arXiv subjects

Sanghoon Lee

Publications and source records attributed to Sanghoon Lee.

At least 37 records · Page 2Linked to original sources

arXiv2025

Rigidity of the gradient estimate for Einstein manifolds

We study the rigidity of Ricci-flat manifolds with quadratic curvature decay under conditions on the Green function. We show that if the gradient of the Green function is uniformly bounded from below, then the manifold is flat. Furthermore, we prove that for a Ricci-flat manifold with quadratic curvature decay and Euclidean volume growth, the curvature is in $L^p$ for any $p \ge 2$. Combining with Cheeger-Tian \cite{CT} and Kröncke-Szabó \cite{KS}, we obtain that the manifold must be ALE of optimal order.

math.DG↗

arXiv2025

Semantic BIM enrichment for firefighting assets: Fire-ART dataset and panoramic image-based 3D reconstruction

Inventory management of firefighting assets is crucial for emergency preparedness, risk assessment, and on-site fire response. However, conventional methods are inefficient due to limited capabilities in automated asset recognition and reconstruction. To address the challenge, this research introduces the Fire-ART dataset and develops a panoramic image-based reconstruction approach for semantic enrichment of firefighting assets into BIM models. The Fire-ART dataset covers 15 fundamental assets, comprising 2,626 images and 6,627 instances, making it an extensive and publicly accessible dataset for asset recognition. In addition, the reconstruction approach integrates modified cube-map conversion and radius-based spherical camera projection to enhance recognition and localization accuracy. Through validations with two real-world case studies, the proposed approach achieves F1-scores of 73% and 88% and localization errors of 0.620 and 0.428 meters, respectively. The Fire-ART dataset and the reconstruction approach offer valuable resources and robust technical solutions to enhance the accurate digital management of fire safety equipment.

cs.CV↗

arXiv2025

Dependency Chain Analysis of ROS 2 DDS QoS Policies: From Lifecycle Tutorial to Static Verification

Robot Operating System 2 (ROS 2) relies on the Data Distribution Service (DDS), which offers more than 20 Quality of Service (QoS) policies governing availability, reliability, and resource usage. Yet ROS 2 users lack clear guidance on safe policy combinations and validation processes prior to deployment, which often leads to trial-and-error tuning and unexpected runtime failures. To address these challenges, we analyze DDS Publisher-Subscriber communication over a life cycle divided into Discovery, Data Exchange, and Disassociation, and provide a user oriented tutorial explaining how 16 QoS policies operate in each phase. Building on this analysis, we derive a QoS dependency chain that formalizes inter-policy relationships and classifies 41 dependency violation rules, capturing constraints that commonly cause communication failures in practice. Finally, we introduce QoS Guard, a ROS 2 package that statically validates DDS XML profiles offline, flags conflicts, and enables safe, predeployment tuning without establishing a live ROS 2 session. Together, these contributions give ROS 2 users both conceptual insight and a concrete tool that enables early detection of misconfigurations, improving the reliability and resource efficiency of ROS 2 based robotic systems.

cs.NI↗

arXiv2025

Optimizing ROS 2 Communication for Wireless Robotic Systems

Wireless transmission of large payloads, such as high-resolution images and LiDAR point clouds, is a major bottleneck in ROS 2, the leading open-source robotics middleware. The default Data Distribution Service (DDS) communication stack in ROS 2 exhibits significant performance degradation over lossy wireless links. Despite the widespread use of ROS 2, the underlying causes of these wireless communication challenges remain unexplored. In this paper, we present the first in-depth network-layer analysis of ROS 2's DDS stack under wireless conditions with large payloads. We identify the following three key issues: excessive IP fragmentation, inefficient retransmission timing, and congestive buffer bursts. To address these issues, we propose a lightweight and fully compatible DDS optimization framework that tunes communication parameters based on link and payload characteristics. Our solution can be seamlessly applied through the standard ROS 2 application interface via simple XML-based QoS configuration, requiring no protocol modifications, no additional components, and virtually no integration efforts. Extensive experiments across various wireless scenarios demonstrate that our framework successfully delivers large payloads in conditions where existing DDS modes fail, while maintaining low end-to-end latency.

