arXiv subjects

Soyeon Park

Publications and source records attributed to Soyeon Park.

16 recordsLinked to original sources

arXiv2026

A Locally Tokenized Generative Model for Robust Time-Series Watermarking

Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under post-editing attacks. We show that existing detectors, which rely on globally coupled re-encoding, suffer from bidirectional drift of the null distribution: post-editing attacks can shift the z-score of non-watermarked samples in either direction, invalidating clean-calibrated thresholds. We argue that this instability is a property of the re-encoding, and that reliable detection requires each recovered unit to depend only on a bounded temporal neighborhood. Guided by this principle, we propose L-VQVAE, a generative model in which each discrete token is produced from a short contiguous window, and LVQMark, a watermarking method over this token space that combines logit-bias injection with robust re-encoding for attack-time detection. Experiments on four benchmarks spanning finance, energy, and neuroimaging show that our approach preserves generation quality while stabilizing both detection power and false-positive behavior under post-editing attacks.

cs.LG↗

arXiv2026

Leveraging Pathology Co-occurrence for Test-Time Adaptation in Chest X-Ray Diagnosis

Medical imaging models often degrade when deployed at new clinical sites due to differences in imaging equipment, protocols, and patient populations. Test-time adaptation (TTA) addresses this by updating a pretrained model using only unlabeled target data, without access to source data. However, existing TTA methods were designed for single-label classification on natural image benchmarks, minimizing entropy uniformly across all samples without considering label dependencies. This overlooks a key property of multi-label medical imaging: pathologies do not occur independently but exhibit structured co-occurrence patterns. In this work, we propose Co-occurrence Weighted Adaptation (CoWA), which leverages disease co-occurrence patterns as a reliability signal for adaptation. CoWA estimates label co-occurrence structure from model predictions and downweights samples that deviate from expected patterns, enabling adaptation to rely more on consistent predictions while reducing the impact of noisy ones. We evaluate CoWA on chest X-ray benchmarks under domain shifts and demonstrate consistent improvements over established baselines.

cs.CV↗

arXiv2026

Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction

Clinical time series prediction in intensive care units remains challenging due to heterogeneous physiological variables and informative missingness. The presence or absence of a measurement can reflect clinical decisions and patient severity, and thus missingness can serve as a predictive signal rather than a simple data artifact. This work presents CISM, a Channel-Independent Spectrogram framework with a Missingness stream for clinical multivariate time series prediction. CISM converts each clinical variable into a variable-wise time-frequency spectrogram, preserves variable identity through variable-aligned encoding, and aligns an explicit missingness stream with the spectrogram representation. Experiments on an in-hospital mortality task derived from MIMIC-IV show that CISM achieves the highest mean AUROC (0.7225), AUPRC (0.3308), and F1 (0.3808) among the compared time series, missingness-aware, vision, and time-frequency baselines. Ablation studies further show that observation patterns provide a meaningful informative signal. Pixel-level mask injection improves performance over plain spectrogram inputs and recovers much of this predictive value. The aligned missingness stream contributes a further, complementary gain in both AUROC and AUPRC. These results highlight the importance of modeling observation patterns as structured signals in clinical time series prediction.

cs.LG↗

arXiv2026

SPINE: Bridging the Cyber-Physical Gap with Agentic AI

Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spinal cord, remains a primary bottleneck to scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise): an agentic framework for systematically debugging and deploying bimanual robots with minimal robotics expertise. SPINE's harness comprises two orchestrated multi-agent workflows: a profile builder that creates robot-specific context, and a debugger that cycles through diagnosis, repair, and validation until teleoperation works. Across seven DOBOT X-Trainer debugging scenarios, a robotics novice using SPINE outperformed human operators using Claude Code with the same reference materials, but without SPINE's structured workflow, improving operationalization success from 75% to 100% and reducing mean time-to-teleoperation from 16 min 45 s to 13 min 47 s. On AgileX PiPER, a distinct ROS/CAN bimanual arm, SPINE resolved all 10 implanted bugs, versus 9 out of 10 for the expert baseline, in nearly the same amount of time. Together, these results show that SPINE can transfer across bimanual platforms, reduce dependence on expert calibration, and move embodied AI closer to scalable real-world deployment.

