arXiv subjects

Seunghun Lee

Publications and source records attributed to Seunghun Lee.

At least 37 records · Page 2Linked to original sources

arXiv2025

Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

In this paper, we present Latest Object Memory Management (LOMM) for temporally consistent video instance segmentation that significantly improves long-term instance tracking. At the core of our method is Latest Object Memory (LOM), which robustly tracks and continuously updates the latest states of objects by explicitly modeling their presence in each frame. This enables consistent tracking and accurate identity management across frames, enhancing both performance and reliability through the VIS process. Moreover, we introduce Decoupled Object Association (DOA), a strategy that separately handles newly appearing and already existing objects. By leveraging our memory system, DOA accurately assigns object indices, improving matching accuracy and ensuring stable identity consistency, even in dynamic scenes where objects frequently appear and disappear. Extensive experiments and ablation studies demonstrate the superiority of our method over traditional approaches, setting a new benchmark in VIS. Notably, our LOMM achieves state-of-the-art AP score of 54.0 on YouTube-VIS 2022, a dataset known for its challenging long videos. Project page: https://seung-hun-lee.github.io/projects/LOMM/

cs.CV↗

arXiv2025

CAVIS: Context-Aware Video Instance Segmentation

In this paper, we introduce the Context-Aware Video Instance Segmentation (CAVIS), a novel framework designed to enhance instance association by integrating contextual information adjacent to each object. To efficiently extract and leverage this information, we propose the Context-Aware Instance Tracker (CAIT), which merges contextual data surrounding the instances with the core instance features to improve tracking accuracy. Additionally, we design the Prototypical Cross-frame Contrastive (PCC) loss, which ensures consistency in object-level features across frames, thereby significantly enhancing matching accuracy. CAVIS demonstrates superior performance over state-of-the-art methods on all benchmark datasets in video instance segmentation (VIS) and video panoptic segmentation (VPS). Notably, our method excels on the OVIS dataset, known for its particularly challenging videos. Project page: https://seung-hun-lee.github.io/projects/CAVIS/

cs.CV↗

arXiv2025

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search

Tokens are fundamental processing units of generative AI (GenAI) and large language models (LLMs), and token communication (TC) is essential for enabling remote AI-generate content (AIGC) and wireless LLM applications. Unlike traditional bits, each of which is independently treated, the semantics of each token depends on its surrounding context tokens. This inter-token dependency makes TC vulnerable to outage channels, where the loss of a single token can significantly distort the original message semantics. Motivated by this, this paper focuses on optimizing token packetization to maximize the average token similarity (ATS) between the original and received token messages under outage channels. Due to inter-token dependency, this token grouping problem is combinatorial, with complexity growing exponentially with message length. To address this, we propose a novel framework of semantic packet aggregation with lookahead search (SemPA-Look), built on two core ideas. First, it introduces the residual semantic score (RSS) as a token-level surrogate for the message-level ATS, allowing robust semantic preservation even when a certain token packet is lost. Second, instead of full search, SemPA-Look applies a lookahead search-inspired algorithm that samples intra-packet token candidates without replacement (fixed depth), conditioned on inter-packet token candidates sampled with replacement (fixed width), thereby achieving linear complexity. Experiments on a remote AIGC task with the MS-COCO dataset (text captioned images) demonstrate that SemPA-Look achieves high ATS and LPIPS scores comparable to exhaustive search, while reducing computational complexity by up to 40$\times$. Compared to other linear-complexity algorithms such as the genetic algorithm (GA), SemPA-Look achieves 10$\times$ lower complexity, demonstrating its practicality for remote AIGC and other TC applications.

eess.SP↗

arXiv2025

Bulk excitations in ultraclean $α$-RuCl$_3$: Quantitative evidence for Majorana dispersions in a Kitaev quantum spin liquid