cs.NI↗

arXiv2025

Probabilistic Latency Analysis of the Data Distribution Service in ROS 2

Robot Operating System 2 (ROS 2) is now the de facto standard for robotic communication, pairing UDP transport with the Data Distribution Service (DDS) publish-subscribe middleware. DDS achieves reliability through periodic heartbeats that solicit acknowledgments for missing samples and trigger selective retransmissions. In lossy wireless networks, the tight coupling among heartbeat period, IP fragmentation, and retransmission interval obscures end to end latency behavior and leaves practitioners with little guidance on how to tune these parameters. To address these challenges, we propose a probabilistic latency analysis (PLA) that analytically models the reliable transmission process of ROS 2 DDS communication using a discrete state approach. By systematically analyzing both middleware level and transport level events, PLA computes the steady state probability distribution of unacknowledged messages and the retransmission latency. We validate our PLA across 270 scenarios, exploring variations in packet delivery ratios, message sizes, and both publishing and retransmission intervals, demonstrating a close alignment between analytical predictions and experimental results. Our findings establish a theoretical basis to systematically optimize reliability, latency, and performance in wireless industrial robotics.

cs.NI↗

arXiv2025

Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusions

Amodal segmentation targets to predict complete object masks, covering both visible and occluded regions. This task poses significant challenges due to complex occlusions and extreme shape variation, from rigid furniture to highly deformable clothing. Existing one-size-fits-all approaches rely on a single model to handle all shape types, struggling to capture and reason about diverse amodal shapes due to limited representation capacity. A natural solution is to adopt a Mixture-of-Experts (MoE) framework, assigning experts to different shape patterns. However, naively applying MoE without considering the object's underlying shape distribution can lead to mismatched expert routing and insufficient expert specialization, resulting in redundant or underutilized experts. To deal with these issues, we introduce ShapeMoE, a shape-specific sparse Mixture-of-Experts framework for amodal segmentation. The key idea is to learn a latent shape distribution space and dynamically route each object to a lightweight expert tailored to its shape characteristics. Specifically, ShapeMoE encodes each object into a compact Gaussian embedding that captures key shape characteristics. A Shape-Aware Sparse Router then maps the object to the most suitable expert, enabling precise and efficient shape-aware expert routing. Each expert is designed as lightweight and specialized in predicting occluded regions for specific shape patterns. ShapeMoE offers well interpretability via clear shape-to-expert correspondence, while maintaining high capacity and efficiency. Experiments on COCOA-cls, KINS, and D2SA show that ShapeMoE consistently outperforms state-of-the-art methods, especially in occluded region segmentation. The code will be released.

cs.CV↗

arXiv2025

Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA

Amodal segmentation aims to infer the complete shape of occluded objects, even when the occluded region's appearance is unavailable. However, current amodal segmentation methods lack the capability to interact with users through text input and struggle to understand or reason about implicit and complex purposes. While methods like LISA integrate multi-modal large language models (LLMs) with segmentation for reasoning tasks, they are limited to predicting only visible object regions and face challenges in handling complex occlusion scenarios. To address these limitations, we propose a novel task named amodal reasoning segmentation, aiming to predict the complete amodal shape of occluded objects while providing answers with elaborations based on user text input. We develop a generalizable dataset generation pipeline and introduce a new dataset focusing on daily life scenarios, encompassing diverse real-world occlusions. Furthermore, we present AURA (Amodal Understanding and Reasoning Assistant), a novel model with advanced global and spatial-level designs specifically tailored to handle complex occlusions. Extensive experiments validate AURA's effectiveness on the proposed dataset.

cs.CV↗

arXiv2025

Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis

Auscultation remains a cornerstone of clinical practice, essential for both initial evaluation and continuous monitoring. Clinicians listen to the lung sounds and make a diagnosis by combining the patient's medical history and test results. Given this strong association, multitask learning (MTL) can offer a compelling framework to simultaneously model these relationships, integrating respiratory sound patterns with disease manifestations. While MTL has shown considerable promise in medical applications, a significant research gap remains in understanding the complex interplay between respiratory sounds, disease manifestations, and patient metadata attributes. This study investigates how integrating MTL with cutting-edge deep learning architectures can enhance both respiratory sound classification and disease diagnosis. Specifically, we extend recent findings regarding the beneficial impact of metadata on respiratory sound classification by evaluating its effectiveness within an MTL framework. Our comprehensive experiments reveal significant improvements in both lung sound classification and diagnostic performance when the stethoscope information is incorporated into the MTL architecture.

