arXiv subjects

Seunghoon Lee

Publications and source records attributed to Seunghoon Lee.

At least 19 recordsLinked to original sources

arXiv2026

A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection

Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resolutions. Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy, indicating greater computational efficiency. These results suggest that for OOD detection tasks of limited visual complexity, lightweight ML approaches can achieve DL-level performance with significantly reduced computational cost, supporting practical real-world deployment.

cs.CV↗

arXiv2026

CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation

Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues. Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation through relation transformer blocks. To improve learning efficiency, we incorporate a token masking strategy that addresses the limitations of relying solely on increased model complexity. Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods.

cs.CV↗

arXiv2026

Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting

Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches suffer from implicit temporal modeling and limited spatial context. These limitations lead to intraframe and inter-frame inconsistencies, which become particularly pronounced in dynamic scenes and large outpainting scenarios. To overcome these challenges, we propose Seen-to-Scene, a novel framework that unifies propagationbased and generation-based paradigms for video outpainting. Specifically, Seen-to-Scene leverages flow-based propagation with a flow completion network pre-trained for video inpainting, which is fine-tuned in an end-to-end manner to bridge the domain gap and reconstruct coherent motion fields. To further improve the efficiency and reliability of propagation, we introduce a reference-guided latent propagation that effectively propagates source content across frames. Extensive experiments demonstrate that our method achieves superior temporal coherence and visual realism with efficient inference, surpassing even prior state-of-the-art methods that require input-specific adaptation.

cs.CV↗

arXiv2026

The Python Simulations of Chemistry Framework: 10 years of an open-source quantum chemistry project

Over the past decade, the Python-based Simulations of Chemistry Framework (PySCF) has developed into a widely used open-source platform for electronic structure theory and quantum chemical method development. This article reviews the major advances since the previous overview in 2020, covering new modules and methodology, infrastructure changes, and performance benchmarks.

physics.chem-ph↗

arXiv2026

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias

Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended biases from spurious correlations within the data. This paper investigates the unique challenges of unlearning from such biased models. We identify a novel phenomenon we term ``shortcut unlearning," where models exhibit an ``easy to learn, yet hard to forget" tendency. Specifically, models struggle to forget easily-learned, bias-aligned samples; instead of forgetting the class attribute, they unlearn the bias attribute, which can paradoxically improve accuracy on the class intended to be forgotten. To address this, we propose CUPID, a new unlearning framework inspired by the observation that samples with different biases exhibit distinct loss landscape sharpness. Our method first partitions the forget set into causal- and bias-approximated subsets based on sample sharpness, then disentangles model parameters into causal and bias pathways, and finally performs a targeted update by routing refined causal and bias gradients to their respective pathways. Extensive experiments on biased datasets including Waterbirds, BAR, and Biased NICO++ demonstrate that our method achieves state-of-the-art forgetting performance and effectively mitigates the shortcut unlearning problem.

cs.LG↗

arXiv2026

Classical computational simulation of the FeMo-cofactor model to chemical accuracy and its implications

We use classical computational methods to estimate the ground-state energy to chemical accuracy in a model of the FeMo-cofactor of nitrogenase which is widely studied as a target of quantum computing. Our result relies on the insight that the ground-state problem can be characterized as one of ranking many competing, but largely simple, states. This allows a combination of systematic high-order coupled cluster and density matrix renormalization group calculations together with an extrapolation protocol to obtain an accurate energy. Within the model we identify several spin isomer candidates for the ground-state that are degenerate to chemical accuracy. Beyond this model, we characterize the impact of additional electronic excitations and the cluster and protein geometric fluctuations on the low-lying electronic landscape. We find that many features of the landscape are retained in more detailed representations of nitrogenase, which points to the complexity of spectroscopic interpretations of the electronic structure of the FeMo-cofactor.

