Searcharxiv⌕ Search

arXiv subjects

Jihun Kim

Publications and source records attributed to Jihun Kim.

At least 19 recordsLinked to original sources

Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks

Structured low-rank and sparse-plus-low-rank parameterizations, motivated by methods such as LoRA and low-rank factorization, impose strong structural constraints on the linear transformations within neural networks. We study the expressive consequences of these constrained structures from the perspective of universal approximation. We first characterize that purely low-rank neural networks, despite being able to exactly interpolate arbitrary finite scalar datasets, can fail to approximate continuous functions that vary along directions ignored by the low-rank hidden mapping. We show that augmenting the low-rank structure with a one-parameter diagonal component suffices to overcome this geometric bottleneck, yielding a Diagonal-plus-Low-Rank (DLoR) structure. We show that a full-rank linear transformation can be reconstructed using DLoR components either by expanding network width through additive decomposition or by extending network depth through multiplicative decomposition. We term this correspondence between additive width expansion and multiplicative depth extension the Structural Correspondence framework. By combining these constructions with local linearization of the activation function, we prove that DLoR neural networks restore universal approximation for general activation functions. These results characterize how architectural width and depth can compensate for severe rank constraints without requiring unrestricted dense hidden transformations. Diagonal terms are required for multiplicative construction, while additive expansion works with purely low-rank terms. We further determine its exact cost: both the minimal number of rank-$r$ DLoR factors representing $W$ and the minimal network depth for that layer equal $\lceilκ(W)/r\rceil$, where $κ(W)=\min_{γ\ne0}rank(W-γI)$, achieving a lower cost than its dense representation when $W$ is identity-centered.

cs.LG↗

Defense Filters for Robust Learning of Partially Observed Dynamical Systems

Robust estimation of unknown system dynamics from partial observations under attack is a core challenge in learning for control, increasingly critical in multi-agent networks subject to adversarial data poisoning. Existing methods either require highly restrictive assumptions on the adversary or yield weak error bounds. In this paper, we consider identifying partially observed linear dynamical systems subject to adversarial attacks with an attack probability $p < 0.5$ at each time. We propose a defense-filtering framework leveraging knowledge of the observation matrix to construct a defense filter satisfying full column rank and subspace separability conditions, which enables the evaluation of a single-attack scenario against observed data. Using this framework, we analyze the constrained $\ell_2$-norm estimator and establish finite-sample error bounds for recovering the Markov parameter matrix up to a linear transformation. This is the first approach to provide provable system identification guarantees via a defense filter for partially observed systems subject to harsh environments where the attack probability approaches $0.5$.

math.OC↗

Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks

System identification in modern engineering systems faces emerging challenges from unanticipated adversarial attacks beyond existing detection mechanisms. In this work, we obtain a provably accurate estimate of the Markov parameter matrix of order $k$ to identify partially observed linear systems, in which the probability $p$ of having an attack at each time is smaller than $0.5$. We show that given the batch data accumulated up to time $T^*$, the $\ell_2$-norm estimator achieves an error with stepwise exponential decay as the attack probability $p$ decreases. Furthermore, low-dimensional attack structures can decouple the exponential decay order from the attack probability $p$, achieving an error decay that scales with $T^*$. We then propose a stochastic projected subgradient descent algorithm on streaming data that produces an estimate at each time $t<T^*$, in which case the expected estimation error proves to be the larger of $\mathcal{O}(k/\sqrt{t})$ and the baseline error of the $\ell_2$-norm estimator at $T^*$. This stochastic approach illustrates how non-smooth estimators can leverage first-order methods despite lacking recursive formulas. Finally, we integrate batch and streaming estimations to recover the Hankel matrix using the appropriate estimates of the Markov parameter matrix, which enables the synthesis of a robust adaptive controller based on the estimated balanced truncated model under adversarial attacks.

math.OC↗

Dynamic Auction Mechanisms in a Closed-Credit Economy: Sequential Slot Reallocation in Air Traffic Management

