arXiv subjects

Geonwoo Kim

Publications and source records attributed to Geonwoo Kim.

9 recordsLinked to original sources

arXiv2026

Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection

Industrial Internet of Things (IIoT) edge pipelines routinely lose contiguous blocks of multi-sensor data to network dropouts and hardware faults. The standard remedy is a disjointed "impute-then-detect" pipeline whose imputer is trained only for Mean Squared Error (MSE). Such an imputer fills a missing block with the most probable normal pattern: a partially observed anomaly is smoothed back toward normality, and boundary artifacts on normal data raise false alarms. We call this imputation bias and propose the Task-Aware Diffusion Refiner (TADR), a conditional diffusion refiner trained against the loss landscape of a frozen downstream detector. Because back-propagating through the sampling trajectory is intractable, the task-aware terms act on the one-step clean-window estimate that the noise prediction already yields, so training costs no more than plain diffusion training. Under strict Point-to-Point evaluation over five seeds with paired significance tests, TADR raises F1 by $0.338$ over the unrefined detector on SMD ($p = 0.0015$), and the anomaly enhancement objective alone contributes $0.463$ in ablation. We also characterise when the method helps: the gain tracks the continuous, mutually redundant channels available and the anomaly evidence the outage removes, and it is absent on telemetry datasets dominated by one-hot command channels and on PSM. At ten sampling steps TADR runs in $41.4$ ms per window on a single CPU core, sustaining about $24$ concurrent 1 Hz streams from a $4.03$ MB model. Code and per-seed results are available at https://github.com/int-park422/TADR.

cs.LG↗

arXiv2026

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods condition on a single reference image and must therefore infer the subject's unseen appearance and geometry as the viewpoint changes. To address this limitation, recent methods extend S2V to multiple reference views, providing more information about the subject from different viewpoints. However, they do not explicitly specify the 3D structure that connects these observations. In addition, existing training data do not guarantee that viewpoint changes preserve the same underlying 3D subject. We present OmniShowcase, built on two components: (i) a fully automated data synthesis pipeline that produces training videos along diverse camera trajectories, with viewpoint variation driven by underlying subject geometry, even spanning full 360-degree orbits; and (ii) a geometry-conditioning method that provides the video model with a turntable of surface-normal maps reconstructed from the reference views without requiring temporal alignment with the generated frames. We construct Showcase-4K, a corpus of 3D-asset-based videos covering twelve camera motions across 88 trajectory configurations with reconstruction-derived surface-normal conditioning, and ShowcaseBench, a held-out evaluation set with the source meshes and camera parameters used to render each video. Experiments show state-of-the-art subject identity and 3D consistency while maintaining competitive video quality and motion. Project page: justin4ai.github.io/OmniShowcase

cs.CV↗

arXiv2026

Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs

Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which preserved record supports that finding. Tool logs, generated explanations, and local citation identifiers capture different parts of this evidence, yet a citation identifier does not establish a source unless its binding to a record is preserved. We audit this distinction using 64 mechanically checkable cases from saved AgentDojo Banking executions. Two LLM readers reconstruct source relationships under controlled variations in visible evidence and identifier-to-record bindings. We separately evaluate complete-record agreement, evidence-grounded findings, justified abstention, and unsupported assertions. With original identifiers and no binding table, Sonnet recovered every literal source location but made unsupported citation-source assertions in 26 of 28 cases requiring the missing relation; 22 nevertheless matched the complete reference. Adding explicit bindings improved grounded reconstruction for both readers, whereas identifier renaming alone provided no consistent remedy. A deterministic same-packet comparator correctly resolved the bounded task or abstained throughout. These results show that factual agreement alone is insufficient for evaluating forensic reconstruction of agent logs and motivate preserving explicit record bindings to distinguish supported findings from correct guesses.

cs.CR↗

arXiv2026

When Valid Tool Calls Change Meaning: Formation-Consistent Dispatch for LLM Agents

Tool-enabled agents form calls from model-visible interfaces, while hosts later select their implementation. Standard dispatch omits the descriptor-handler relation. An unchanged and schema-valid call can therefore acquire a different security effect during rollout, reconnect, or delayed approval. We call this failure schema-epoch drift. We present formation-consistent dispatch (FCD), which connects implementation analysis to execution authority. Reviewed profiles produce provenance-bound over-approximations of declared in-scope effects from official source. Under a closed-target approval policy, a verifier applies each formed call to a summary and captures a successor only when its effects fit the call's security contract. Atomic admission and a final-hop fence preserve this decision to the effect. The exact source retains priority, and the captured successor becomes eligible only after source retirement. Stock releases and deployment changes reproduced the failure. Four profiles covered 32 official releases: 29 required no release-specific change and three escalated. A frozen 16-release expansion matched a separate source oracle. In a preregistered stock comparison, FCD completed all three pending calls whose effect remained private and blocked all three whose omission became public. Exact pinning and release-wide denial stopped all six calls, while release-wide approval completed all six but produced three public effects. A separate lifecycle experiment carried a formation-captured certificate across source retirement. The same safe certificate installed later governed new formations without expanding the pending call's authority.