physics.chem-ph↗

arXiv2025

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

We present in this paper a novel post-training quantization (PTQ) method, dubbed AccuQuant, for diffusion models. We show analytically and empirically that quantization errors for diffusion models are accumulated over denoising steps in a sampling process. To alleviate the error accumulation problem, AccuQuant minimizes the discrepancies between outputs of a full-precision diffusion model and its quantized version within a couple of denoising steps. That is, it simulates multiple denoising steps of a diffusion sampling process explicitly for quantization, accounting the accumulated errors over multiple denoising steps, which is in contrast to previous approaches to imitating a training process of diffusion models, namely, minimizing the discrepancies independently for each step. We also present an efficient implementation technique for AccuQuant, together with a novel objective, which reduces a memory complexity significantly from $\mathcal{O}(n)$ to $\mathcal{O}(1)$, where $n$ is the number of denoising steps. We demonstrate the efficacy and efficiency of AccuQuant across various tasks and diffusion models on standard benchmarks.

cs.CV↗

arXiv2025

Differentially Private Compression and the Sensitivity of LZ77

We initiate the study of differentially private data-compression schemes motivated by the insecurity of the popular "Compress-Then-Encrypt" framework. Data compression is a useful tool which exploits redundancy in data to reduce storage/bandwidth when files are stored or transmitted. However, if the contents of a file are confidential then the length of a compressed file might leak confidential information about the content of the file itself. Encrypting a compressed file does not eliminate this leakage as data encryption schemes are only designed to hide the content of confidential message instead of the length of the message. In our proposed Differentially Private Compress-Then-Encrypt framework, we add a random positive amount of padding to the compressed file to ensure that any leakage satisfies the rigorous privacy guarantee of $(ε,δ)$-differential privacy. The amount of padding that needs to be added depends on the sensitivity of the compression scheme to small changes in the input, i.e., to what degree can changing a single character of the input message impact the length of the compressed file. While some popular compression schemes are highly sensitive to small changes in the input, we argue that effective data compression schemes do not necessarily have high sensitivity. Our primary technical contribution is analyzing the fine-grained sensitivity of the LZ77 compression scheme (IEEE Trans. Inf. Theory 1977) which is one of the most common compression schemes used in practice. We show that the global sensitivity of the LZ77 compression scheme has the upper bound $O(W^{2/3}\log n)$ where $W\leq n$ denotes the size of the sliding window. When $W=n$, we show the lower bound $Ω(n^{2/3}\log^{1/3}n)$ for the global sensitivity of the LZ77 compression scheme which is tight up to a sublogarithmic factor.

cs.CC↗

arXiv2025

Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation

Referring video object segmentation aims to segment and track a target object in a video using a natural language prompt. Existing methods typically fuse visual and textual features in a highly entangled manner, processing multi-modal information together to generate per-frame masks. However, this approach often struggles with ambiguous target identification, particularly in scenes with multiple similar objects, and fails to ensure consistent mask propagation across frames. To address these limitations, we introduce FindTrack, an efficient decoupled framework that separates target identification from mask propagation. FindTrack first adaptively selects a key frame by balancing segmentation confidence and vision-text alignment, establishing a robust reference for the target object. This reference is then utilized by a dedicated propagation module to track and segment the object across the entire video. By decoupling these processes, FindTrack effectively reduces ambiguities in target association and enhances segmentation consistency. FindTrack significantly outperforms all existing methods on public benchmarks, demonstrating its superiority.

cs.CV↗

arXiv2025

Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View

Recent studies construct deblurred neural radiance fields~(DeRF) using dozens of blurry images, which are not practical scenarios if only a limited number of blurry images are available. This paper focuses on constructing DeRF from sparse-view for more pragmatic real-world scenarios. As observed in our experiments, establishing DeRF from sparse views proves to be a more challenging problem due to the inherent complexity arising from the simultaneous optimization of blur kernels and NeRF from sparse view. Sparse-DeRF successfully regularizes the complicated joint optimization, presenting alleviated overfitting artifacts and enhanced quality on radiance fields. The regularization consists of three key components: Surface smoothness, helps the model accurately predict the scene structure utilizing unseen and additional hidden rays derived from the blur kernel based on statistical tendencies of real-world; Modulated gradient scaling, helps the model adjust the amount of the backpropagated gradient according to the arrangements of scene objects; Perceptual distillation improves the perceptual quality by overcoming the ill-posed multi-view inconsistency of image deblurring and distilling the pre-deblurred information, compensating for the lack of clean information in blurry images. We demonstrate the effectiveness of the Sparse-DeRF with extensive quantitative and qualitative experimental results by training DeRF from 2-view, 4-view, and 6-view blurry images.