Indivisible resources allocated in advance may need to be reallocated when capacity reductions make existing assignments infeasible, yet monetary compensation is often impractical or undesirable. We develop a sequential resource reallocation scheme using reusable artificial credits, where agents hold pre-existing resource rights and have heterogeneous marginal valuations over time blocks. Capacity reductions produce fractional endowments, which our closed-credit scheme resolves into indivisible final allocations. We model agents' intertemporal preferences through a predicted-value-to-go function and characterize conditions ensuring that their optimal demand is non-increasing in price. We propose an ascending-auction mechanism that partitions agents into subgroups and uses the minimum subgroup market-clearing price as a common transaction price. We show that the mechanism preserves non-myopic individual rationality and weak nontrader neutrality. Moreover, we establish Pareto efficiency under optimal-demand clearing in the unified market and bound the expected gain from misreporting by the probability that an agent changes the common price. Simulations of airport slot reallocation demonstrate reductions in total modeled delay and cancellation costs relative to a ground-delay baseline.

cs.GT↗

Partially Observable Zero-shot coordination by Predicting Intention of Partner

Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting Intention of Partner (PIP) to jointly address these challenges. PIP uses a Joint-view VAE to distill richer training-time evidence from the union of both agents' local observations into a partner representation available from local observations alone. Partner-state Belief networks further infer the partner's hidden location and behavioral tendencies from the ego agent's interaction history. We evaluate PIP in Burrito-PO, Overcooked-PO, and a Melting Pot substrate, together with a human evaluation in Burrito-PO. PIP attains the highest mean performance among the compared methods across all three benchmarks. Human evaluation and diagnostic analyses further support coordination with unseen partners and the contributions of both components under partner occlusion.

cs.AI↗

SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs

This work presents SeedFlood, a new approach to decentralized LLM fine-tuning designed to scale across large models, large collaborations, and complex network topologies while achieving global consensus with negligible communication overhead. Traditional methods suffer from high communication costs that grow with model size, while information decay over network hops renders global consensus inefficient. SeedFlood takes a significant departure from these practices by exploiting the seed-reconstructible structure of zeroth-order gradients and effectively making the messages to transmit near-zero in size, allowing them to be flooded to every client in the network, and thereby enhancing scalability of decentralized training. Consequently, SeedFlood enables training in regimes previously considered impractical, such as billion-parameter scale models or distributed across hundred of clients. Our experiments on decentralized LLM fine-tuning demonstrate that SeedFlood consistently outperforms the standard zeroth-order baselines in both communication efficiency and generalization performance, and even achieves results comparable to first-order gossip-based methods in large-scale settings, while requiring orders-of-magnitude less communication cost. We also provide theoretical analysis to formalize that SeedFlood avoids topology-dependent consensus terms in the convergence bound while retaining the acceleration enabled by increased client participation.

cs.LG↗

Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models

Progress in 4D LiDAR segmentation is bottlenecked by data. Assigning temporally consistent labels across sparse point cloud sequences is costly and hard to scale, and every new task or domain tends to demand fresh dense annotation. This motivates a simple question of whether high-quality LiDAR training data can be produced automatically, without any human labeling. To this end, we introduce LiDAR-SAM2, a framework that turns a 2D video foundation model, SAM2, into a scalable source of supervision for the 4D LiDAR domain. On the data side, it automatically generates temporally coherent LiDAR-level labels from SAM2 video masks through multi-view projection and spatio-temporal aggregation. On the modeling side, a tailored modality interface and a two-stage learning objective adapt SAM2's video segmentation kernel to spatio-temporal LiDAR structure, so that a single click per object yields a consistent mask track across the sequence. Trained with no human LiDAR annotation, LiDAR-SAM2 produces semantic and panoptic labels on SemanticKITTI that approach the quality of full human annotation from only a few points, and models trained on these labels approach the performance of full ground-truth supervision. This positions LiDAR-SAM2 as a scalable labeling tool that substantially reduces the annotation burden for 3D and 4D scene understanding.

cs.CV↗

Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement

Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. However, OVSS performance often degrades in specialized domains such as medical imaging, remote sensing, and industrial inspection, where dense pixel-level masks for adaptation are costly to obtain and require domain-specific expertise. We propose a preference-guided adaptation framework that replaces dense mask supervision with binary preferences. We observe that different prompt templates produce systematically different segmentations for the same image, a phenomenon we call prompt disagreement, and we repurpose it as a built-in source of preference supervision. Building on this, we mine localized preference queries from regions of high cross-template uncertainty, and adapt the OVSS model with Region-Localized Preference Optimization (RLPO) together with consistency regularization that stabilizes updates outside the queried region. Across extensive experiments on the MESS benchmark, the proposed method achieves consistent gains across diverse OVSS backbones without any pixel-level annotation, and remains effective under noisy preferences. Our code is available at https://github.com/blue-531/pref-ovss.

