemplar retrieval method for selecting exemplar image-segmentation pairs efficiently. Despite utilizing minimal learnable parameters, AM-Adapter achieves state-of-the-art performance, excelling in both semantic alignment and local appearance fidelity. Extensive ablations validate our design choices. Code and weights will be released.: https://cvlab-kaist.github.io/AM-Adapter/

cs.CV↗

arXiv2024

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aimed to address these limitations and improve fidelity. However, they still face challenges, including extensive sampling times and difficulties in maintaining temporal consistency due to the high stochasticity of diffusion models. To overcome these challenges, we propose a novel motion-disentangled diffusion model for high-quality talking head generation, dubbed MoDiTalker. We introduce the two modules: audio-to-motion (AToM), designed to generate a synchronized lip motion from audio, and motion-to-video (MToV), designed to produce high-quality head video following the generated motion. AToM excels in capturing subtle lip movements by leveraging an audio attention mechanism. In addition, MToV enhances temporal consistency by leveraging an efficient tri-plane representation. Our experiments conducted on standard benchmarks demonstrate that our model achieves superior performance compared to existing models. We also provide comprehensive ablation studies and user study results.

cs.CV↗

arXiv2024

Characterisation of analogue Monolithic Active Pixel Sensor test structures implemented in a 65 nm CMOS imaging process

Analogue test structures were fabricated using the Tower Partners Semiconductor Co. CMOS 65 nm ISC process. The purpose was to characterise and qualify this process and to optimise the sensor for the next generation of Monolithic Active Pixels Sensors for high-energy physics. The technology was explored in several variants which differed by: doping levels, pixel geometries and pixel pitches (10-25 $μ$m). These variants have been tested following exposure to varying levels of irradiation up to 3 MGy and $10^{16}$ 1 MeV n$_\text{eq}$ cm$^{-2}$. Here the results from prototypes that feature direct analogue output of a 4$\times$4 pixel matrix are reported, allowing the systematic and detailed study of charge collection properties. Measurements were taken both using $^{55}$Fe X-ray sources and in beam tests using minimum ionizing particles. The results not only demonstrate the feasibility of using this technology for particle detection but also serve as a reference for future applications and optimisations.

physics.ins-det↗

arXiv2023

Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization

Unsupervised semantic segmentation (USS) aims to discover and recognize meaningful categories without any labels. For a successful USS, two key abilities are required: 1) information compression and 2) clustering capability. Previous methods have relied on feature dimension reduction for information compression, however, this approach may hinder the process of clustering. In this paper, we propose a novel USS framework called Expand-and-Quantize Unsupervised Semantic Segmentation (EQUSS), which combines the benefits of high-dimensional spaces for better clustering and product quantization for effective information compression. Our extensive experiments demonstrate that EQUSS achieves state-of-the-art results on three standard benchmarks. In addition, we analyze the entropy of USS features, which is the first step towards understanding USS from the perspective of information theory.

cs.CV↗

arXiv2023

Depth-Relative Self Attention for Monocular Depth Estimation

Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints are overly exploited, the network can be biased on RGB information without considering the comprehensive view. We propose a novel depth estimation model named RElative Depth Transformer (RED-T) that uses relative depth as guidance in self-attention. Specifically, the model assigns high attention weights to pixels of close depth and low attention weights to pixels of distant depth. As a result, the features of similar depth can become more likely to each other and thus less prone to misused visual hints. We show that the proposed model achieves competitive results in monocular depth estimation benchmarks and is less biased to RGB information. In addition, we propose a novel monocular depth estimation benchmark that limits the observable depth range during training in order to evaluate the robustness of the model for unseen depths.

cs.CV↗

arXiv2022

Towards Intelligent Millimeter and Terahertz Communication for 6G: Computer Vision-aided Beamforming

Beamforming technique realized by the multiple-input-multiple-output (MIMO) antenna arrays has been widely used to compensate for the severe path loss in the millimeter wave (mmWave) bands. In 5G NR system, the beam sweeping and beam refinement are employed to find out the best beam codeword aligned to the mobile. Due to the complicated handshaking and finite resolution of the codebook, today's 5G-based beam management strategy is ineffective in various scenarios in terms of the data rate, energy consumption, and also processing latency. An aim of this article is to introduce a new type of beam management framework based on the computer vision (CV) technique. In this framework referred to as computer vision-aided beam management (CVBM), a camera attached to the BS captures the image and then the deep learning-based object detector identifies the 3D location of the mobile. Since the base station can directly set the beam direction without codebook quantization and feedback delay, CVBM achieves the significant beamforming gain and latency reduction. Using the specially designed dataset called Vision Objects for Beam Management (VOBEM), we demonstrate that CVBM achieves more than 40% improvement in the beamforming gain and 40% reduction in the beam training overhead over the 5G NR beam management.

eess.SP↗

arXiv2022

A phase field model combined with genetic algorithm for polycrystalline hafnium zirconium oxide ferroelectrics

Ferroelectric hafnium zirconium oxide (HZO) thin films show significant promise for applications in ferroelectric random-access memory, ferroelectric field-effect transistors, and ferroelectric tunneling junctions. However, there are shortcomings in understanding ferroelectric switching, which is crucial in the operation of these devices. Here a computational model based on phase field method is developed to simulate the switching behavior of polycrystalline HZO thin films. Furthermore, we introduce a novel approach to optimize the effective Landau coefficients describing the free energy of HZO by combining the phase field model with a genetic algorithm. We validate the model by accurately simulating switching curves for HZO thin films with different ferroelectric phase fractions. The simulated domain dynamics during switching also shows amazing similarity to the available experimental observations. The present work also provides fundamental insights into enhancing the ferroelectricity in HZO thin films by controlling grain morphology and crystalline texture. It can potentially be extended to improve the ferroelectric properties of other hafnia based thin films.

cond-mat.mtrl-sci↗