The spin-orbit coupled Mott insulator $α$-RuCl$_3$ has emerged as a prime candidate for realizing the Kitaev quantum spin liquid (KQSL), characterized by Majorana quasiparticles, whose edge states exhibit a distinctive half-integer quantized thermal Hall conductivity. However, its van der Waals nature makes its thermal Hall response highly sensitive to structural disorder, leading to sample-dependent variations. Here, we investigate low-energy bulk excitations in the field-induced quantum disordered (FIQD) state of newly available ultraclean single crystals of $α$-RuCl$_3$. High-resolution specific heat measurements under in-plane magnetic field rotation reveal an anisotropic excitation gap, whose field dependence is consistent with the Majorana gap in the KQSL state. Remarkably, when the field aligns with Ru-Ru bond directions, we observe gapless excitations with Dirac-like dispersions that quantitatively match theoretical predictions of Majorana bands based on the reported Kitaev interactions. Our findings in these ultraclean crystals provide strong evidence that the FIQD state of $α$-RuCl$_3$ is a robust KQSL, resilient against small disorder perturbations.

cond-mat.str-el↗

arXiv2025

Semantic Packet Aggregation for Token Communication via Genetic Beam Search

Token communication (TC) is poised to play a pivotal role in emerging language-driven applications such as AI-generated content (AIGC) and wireless language models (LLMs). However, token loss caused by channel noise can severely degrade task performance. To address this, in this article, we focus on the problem of semantics-aware packetization and develop a novel algorithm, termed semantic packet aggregation with genetic beam search (SemPA-GBeam), which aims to maximize the average token similarity (ATS) over erasure channels. Inspired from the genetic algorithm (GA) and the beam search algorithm, SemPA-GBeam iteratively optimizes token grouping for packetization within a fixed number of groups (i.e., fixed beam width in beam search) while randomly swapping a fraction of tokens (i.e., mutation in GA). Experiments on the MS-COCO dataset demonstrate that SemPA-GBeam achieves ATS and LPIPS scores comparable to exhaustive search while reducing complexity by more than 20x.

eess.SP↗

arXiv2025

Latent Bayesian Optimization via Autoregressive Normalizing Flows

Bayesian Optimization (BO) has been recognized for its effectiveness in optimizing expensive and complex objective functions. Recent advancements in Latent Bayesian Optimization (LBO) have shown promise by integrating generative models such as variational autoencoders (VAEs) to manage the complexity of high-dimensional and structured data spaces. However, existing LBO approaches often suffer from the value discrepancy problem, which arises from the reconstruction gap between input and latent spaces. This value discrepancy problem propagates errors throughout the optimization process, leading to suboptimal outcomes. To address this issue, we propose a Normalizing Flow-based Bayesian Optimization (NF-BO), which utilizes normalizing flow as a generative model to establish one-to-one encoding function from the input space to the latent space, along with its left-inverse decoding function, eliminating the reconstruction gap. Specifically, we introduce SeqFlow, an autoregressive normalizing flow for sequence data. In addition, we develop a new candidate sampling strategy that dynamically adjusts the exploration probability for each token based on its importance. Through extensive experiments, our NF-BO method demonstrates superior performance in molecule generation tasks, significantly outperforming both traditional and recent LBO approaches.

cs.LG↗

arXiv2025

Style-Editor: Text-driven object-centric style editing

We present Text-driven object-centric style editing model named Style-Editor, a novel method that guides style editing at an object-centric level using textual inputs. The core of Style-Editor is our Patch-wise Co-Directional (PCD) loss, meticulously designed for precise object-centric editing that are closely aligned with the input text. This loss combines a patch directional loss for text-guided style direction and a patch distribution consistency loss for even CLIP embedding distribution across object regions. It ensures a seamless and harmonious style editing across object regions. Key to our method are the Text-Matched Patch Selection (TMPS) and Pre-fixed Region Selection (PRS) modules for identifying object locations via text, eliminating the need for segmentation masks. Lastly, we introduce an Adaptive Background Preservation (ABP) loss to maintain the original style and structural essence of the image's background. This loss is applied to dynamically identified background areas. Extensive experiments underline the effectiveness of our approach in creating visually coherent and textually aligned style editing.

cs.CV↗

arXiv2025

Semantic Packet Aggregation and Repeated Transmission for Text-to-Image Generation

Text-based communication is expected to be prevalent in 6G applications such as wireless AI-generated content (AIGC). Motivated by this, this paper addresses the challenges of transmitting text prompts over erasure channels for a text-to-image AIGC task by developing the semantic segmentation and repeated transmission (SMART) algorithm. SMART groups words in text prompts into packets, prioritizing the task-specific significance of semantics within these packets, and optimizes the number of repeated transmissions. Simulation results show that SMART achieves higher similarities in received texts and generated images compared to a character-level packetization baseline, while reducing computing latency by orders of magnitude compared to an exhaustive search baseline.