cs.CV↗

A class of generalised Killing spinors determined by the Ricci tensor and the metric

We introduce a class of generalised Killing spinors, termed affine Killing spinors (AKS), for which the associated endomorphism is a constant linear combination of the Ricci endomorphism and the identity map. We classify Riemannian spin manifolds admitting an AKS under two additional curvature hypotheses: harmonic curvature and local conformal flatness. Furthermore, we characterise Riemannian spin manifolds that admit a non-zero parallel one-form and an AKS. Additionally, we prove that in dimension three every curvature-homogeneous manifold carrying an AKS is locally homogeneous. Finally, we provide a complete classification of three-dimensional Lie groups equipped with a Bianchi metric admitting an invariant AKS.

math.DG↗

Huber-based Robust System Identification with Near-Optimal Guarantees Across Independent and Adversarial Regimes

Dynamical systems can confront one of two extreme types of disturbances: persistent zero-mean independent noise, and sparse nonzero-mean adversarial attacks, depending on the specific scenario being modeled. While mean-based estimators like least-squares are well-suited for the former, a median-based approach such as the $\ell_1$-norm estimator is required for the latter. In this paper, we propose a Huber-based estimator, characterized by a threshold constant $μ$, to identify the governing matrix of a linearly parameterized nonlinear system from a single trajectory of length $T$. This formulation bridges the gap between mean- and median-based estimation, achieving provably robust error in both extreme disturbance scenarios under mild assumptions. In particular, for persistent zero-mean noise with a positive probability density around zero, the proposed estimator achieves an $\mathcal{O}(1/\sqrt{T})$ error rate if the disturbance is symmetric or the basis functions are linear. For arbitrary nonzero-mean attacks that occur at each time with probability smaller than 0.5, the error is bounded by $\mathcal{O}(μ)$. We validate our theoretical results with experiments illustrating that integrating our approach into frameworks like SINDy yields robust identification of discrete-time systems.

math.OC↗

Phase Retrieval in $\mathbb C^4$ Requires Exactly Eleven Measurements

Determining the minimal number of intensity measurements required for phase retrieval in $\mathbb{C}^4$ has been a long-standing open problem. Prior to this work, the best-known results implied that this minimum was either $10$ or $11$. In this paper, we leverage characteristic classes and cohomology groups from differential topology to prove that no family of $10$ vectors in $\mathbb{C}^4$ possesses the phase retrieval property. Combining our lower bound with Vinzant's explicit eleven-vector construction establishes that the exact minimum is $11$. Our result yields a significant consequence for pure state quantum tomography, namely, a rank-one POVM on $\mathbb{C}^4$ requires exactly $11$ elements to be informationally complete for pure states. This further implies that three orthonormal bases are insufficient to uniquely distinguish all pure states in $\mathbb{C}^4$. Because four orthonormal bases are already known to be sufficient, we conclude that exactly four bases are required, thereby completely resolving the problem left in [C. Carmeli, T. Heinosaari, J. Schultz, A. Toigo, Eur. Phys. J. D].

quant-ph↗

System Identification under Noise and Attack Regimes: Agnostic and Composite Robustness

Dynamical systems often confront persistent zero-mean independent noise and/or sparse nonzero-mean adversarial attacks. While mean-based estimators like least-squares handle the former, the median-based $\ell_1$-norm estimator is effective for the latter. In this paper, we develop robust system identification frameworks to identify a linearly-parametrized nonlinear system from a single trajectory of length $T$. We tackle two types of robustness: (1) $\textit{agnostic robustness}$ under either pure noise or pure attacks without knowing which regime is active; and (2) $\textit{composite robustness}$ under concurrent noise and attacks. We first show that the Huber estimator attains agnostic robustness by achieving an $\mathcal{O}(1/\sqrt{T})$ error rate for the noise regime and a bounded error for the attack regime, serving as a one-stage estimator interpolating between mean- and median-based methods. We then prove that no convex one-stage estimator is consistent under both noise and attacks, which motivates a two-stage estimation that sequentially applies median- and mean-based estimators for composite robustness. These dual notions of robustness require a corresponding duality in estimator design, providing a solid foundation for robust control in safety-critical systems.