cs.AI↗

arXiv2026

Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives

We propose a framework for reward allocation in fully delegated AI cooperatives where humans are represented by agents that contribute data and participate in model updates under heterogeneous value constraints. The key idea is to credit only those updates that remain admissible after screening them against each principal's value profile. We formulate value-conditioned gradient filtering, online marginal contribution signals, and cumulative revenue settlement within a traversal learning (TL) substrate. TL is especially attractive here because it performs decentralized backpropagation without the quality loss associated with aggregation-centric distributed learning and, we argue, offers a finer attribution substrate than FedAvg-style federated learning by preserving explicit traversal and gradient paths. The framework is positioned against data valuation, federated contribution estimation, personalized federated learning, and pluralistic alignment.

cs.LG↗

arXiv2026

Channel-wise Retrieval for Multivariate Time Series Forecasting

Multivariate time series forecasting often struggles to capture long-range dependencies due to fixed lookback windows. Retrieval-augmented forecasting addresses this by retrieving historical segments from memory, but existing approaches rely on a channel-agnostic strategy that applies the same references to all variables. This neglects inter-variable heterogeneity, where different channels exhibit distinct periodicities and spectral profiles. We propose CRAFT (Channel-wise retrieval-augmented forecasting), a novel framework that performs retrieval independently for each channel. To ensure efficiency, CRAFT adopts a two-stage pipeline: a sparse relation graph constructed in the time domain prunes irrelevant candidates, and spectral similarity in the frequency domain ranks references, emphasizing dominant periodic components while suppressing noise. Experiments on seven public benchmarks demonstrate that CRAFT outperforms state-of-the-art forecasting baselines, achieving superior accuracy with practical inference efficiency.

cs.LG↗

arXiv2026

Multimodal Forecasting for Commodity Prices Using Spectrogram-Based and Time Series Representations

Forecasting multivariate time series remains challenging due to complex cross-variable dependencies and the presence of heterogeneous external influences. This paper presents Spectrogram-Enhanced Multimodal Fusion (SEMF), which combines spectral and temporal representations for more accurate and robust forecasting. The target time series is transformed into Morlet wavelet spectrograms, from which a Vision Transformer encoder extracts localized, frequency-aware features. In parallel, exogenous variables, such as financial indicators and macroeconomic signals, are encoded via a Transformer to capture temporal dependencies and multivariate dynamics. A bidirectional cross-attention module integrates these modalities into a unified representation that preserves distinct signal characteristics while modeling cross-modal correlations. Applied to multiple commodity price forecasting tasks, SEMF achieves consistent improvements over seven competitive baselines across multiple forecasting horizons and evaluation metrics. These results demonstrate the effectiveness of multimodal fusion and spectrogram-based encoding in capturing multi-scale patterns within complex financial time series.

cs.LG↗

arXiv2026

Hierarchical Latent Space Item Response Model for Analyzing Mental Health Vulnerability of Elementary School Students in South Korea

Mental health difficulties among elementary school students represent a growing public health concern in South Korea, yet analytical tools for identifying school-specific vulnerability patterns from item response data remain limited. We propose the hierarchical latent space item response model (HLSIRM), which adds hierarchical respondent effects and an inner-product latent interaction for signed respondent-item associations, yielding a unified interaction map that separates school, individual main effects from school/individual-item interactions. We apply HLSIRM to mental health vulnerability data from 2,210 elementary school students across 35 schools in Incheon, South Korea. Clustering item vectors by directional similarity identifies four empirically derived vulnerability domains. School-level analysis reveals that the absence of counseling experience is the primary vulnerability domain aligned with most school vectors, while stress, depression, and smartphone dependency concentrate in specific schools. Within-school analysis demonstrates how individual student positions in the interaction map translate into targeted intervention strategies that address school-specific needs.