cs.AI↗

arXiv2026

Sling2Sim2Real: One-Shot Elastic System Identification for Non-Destructive Slingshot Policy Learning

Elastic object manipulation (EOM) involves highdimensional, nonlinear, and elastic deformations. The diverse deformation properties of elastic objects substantially expand the relevant state space, requiring extensive exploration to learn accurate manipulation policies for tasks such as slingshot manipulation. While simulation enables large-scale and safe exploration compared to costly and potentially destructive real-world trials (e.g., repeated projectile launches), accurately calibrating elastic behavior between the real world and simulation remains challenging since elastic properties are largely indistinguishable from visual observations alone. To address these challenges, we propose Sling2Sim2Real, a one-shot Real2Sim2Real framework that identifies elastic parameters from a single non-destructive interaction and enables policy learning in simulation. The framework consists of two stages: 1) a multi-start Real2Sim system identification method that exploits parameter covariance to estimate elastic properties, and 2) simulation-based policy learning followed by zero-shot Sim2Real transfer using the calibrated simulator. We evaluate Sling2Sim2Real on a slingshot manipulation task using a Franka Emika Panda arm and elastic bands with diverse physical properties across varying target distances. Experimental results demonstrate that Sling2Sim2Real achieves accurate policy learning and robust generalization while significantly reducing the amount of required real-world interaction.

cs.RO↗

arXiv2025

FRAG: Frequency Adapting Group for Diffusion Video Editing

In video editing, the hallmark of a quality edit lies in its consistent and unobtrusive adjustment. Modification, when integrated, must be smooth and subtle, preserving the natural flow and aligning seamlessly with the original vision. Therefore, our primary focus is on overcoming the current challenges in high quality edit to ensure that each edit enhances the final product without disrupting its intended essence. However, quality deterioration such as blurring and flickering is routinely observed in recent diffusion video editing systems. We confirm that this deterioration often stems from high-frequency leak: the diffusion model fails to accurately synthesize high-frequency components during denoising process. To this end, we devise Frequency Adapting Group (FRAG) which enhances the video quality in terms of consistency and fidelity by introducing a novel receptive field branch to preserve high-frequency components during the denoising process. FRAG is performed in a model-agnostic manner without additional training and validates the effectiveness on video editing benchmarks (i.e., TGVE, DAVIS).

cs.CV↗

arXiv2024

Double/Debiased CoCoLASSO of Treatment Effects with Mismeasured High-Dimensional Control Variables

We develop an estimator for treatment effects in high-dimensional settings with additive measurement error, a prevalent challenge in modern econometrics. We introduce the Double/Debiased Convex Conditioned LASSO (Double/Debiased CoCoLASSO), which extends the double/debiased machine learning framework to accommodate mismeasured covariates. Our principal contributions are threefold. (1) We construct a Neyman-orthogonal score function that remains valid under measurement error, incorporating a bias correction term to account for error-induced correlations. (2) We propose a method of moments estimator for the measurement error variance, enabling implementation without prior knowledge of the error covariance structure. (3) We establish the $\sqrt{N}$-consistency and asymptotic normality of our estimator under general conditions, allowing for both the number of covariates and the magnitude of measurement error to increase with the sample size. Our theoretical results demonstrate the estimator's efficiency within the class of regularized high-dimensional estimators accounting for measurement error. Monte Carlo simulations corroborate our asymptotic theory and illustrate the estimator's robust performance across various levels of measurement error. Notably, our covariance-oblivious approach nearly matches the efficiency of methods that assume known error variance.

econ.EM↗

arXiv2020

The contact geometry of the spatial circular restricted 3-body problem

We show that a hypersurface of the regularized, spatial circular restricted three-body problem is of contact type whenever the energy level is below the first critical value (the energy level of the first Lagrange point) or if the energy level is slightly above it. A dynamical consequence is that there is no blue sky catastrophe in this energy range.

math.SG↗

arXiv2019

Consistent and Efficient Pricing of SPX and VIX Options under Multiscale Stochastic Volatility

This study provides a consistent and efficient pricing method for both Standard & Poor's 500 Index (SPX) options and the Chicago Board Options Exchange's Volatility Index (VIX) options under a multiscale stochastic volatility model. To capture the multiscale volatility of the financial market, our model adds a fast scale factor to the well-known Heston volatility and we derive approximate analytic pricing formulas for the options under the model. The analytic tractability can greatly improve the efficiency of calibration compared to fitting procedures with the finite difference method or Monte Carlo simulation. Our experiment using options data from 2016 to 2018 shows that the model reduces the errors on the training sets of the SPX and VIX options by 9.9% and 13.2%, respectively, and decreases the errors on the test sets of the SPX and VIX options by 13.0\% and 16.5\%, respectively, compared to the single-scale model of Heston. The error reduction is possible because the additional factor reflects short-term impacts on the market, which is difficult to achieve with only one factor. It highlights the necessity of modeling multiscale volatility.

q-fin.MF↗