cs.CV↗

arXiv2024

Rapid initial state preparation for the quantum simulation of strongly correlated molecules

Studies on quantum algorithms for ground state energy estimation often assume perfect ground state preparation; however, in reality the initial state will have imperfect overlap with the true ground state. Here we address that problem in two ways: by faster preparation of matrix product state (MPS) approximations, and more efficient filtering of the prepared state to find the ground state energy. We show how to achieve unitary synthesis with a Toffoli complexity about $7 \times$ lower than that in prior work, and use that to derive a more efficient MPS preparation method. For filtering we present two different approaches: sampling and binary search. For both we use the theory of window functions to avoid large phase errors and minimise the complexity. We find that the binary search approach provides better scaling with the overlap at the cost of a larger constant factor, such that it will be preferred for overlaps less than about $0.003$. Finally, we estimate the total resources to perform ground state energy estimation of Fe-S cluster systems, including the FeMo cofactor by estimating the overlap of different MPS initial states with potential ground-states of the FeMo cofactor using an extrapolation procedure. {With a modest MPS bond dimension of 4000, our procedure produces an estimate of $\sim 0.9$ overlap squared with a candidate ground-state of the FeMo cofactor, producing a total resource estimate of $7.3 \times 10^{10}$ Toffoli gates; neglecting the search over candidates and assuming the accuracy of the extrapolation, this validates prior estimates that used perfect ground state overlap. This presents an example of a practical path to prepare states of high overlap in a challenging-to-compute chemical system.

quant-ph↗

arXiv2024

Improving Unsupervised Video Object Segmentation via Fake Flow Generation

Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-stream approaches that leverage both RGB images and optical flow maps have gained significant attention. However, the limited amount of training data remains a substantial challenge. In this study, we propose a novel data generation method that simulates fake optical flows from single images, thereby creating large-scale training data for stable network learning. Inspired by the observation that optical flow maps are highly dependent on depth maps, we generate fake optical flows by refining and augmenting the estimated depth maps of each image. By incorporating our simulated image-flow pairs, we achieve new state-of-the-art performance on all public benchmark datasets without relying on complex modules. We believe that our data generation method represents a potential breakthrough for future VOS research.

cs.CV↗

arXiv2024

Dual Prototype Attention for Unsupervised Video Object Segmentation

Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion between different frames. This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames. IMA densely integrates context information from different modalities based on a mutual refinement. IFA injects global context of a video to the query frame, enabling a full utilization of useful properties from multiple frames. Experimental results on public benchmark datasets demonstrate that our proposed approach outperforms all existing methods by a substantial margin. The proposed two components are also thoroughly validated via ablative study.

cs.CV↗

arXiv2024

Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation

Unsupervised Video Object Segmentation (UVOS) refers to the challenging task of segmenting the prominent object in videos without manual guidance. In recent works, two approaches for UVOS have been discussed that can be divided into: appearance and appearance-motion-based methods, which have limitations respectively. Appearance-based methods do not consider the motion of the target object due to exploiting the correlation information between randomly paired frames. Appearance-motion-based methods have the limitation that the dependency on optical flow is dominant due to fusing the appearance with motion. In this paper, we propose a novel framework for UVOS that can address the aforementioned limitations of the two approaches in terms of both time and scale. Temporal Alignment Fusion aligns the saliency information of adjacent frames with the target frame to leverage the information of adjacent frames. Scale Alignment Decoder predicts the target object mask by aggregating multi-scale feature maps via continuous mapping with implicit neural representation. We present experimental results on public benchmark datasets, DAVIS 2016 and FBMS, which demonstrate the effectiveness of our method. Furthermore, we outperform the state-of-the-art methods on DAVIS 2016.

cs.CV↗

arXiv2023

Multireference protonation energetics of a dimeric model of nitrogenase iron-sulfur clusters