cs.LG↗

arXiv2025

Rigidity of Poincaré-Einstein manifolds with flat Euclidean conformal infinity

In this paper, we prove a rigidity theorem for Poincaré-Einstein manifolds whose conformal infinity is a flat Euclidean space. The proof relies on analyzing the propagation of curvature tensors over the level sets of an adapted boundary defining function. Additionally, we provide examples of Poincaré-Einstein manifolds with non-compact conformal infinities. Furthermore, we draw analogies with Ricci-flat manifolds exhibiting Euclidean volume growth, particularly when the compactified metric has non-negative scalar curvature.

math.DG↗

arXiv2025

Symmetry-breaking effects on spin-orbit torque switching in ferromagnetic semiconductors with perpendicular magnetic anisotropy

This study explores the mechanisms of spin-orbit torque (SOT) switching in ferromagnetic semiconductors (FMS) with perpendicular magnetic anisotropy (PMA), emphasizing the impact of symmetry-breaking. Using micromagnetic simulations based on the Landau-Lifshitz-Gilbert (LLG) equation, we examine several symmetry-breaking factors, including bias field misalignment, interlayer exchange coupling, out-of-plane spin polarization, and tilted magnetic anisotropy. The results reveal that bias field misalignment relative to the film plane significantly distorts the SOT switching hysteresis. Additionally, intrinsic symmetry-breaking effects, such as internal coupling fields, out-of-plane spin polarization, and tilted anisotropy, facilitate field-free SOT (FF-SOT) switching without external bias fields. Each type of FF-SOT switching exhibits distinct characteristics, including hysteresis shifts, switching ratios, and saturated magnetization. This work emphasizes the role of symmetry-breaking in FF-SOT switching and offers fundamental information for interpreting FF-SOT switching observed from FMS films in experiments, contributing to the optimization of SOT efficiency and the advancement of spintronics technologies.

cond-mat.mes-hall↗

arXiv2025

TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models

Navigating the vast chemical space of druggable compounds is a formidable challenge in drug discovery, where generative models are increasingly employed to identify viable candidates. Conditional 3D structure-based drug design (3D-SBDD) models, which take into account complex three-dimensional interactions and molecular geometries, are particularly promising. Scaffold hopping is an efficient strategy that facilitates the identification of similar active compounds by strategically modifying the core structure of molecules, effectively narrowing the wide chemical space and enhancing the discovery of drug-like products. However, the practical application of 3D-SBDD generative models is hampered by their slow processing speeds. To address this bottleneck, we introduce TurboHopp, an accelerated pocket-conditioned 3D scaffold hopping model that merges the strategic effectiveness of traditional scaffold hopping with rapid generation capabilities of consistency models. This synergy not only enhances efficiency but also significantly boosts generation speeds, achieving up to 30 times faster inference speed as well as superior generation quality compared to existing diffusion-based models, establishing TurboHopp as a powerful tool in drug discovery. Supported by faster inference speed, we further optimize our model, using Reinforcement Learning for Consistency Models (RLCM), to output desirable molecules. We demonstrate the broad applicability of TurboHopp across multiple drug discovery scenarios, underscoring its potential in diverse molecular settings.

cs.LG↗

arXiv2024

Type-I Blowup Solutions for Yang-Mills Flow

In this paper, we construct an infinite-dimensional family of solutions for the Yang-Mills flow on $\mathbb{R}^n \times SO(n)$ for $5 \leq n \leq 9$, which converge to $SO(n)$-equivariant homothetically shrinking solitons, modulo the gauge group. As a corollary, we prove the existence of asymmetric Type-I blowup solutions for the Yang-Mills flow.

math.DG↗

arXiv2024

AVIN-Chat: An Audio-Visual Interactive Chatbot System with Emotional State Tuning

This work presents an audio-visual interactive chatbot (AVIN-Chat) system that allows users to have face-to-face conversations with 3D avatars in real-time. Compared to the previous chatbot services, which provide text-only or speech-only communications, the proposed AVIN-Chat can offer audio-visual communications providing users with a superior experience quality. In addition, the proposed AVIN-Chat emotionally speaks and expresses according to the user's emotional state. Thus, it enables users to establish a strong bond with the chatbot system, increasing the user's immersion. Through user subjective tests, it is demonstrated that the proposed system provides users with a higher sense of immersion than previous chatbot systems. The demonstration video is available at https://www.youtube.com/watch?v=Z74uIV9k7_k.