stat.AP↗

arXiv2025

Adaptive Information Routing for Multimodal Time Series Forecasting

Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in practical scenarios, this is often insufficient for accurate predictions due to the limited information available. To address this challenge, multimodal time series forecasting methods which incorporate additional data modalities, mainly text data, alongside time series data have been explored. In this work, we introduce the Adaptive Information Routing (AIR) framework, a novel approach for multimodal time series forecasting. Unlike existing methods that treat text data on par with time series data as interchangeable auxiliary features for forecasting, AIR leverages text information to dynamically guide the time series model by controlling how and to what extent multivariate time series information should be combined. We also present a text-refinement pipeline that employs a large language model to convert raw text data into a form suitable for multimodal forecasting, and we introduce a benchmark that facilitates multimodal forecasting experiments based on this pipeline. Experiment results with the real world market data such as crude oil price and exchange rates demonstrate that AIR effectively modulates the behavior of the time series model using textual inputs, significantly enhancing forecasting accuracy in various time series forecasting tasks.

cs.LG↗

arXiv2025

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 2025). AIxCC (2023-2025) challenged teams to build autonomous cyber reasoning systems capable of discovering and patching vulnerabilities at the speed and scale of modern software. ATLANTIS integrates large language models (LLMs) with program analysis -- combining symbolic execution, directed fuzzing, and static analysis -- to address limitations in automated vulnerability discovery and program repair. Developed by researchers at Georgia Institute of Technology, Samsung Research, KAIST, and POSTECH, the system addresses core challenges: scaling across diverse codebases from C to Java, achieving high precision while maintaining broad coverage, and producing semantically correct patches that preserve intended behavior. We detail the design philosophy, architectural decisions, and implementation strategies behind ATLANTIS, share lessons learned from pushing the boundaries of automated security when program analysis meets modern AI, and release artifacts to support reproducibility and future research.

cs.CR↗

arXiv2024

Mesoscopic Stacking Reconfigurations in Stacked van der Waals Film

Mesoscopic-scale stacking reconfigurations are investigated when van der Waals films are stacked. We have developed a method to visualize complicated stacking structures and mechanical distortions simultaneously in stacked atom-thick films using Raman spectroscopy. In the rigid limit, we found that the distortions originate from the transfer process, which can be understood through thin film mechanics with a large elastic property mismatch. In contrast, with atomic corrugations, the in-plane strain fields are more closely correlated with the stacking configuration, highlighting the impact of atomic reconstructions on the mesoscopic scale. We discovered that the grain boundaries don`t have a significant effect while the cracks are causing inhomogeneous strain in stacked polycrystalline films. This result contributes to understanding the local variation of emerging properties from moiré structures and advancing the reliability of stacked vdW material fabrication.

cond-mat.mtrl-sci↗

arXiv2023

Can We Utilize Pre-trained Language Models within Causal Discovery Algorithms?

Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal relationships between variables utilizing data. Recently, there has been current research regarding a method that mimics causal discovery by aggregating the outcomes of repetitive causal reasoning, achieved through specifically designed prompts. It highlights the usefulness of PLMs in discovering cause and effect, which is often limited by a lack of data, especially when dealing with multiple variables. Conversely, the characteristics of PLMs which are that PLMs do not analyze data and they are highly dependent on prompt design leads to a crucial limitation for directly using PLMs in causal discovery. Accordingly, PLM-based causal reasoning deeply depends on the prompt design and carries out the risk of overconfidence and false predictions in determining causal relationships. In this paper, we empirically demonstrate the aforementioned limitations of PLM-based causal reasoning through experiments on physics-inspired synthetic data. Then, we propose a new framework that integrates prior knowledge obtained from PLM with a causal discovery algorithm. This is accomplished by initializing an adjacency matrix for causal discovery and incorporating regularization using prior knowledge. Our proposed framework not only demonstrates improved performance through the integration of PLM and causal discovery but also suggests how to leverage PLM-extracted prior knowledge with existing causal discovery algorithms.

cs.AI↗

arXiv2022

Mapping the Pathways of Photo-induced Ion Migration in Organic-inorganic Hybrid Halide Perovskites