math.OC↗

Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning

Early detection of dental caries remains challenging due to limitations in traditional diagnostic methods, particularly for proximal lesions in posterior teeth. Deep learning models show promise for automated caries detection but face scalability constraints due to requirements for large volumes of expertly annotated training data. This study presents a dual-stage deep learning framework combining Faster R-CNN for tooth localization with U-Net for pixel-wise caries segmentation in panoramic radiographs. We developed a systematic transformation pipeline to convert large-scale polygon-annotated datasets into high-resolution binary segmentation masks, enabling pixel-wise supervised learning. The framework was trained using both expert-verified datasets and algorithmically processed labels from 3,000 panoramic images. Our approach achieved robust performance with an IoU of 0.9013, Dice coefficient of 0.9482, Recall of 0.9433, and Precision of 0.9774, demonstrating superior accuracy compared to existing methods while significantly reducing false-positive rates. The dual-stage framework effectively addresses data annotation bottlenecks in dental AI applications and demonstrates potential for scalable, automated caries detection systems that can improve diagnostic consistency and support clinical decision-making.

cs.CV↗

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

Continual Test-Time Adaptation (CTTA) aims to maintain model performance under evolving target domains by adapting online without labeled data. However, practical deployments often cannot retain the source dataset due to privacy or licensing constraints, and purely source-free CTTA methods tend to become unstable under long-term distribution shift, suffering from compounding self-training errors and catastrophic forgetting. We introduce DO-ALL (Distill Once, Adapt Life-Long), a plug-and-play framework that revisits source information in a compact and privacy-conscious form via Dataset Distillation (DD). Before deployment, DO-ALL performs DD to produce a small set of synthetic distilled anchors that summarize the source distribution. During adaptation, each target sample is matched with its most semantically aligned anchor, which provides a stable reference for various CTTA via source replay, representation alignment, and manifold-smoothing regularization. DO-ALL can be seamlessly integrated into existing CTTA algorithms, consistently improving long-term robustness across CIFAR100-C, ImageNet-C, and the CCC benchmark. This demonstrates the potential of leveraging DD to enable stable and continuous adaptation without retaining raw source data. The code is available at https://github.com/blue-531/DOALL.

cs.CV↗

On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks

This paper is concerned with learning the input-output mapping of general nonlinear dynamical systems. While the existing literature focuses on Gaussian inputs and benign disturbances, we significantly broaden the scope of admissible control inputs and allow correlated, nonzero-mean, adversarial disturbances. With our reformulation as a linear combination of basis functions, we prove that the $\ell_2$-norm estimator overcomes the challenges posed by an adversary with access to the full information history, provided that the attack times are sparse, i.e., the probability that the system is under adversarial attack at a given time is smaller than a certain threshold. We provide an estimation error bound that decays with the input memory length and prove its optimality by constructing a problem instance that suffers from the same bound under probabilistic adversarial attacks. Our work provides a sharp input-output analysis for a generic nonlinear and partially observed system under significantly generalized assumptions compared to existing works.

math.OC↗

DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation

Interactive segmentation (IS) allows users to iteratively refine object boundaries with minimal cues, such as positive and negative clicks. While the Segment Anything Model (SAM) has garnered attention in the IS community for its promptable segmentation capabilities, it often struggles in specialized domains or when handling complex scenarios (e.g., camouflaged or multi-part objects). To overcome these challenges, we propose DC-TTA, a novel test-time adaptation (TTA) framework that adapts SAM on a per-sample basis by leveraging user interactions as supervision. Instead of forcing a single model to incorporate all user clicks at once, DC-TTA partitions the clicks into more coherent subsets, each processed independently via TTA with a separated model. This Divide-and-Conquer strategy reduces conflicts among diverse cues and enables more localized updates. Finally, we merge the adapted models to form a unified predictor that integrates the specialized knowledge from each subset. Experimental results across various benchmarks demonstrate that DC-TTA significantly outperforms SAM's zero-shot results and conventional TTA methods, effectively handling complex tasks such as camouflaged object segmentation with fewer interactions and improved accuracy.

cs.CV↗