cs.HC↗

arXiv2024

Convergence rate of the $Q$-curvature flow

Carlotto, Chodosh and Rubinstein have studied the convergence rate of the Yamabe flow. Inspired by their result, we study the convergence rate of the $Q$-curvature flow in this paper. In particular, we provide an example of a slowly converging $Q_6$-curvature flow in dimension 6, in constrast to the dimension 2 case, where the $Q$-curvature flow always converges exponentially.

math.DG↗

arXiv2024

Compact Localized States in Electric Circuit Flatband Lattices

We generate compact localized states in an electrical diamond lattice, comprised of only capacitors and inductors, via local driving near its flatband frequency. We compare experimental results to numerical simulations and find very good agreement. We also examine the stub lattice, which features a flatband of a different class where neighboring compact localized states share lattice sites. We find that local driving, while exciting the lattice at that flatband frequency, is unable to isolate a single compact localized state due to their non-orthogonality. Finally, we introduce lattice nonlinearity and showcase the realization of nonlinear compact localized states in the diamond lattice. Our findings pave the way of applying flatband physics to complex electric circuit dynamics.

cond-mat.mes-hall↗

arXiv2024

Trapping Hard-Core Bosons in Flatband Lattices

We investigate 1D and 2D cross-stitch lattices with hard-core bosons and analytically construct exact groundstates that feature macroscopic degeneracy. The construction relies on the presence of a flatband in the single particle spectrum and the orthogonality of the associated compact localized states (CLS). Up to filling fraction $ν=1/2$, the groundstate is constructed by occupying the CLS. Exactly at $ν=1/2$, the groundstate becomes a Wigner crystal. For higher filling fractions, the groundstate is constructed by filling the CLS sites completely one by one. Macroscopic degeneracy arises from the multiple choices available when occupying or filling the CLS sites. An occupied CLS acts as an impenetrable barrier for bosons both in 1D and 2D, leading to Hilbert space fragmentation. A similar phenomenology also holds for hard-core bosons on the diamond chain and its higher dimensional generalizations. We also discuss the mapping of these hard-core models onto spin models with quantum many-body scars.

cond-mat.str-el↗

arXiv2024

Learning-enabled Flexible Job-shop Scheduling for Scalable Smart Manufacturing

In smart manufacturing systems (SMSs), flexible job-shop scheduling with transportation constraints (FJSPT) is essential to optimize solutions for maximizing productivity, considering production flexibility based on automated guided vehicles (AGVs). Recent developments in deep reinforcement learning (DRL)-based methods for FJSPT have encountered a scale generalization challenge. These methods underperform when applied to environment at scales different from their training set, resulting in low-quality solutions. To address this, we introduce a novel graph-based DRL method, named the Heterogeneous Graph Scheduler (HGS). Our method leverages locally extracted relational knowledge among operations, machines, and vehicle nodes for scheduling, with a graph-structured decision-making framework that reduces encoding complexity and enhances scale generalization. Our performance evaluation, conducted with benchmark datasets, reveals that the proposed method outperforms traditional dispatching rules, meta-heuristics, and existing DRL-based approaches in terms of makespan performance, even on large-scale instances that have not been experienced during training.

eess.SY↗

arXiv2024

MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker Joints

Molecular core structures and R-groups are essential concepts in drug development. Integration of these concepts with conventional graph pre-training approaches can promote deeper understanding in molecules. We propose MolPLA, a novel pre-training framework that employs masked graph contrastive learning in understanding the underlying decomposable parts inmolecules that implicate their core structure and peripheral R-groups. Furthermore, we formulate an additional framework that grants MolPLA the ability to help chemists find replaceable R-groups in lead optimization scenarios. Experimental results on molecular property prediction show that MolPLA exhibits predictability comparable to current state-of-the-art models. Qualitative analysis implicate that MolPLA is capable of distinguishing core and R-group sub-structures, identifying decomposable regions in molecules and contributing to lead optimization scenarios by rationally suggesting R-group replacements given various query core templates. The code implementation for MolPLA and its pre-trained model checkpoint is available at https://github.com/dmis-lab/MolPLA

cs.LG↗