eess.SP↗

arXiv2025

Rapid analysis of point-contact Andreev reflection spectra via machine learning with adaptive data augmentation

Delineating the superconducting order parameters is a pivotal task in investigating superconductivity for probing pairing mechanisms, as well as their symmetry and topology. Point-contact Andreev reflection (PCAR) measurement is a simple yet powerful tool for identifying the order parameters. The PCAR spectra exhibit significant variations depending on the type of the order parameter in a superconductor, including its magnitude ($\mathitΔ$), as well as temperature, interfacial quality, Fermi velocity mismatch, and other factors. The information on the order parameter can be obtained by finding the combination of these parameters, generating a theoretical spectrum that fits a measured experimental spectrum. However, due to the complexity of the spectra and the high dimensionality of parameters, extracting the fitting parameters is often time-consuming and labor-intensive. In this study, we employ a convolutional neural network (CNN) algorithm to create models for rapid and automated analysis of PCAR spectra of various superconductors with different pairing symmetries (conventional $s$-wave, chiral $p_x+ip_y$-wave, and $d_{x^2-y^2}$-wave). The training datasets are generated based on the Blonder-Tinkham-Klapwijk (BTK) theory and further modified and augmented by selectively incorporating noise and peaks according to the bias voltages. This approach not only replicates the experimental spectra but also brings the model's attention to important features within the spectra. The optimized models provide fitting parameters for experimentally measured spectra in less than 100 ms per spectrum. Our approaches and findings pave the way for rapid and automated spectral analysis which will help accelerate research on superconductors with complex order parameters.

cond-mat.supr-con↗

arXiv2024

Color simulation for multilayered thin films using Python

Physical insight into a material can be first gained by its color since the reflectance spectrum from an object reflects its microstructure and complex reflective indices. We here present a comprehensive overview of electrodynamics and optics related to reflectance spectra and color and provide an open-source Python code for simulating reflectance spectra and extracting color values. The validity and applicability of the code are demonstrated through comparative analysis with both literature and experimental data.

physics.optics↗

arXiv2024

Emission and Coherent Control of Levitons in Graphene

Flying qubits encode quantum information in propagating modes instead of stationary discrete states. Although photonic flying qubits are available, the weak interaction between photons limits the efficiency of conditional quantum gates. Conversely, electronic flying qubits can use Coulomb interactions, but the weaker quantum coherence in conventional semiconductors has hindered their realization. In this work, we engineered on-demand injection of a single electronic flying qubit state and its manipulation over the Bloch sphere. The flying qubit is a Leviton propagating in quantum Hall edge channels of a high-mobility graphene monolayer. Although single-shot qubit readout and two-qubit operations are still needed for a viable manipulation of flying qubits, the coherent manipulation of an itinerant electronic state at the single-electron level presents a highly promising alternative to conventional qubits.

cond-mat.mes-hall↗

arXiv2024

Q-divisor and Ampleness

We give two criteria for a divisor on complex smooth projective variety to be ample using the multiplier ideal sheaf and the model category.

math.AG↗

arXiv2024

Homotopical presentation of categories

We give a criterion for a functor $F:C\rightarrow B$ between small categories to generate a small presentation of the universal model category $U(B)$ in the sense of Dugger.

math.CT↗

arXiv2024

Inversion-based Latent Bayesian Optimization

Latent Bayesian optimization (LBO) approaches have successfully adopted Bayesian optimization over a continuous latent space by employing an encoder-decoder architecture to address the challenge of optimization in a high dimensional or discrete input space. LBO learns a surrogate model to approximate the black-box objective function in the latent space. However, we observed that most LBO methods suffer from the `misalignment problem`, which is induced by the reconstruction error of the encoder-decoder architecture. It hinders learning an accurate surrogate model and generating high-quality solutions. In addition, several trust region-based LBO methods select the anchor, the center of the trust region, based solely on the objective function value without considering the trust region`s potential to enhance the optimization process. To address these issues, we propose Inversion-based Latent Bayesian Optimization (InvBO), a plug-and-play module for LBO. InvBO consists of two components: an inversion method and a potential-aware trust region anchor selection. The inversion method searches the latent code that completely reconstructs the given target data. The potential-aware trust region anchor selection considers the potential capability of the trust region for better local optimization. Experimental results demonstrate the effectiveness of InvBO on nine real-world benchmarks, such as molecule design and arithmetic expression fitting tasks. Code is available at https://github.com/mlvlab/InvBO.