Characterizing the electronic structure of the iron--sulfur clusters in nitrogenase is necessary to understand their role in the nitrogen fixation process. One challenging task is to determine the protonation state of the intermediates in the nitrogen fixing cycle. Here, we use a dimeric iron--sulfur model to study relative energies of protonation at C, S or Fe. Using a composite method based on coupled cluster and density matrix renormalization group energetics, we converge the relative energies of four protonated configurations with respect to basis set and correlation level. We find that accurate relative energies require large basis sets, as well as a proper treatment of multireference and relativistic effects. We have also tested ten density functional approximations for these systems. Most of them give large errors in the relative energies. The best performing functional in this system is B3LYP, which gives mean absolute and maximum errors of only 10 and 13 kJ/mol with respect to our correlated wavefunction estimates, respectively. Our work provides benchmark results for the calibration of new approximate electronic structure methods and density functionals for these problems.

physics.chem-ph↗

arXiv2023

Block2: a comprehensive open source framework to develop and apply state-of-the-art DMRG algorithms in electronic structure and beyond

Block2 is an open source framework to implement and perform density matrix renormalization group and matrix product state algorithms. Out-of-the-box it supports the eigenstate, time-dependent, response, and finite-temperature algorithms. In addition, it carries special optimizations for ab initio electronic structure Hamiltonians and implements many quantum chemistry extensions to the density matrix renormalization group, such as dynamical correlation theories. The code is designed with an emphasis on flexibility, extensibility, and efficiency, and to support integration with external numerical packages. Here we explain the design principles and currently supported features and present numerical examples in a range of applications.

physics.chem-ph↗

arXiv2023

Crystal Facet Effect in Plasmonic Catalysis

In the realm of plasmonic catalytic systems, much attention has been devoted to the plasmon-derived mechanisms, yet the influence of nanoparticles' crystal facets in this type of processes has been sparsely investigated. In this work, we study the plasmon-assisted electrocatalytic CO2 reduction reaction using three different shapes of plasmonic Au nanoparticles - nanocube (NC), rhombic dodecahedron (RD) and octahedron (OC) - with three different exposed facets: {100}, {110} and {111}, respectively. These particles were synthesized with similar sizes and LSPR wavelengths to reveal the role of the facet more than other contributions to the plasmon-assisted reaction. Upon plasmon excitation, Au OCs exhibited nearly a doubling in the Faradaic efficiency of CO (FE(CO)) and a remarkable threefold enhancement in the partial current density of CO (j(CO)) compared to the non-illuminated response, NCs also demonstrated an improved performance under illumination. In contrast, Au RDs showed nearly the same performance in dark or light conditions. Temperature-dependent experiments ruled out heat as the main factor in the enhanced response of Au OCs and NCs. Large-scale atomistic simulations of the nanoparticles' electronic structure and electromagnetic modeling revealed higher hot carrier abundance and electric field enhancement on Au OCs and NCs compared to RDs. Abundant hot carriers on edges facilitate molecular activation, leading to enhanced selectivity and activity. Thus, OCs with the highest edge/facet ratio exhibited the strongest enhancement in FE(CO) and j(CO) upon illumination. This observation is further supported by plasmon-assisted H2 evolution reaction experiments. Our findings highlight the dominance of low coordinated sites over facets in plasmonic catalytic processes, providing valuable insights for designing more efficient catalysts for solar fuels production.

physics.optics↗

arXiv2023

An ab initio correction vector restricted active space approach to the L-edge XAS and 2p3d RIXS spectra of transition metal clusters

We describe an ab initio approach to simulate L-edge X-ray absorption (XAS) and 2p3d resonant inelastic X-ray scattering (RIXS) spectroscopies. We model the strongly correlated electronic structure within a restricted active space and employ a correction vector formulation instead of sum-over-states expressions for the spectra, thus eliminating the need to calculate a large number of intermediate and final electronic states. We present benchmark simulations of the XAS and RIXS spectra of the iron complexes [FeCl4]^{-1/-2} and [Fe(SCH3)4]^{-1/-2} and interpret the spectra by deconvolving the correction vectors. Our approach represents a step towards simulating the X-ray spectroscopies of larger metal cluster systems that play a pivotal role in biology.

physics.chem-ph↗