Organic-inorganic hybrid perovskites (OIHPs) exhibiting exceptional photovoltaic and optoelectronic properties are of fundamental and practical interest, owing to their tunability and low manufacturing cost. For practical applications, however, challenges such as material instability and the photocurrent hysteresis occurring in perovskite solar cells under light exposure need to be understood and addressed. While extensive investigations have suggested that ion migration is a plausible origin of these detrimental effects, detailed understanding of the ion migration pathways remains elusive. Here, we report the characterization of photo-induced ion migration in OIHPs using \textit{in situ} laser illumination inside a scanning electron microscope, coupled with secondary electron imaging, energy-dispersive X-ray spectroscopy and cathodoluminescence with varying primary electron energies. Using methylammonium lead iodide (MAPbI$_3$), formamidinium lead iodide (FAPbI$_3$) and hybrid formamidinium-methylammonium lead iodide as model systems, we observed photo-induced long-range migration of halide ions over hundreds of micrometers and elucidated the transport pathways of various ions both near the surface and inside the bulk of the OIHPs, including a surprising finding of the vertical migration of lead ions. Our study provides insights into ion migration processes in OIHPs that can aid OIHP material design and processing in future applications.

physics.app-ph↗

arXiv2021

Structured electrode additive manufacturing for lithium-ion batteries

A thick electrode with high areal capacity has been developed as a strategy for high-energy-density lithium-ion batteries, but thick electrodes have difficulties in manufacturing and limitations in ion transport. Here, we reported a new manufacturing approach for ultra-thick electrode with aligned structure, called structure electrode additive manufacturing or SEAM, which aligns active materials to the through-thicknesses direction of electrodes using shear flow and a designed printing path. The ultra-thick electrodes with high loading of active materials, low tortuous structure, and good structure stability resulting from a simple and scalable SEAM lead to rapid ion transport and fast electrolyte infusion, delivering a higher areal capacity than slurry-casted thick electrodes. SEAM shows strengths in design flexibility and scalability, which allows the production of practical high energy/power density structure electrodes.

cond-mat.mtrl-sci↗

arXiv2021

Semantic-aware Binary Code Representation with BERT

A wide range of binary analysis applications, such as bug discovery, malware analysis and code clone detection, require recovery of contextual meanings on a binary code. Recently, binary analysis techniques based on machine learning have been proposed to automatically reconstruct the code representation of a binary instead of manually crafting specifics of the analysis algorithm. However, the existing approaches utilizing machine learning are still specialized to solve one domain of problems, rendering recreation of models for different types of binary analysis. In this paper, we propose DeepSemantic utilizing BERT in producing the semantic-aware code representation of a binary code. To this end, we introduce well-balanced instruction normalization that holds rich information for each of instructions yet minimizing an out-of-vocabulary (OOV) problem. DeepSemantic has been carefully designed based on our study with large swaths of binaries. Besides, DeepSemantic leverages the essence of the BERT architecture into re-purposing a pre-trained generic model that is readily available as a one-time processing, followed by quickly applying specific downstream tasks with a fine-tuning process. We demonstrate DeepSemantic with two downstream tasks, namely, binary similarity comparison and compiler provenance (i.e., compiler and optimization level) prediction. Our experimental results show that the binary similarity model outperforms two state-of-the-art binary similarity tools, DeepBinDiff and SAFE, 49.84% and 15.83% on average, respectively.

cs.CR↗

arXiv2018

libmpk: Software Abstraction for Intel Memory Protection Keys

Intel memory protection keys (MPK) is a new hardware feature to support thread-local permission control on groups of pages without requiring modification of page tables. Unfortunately, its current hardware implementation and software supports suffer from security, scalability, and semantic-gap problems: (1) MPK is vulnerable to protection-key-use-after-free and protection-key corruption; (2) MPK does not scale due to hardware limitations; and (3) MPK is not perfectly compatible with mprotect() because it does not support permission synchronization across threads. In this paper, we propose libmpk, a software abstraction for MPK. libmpk virtualizes protection keys to eliminate the protection-key-use-after-free and protection-key corruption problems while supporting a tremendous number of memory page groups. libmpk also prevents unauthorized writes to its metadata and supports inter-thread key synchronization. We apply libmpk to three real-world applications: OpenSSL, JavaScript JIT compiler, and Memcached for memory protection and isolation. An evaluation shows that libmpk introduces negligible performance overhead (<1%) compared with insecure versions, and improves their performance by 8.1x over secure equivalents using mprotect(). The source code of libmpk will be publicly available and maintained as an open source project.

cs.CR↗