cs.LG↗

arXiv2024

The interval coloring impropriety of planar graphs

For a graph $G$, we call an edge coloring of $G$ an \textit{improper} \textit{interval edge coloring} if for every $v\in V(G)$ the colors, which are integers, of the edges incident with $v$ form an integral interval. The \textit{interval coloring impropriety} of $G$, denoted by $μ_{int}(G)$, is the smallest value $k$ such that $G$ has an improper interval edge coloring where at most $k$ edges of $G$ with a common endpoint have the same color. The purpose of this note is to communicate solutions to two previous questions on interval coloring impropriety, mainly regarding planar graphs. First, we prove $μ_{int}(G) \leq 2$ for every outerplanar graph $G$. This confirms the conjecture by Casselgren and Petrosyan in the affirmative. Secondly, we prove that for each $k\geq 2$, the interval coloring impropriety of $k$-trees is unbounded. This refutes the conjecture by Carr, Cho, Crawford, Iršič, Pai and Robinson.

math.CO↗

arXiv2024

Superconducting phase diagram in Bi$_x$Ni$_{1-x}$ thin films$\colon$ the effects of Bi stoichiometry on superconductivity

The Bi${-}$Ni binary system has been of interest due to possible unconventional superconductivity aroused therein, such as time-reversal symmetry breaking in Bi/Ni bilayers or the coexistence of superconductivity and ferromagnetism in Bi$_3$Ni crystals. While Ni acts as a ferromagnetic element in such systems, the role of strong spin-orbit-coupling element Bi in superconductivity has remained unexplored. In this work, we systematically studied the effects of Bi stoichiometry on the superconductivity of Bi$_x$Ni$_{1-x}$ thin films (${x} \approx$ 0.5 to 0.9) fabricated via a composition-spread approach. The superconducting phase map of Bi$_x$Ni$_{1-x}$ thin films exhibited a superconducting composition region attributable to the intermetallic Bi$_3$Ni phase with different amount of excess Bi, revealed by synchrotron X-ray diffraction analysis. Interestingly, the mixed phase region with Bi$_3$Ni and Bi showed unusual increases in the superconducting transition temperature and residual resistance ratio as more Bi impurities were included, with the maximum ${T}_{c}$ ($=$ 4.2 K) observed at $x \approx$ 0.79. A correlation analysis of structural, electrical, and magneto-transport characteristics across the composition variation revealed that the unusual superconducting $"$dome$"$ is due to two competing roles of Bi$\colon$ impurity scattering and carrier doping. We found that the carrier doping effect is dominant in the mild doping regime (0.74 $\leq {x} \leq$ 0.79), while impurity scattering becomes more pronounced at larger Bi stoichiometry.

cond-mat.supr-con↗

arXiv2023

Advancing Bayesian Optimization via Learning Correlated Latent Space

Bayesian optimization is a powerful method for optimizing black-box functions with limited function evaluations. Recent works have shown that optimization in a latent space through deep generative models such as variational autoencoders leads to effective and efficient Bayesian optimization for structured or discrete data. However, as the optimization does not take place in the input space, it leads to an inherent gap that results in potentially suboptimal solutions. To alleviate the discrepancy, we propose Correlated latent space Bayesian Optimization (CoBO), which focuses on learning correlated latent spaces characterized by a strong correlation between the distances in the latent space and the distances within the objective function. Specifically, our method introduces Lipschitz regularization, loss weighting, and trust region recoordination to minimize the inherent gap around the promising areas. We demonstrate the effectiveness of our approach on several optimization tasks in discrete data, such as molecule design and arithmetic expression fitting, and achieve high performance within a small budget.

cs.LG↗

arXiv2023

Inscribable order types

We call an order type inscribable if it is realized by a point configuration where the extreme points are all on a circle. In this paper, we investigate inscribability of order types. We first show that every simple order type with at most 2 interior points is inscribable, and that the number of such order types is $Θ(\frac{4^n}{n^{3/2}})$. We further construct an infinite family of minimally uninscribable order types. The proof of uninscribability mainly uses Möbius transformations. We also suggest open problems around inscribability.

math.MG↗