arXiv subjects

Yasin Yilmaz

Publications and source records attributed to Yasin Yilmaz.

At least 19 recordsLinked to original sources

arXiv2026

Mix&Fix-Net: A Dual-Stage Trajectory Prediction Model for AIS and Vision-Derived Vessel Data

Vessel trajectory prediction is critical for maritime safety and accident prevention. While most existing trajectory prediction models rely on Automatic Identification System (AIS) data due to its precision and availability, small vessels mostly operate without AIS, resulting in a significant monitoring gap. To address this, we propose Mix&Fix-Net, a dual-stage mixer-based trajectory prediction model designed to handle vessel trajectory time-series data derived from both AIS and (non-AIS) vision data. Our architecture integrates a Primary Trajectory Predictor with a Residual Trajectory Adjuster, enabling more refined trajectory prediction. Additionally, we introduce a new video-based dataset derived from webcam streams, from which vessel trajectories are extracted to represent non-AIS data. Extensive evaluations on both AIS and non-AIS datasets across six metrics (mean squared error, mean absolute error, symmetric mean absolute percentage error, final displacement error, Frechet distance, and average Euclidean distance) demonstrate that Mix&Fix-Net consistently outperforms existing baselines across most metrics and datasets.

cs.CV↗

arXiv2026

SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving

Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent relationships rather than movement statistics alone. A child running away from a guardian, a person being carried by another, or a pursuer chasing a pedestrian across a sidewalk are all anomalous in social context, yet none produces an obvious motion signal that current anomaly detectors are equipped to flag. We introduce SENSE-VAD, the first synthetic video anomaly detection benchmark for autonomous driving explicitly designed around socially complex anomalies. Using the CARLA simulator and Unreal Engine (UE), we generate distinct anomaly scenarios across multiple categories: individual behaviors, group behaviors, person--object interactions, cyclist interactions, vehicle & agent, each annotated with per-frame binary labels. A key design principle is the separation of social anomaly from motion-based or appearance-based anomaly: many scenarios involve motion of objects that appears unremarkable in isolation but is anomalous in relational context. We additionally provide real-world normal and anomalous videos as a sim-to-real transfer probe. We evaluate state-of-the-art video anomaly detection baselines and demonstrate that socially complex anomalies constitute a distinct and currently unsolved challenge. Our dataset, annotations, and generation code are publicly available.

cs.CV↗

arXiv2026

Submission Responsibility Matters: Role-Aware Submission Quotas under Coauthorship

Author-level submission quotas are increasingly used to control growing peer-review load. Recent coauthorship-sensitive quota rules improve over fixed per-author limits by reducing the quota cost of multi-author submissions, often using harmonic authorship-credit models to prevent simple author-list padding. However, these rules conflate three distinct quantities: review burden, authorship credit, and submission responsibility. As a result, they can penalize genuine solo-authored work, treat all coauthors as equally responsible for a submission, and create bottlenecks for student-led papers when a faculty advisor appears on multiple unrelated submissions. We argue that submission quotas should be designed around the responsibility structure of a paper rather than only its number of coauthors. We formalize desiderata for quota rules, including venue-load control, padding resistance, role sensitivity, solo neutrality, and student non-blocking. We then propose a role-aware quota framework that assigns author-specific quota costs based on constrained roles such as lead author, regular coauthor, and designated advisor. The framework includes fixed, per-capita, and harmonic-style rules as special or limiting cases, while allowing venues to distinguish lead authors, corresponding authors, advisors, and peripheral contributors. We show how simple role constraints can preserve resistance to manipulation while avoiding several structural disadvantages of coauthor-symmetric quota rules. Our analysis suggests that role-aware quota mechanisms provide a more faithful and flexible foundation for managing peer-review load under modern collaborative authorship.

cs.DL↗

arXiv2026

Learning Where and When: Patch-Based Spatiotemporal Localization in Weakly Supervised Video Anomaly Detection

Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neglecting their spatial extent within frames. Yet, spatial localization is essential for interpretability and practical deployment in real-world settings. We introduce a patch-based spatiotemporal framework for weakly supervised anomaly localization that jointly models where and when anomalies occur. Our approach operates on grid-level patch features and learns region-level anomaly scores under a multiple instance learning paradigm. We further propose a Proximity-Aware Top-k spatiotemporal selection strategy that enables the model to generate fine-grained spatial anomaly maps without requiring bounding-box supervision during training. Our method surpasses existing state-of-the-art approaches across multiple benchmarks, yielding substantial gains in spatiotemporal localization accuracy. In addition, we release frame-level bounding-box annotations for the test sets of two widely used datasets, along with our code and pretrained models, providing new resources to facilitate future research in spatially grounded WSVAD.

cs.CV↗

arXiv2026

Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series

Early and accurate detection of anomalies in time-series data is critical due to the substantial risks associated with false or missed detections. While MLP-based mixer models have shown promise in time-series analysis, they do not maintain temporal causality during data processing. Moreover, real-world multivariate time series often contain numerous channels with diverse inter-channel correlations. Spurious correlations in the reconstructed time series lead to noisy representations, resulting in inaccurate anomaly detection. In addition, anomaly scoring methods that ignore temporal continuity can mislead sequential detection. To address these challenges, we propose a cluster-aware causal mixer for multivariate time-series anomaly detection. Channels are grouped into clusters based on their correlations, and each cluster is embedded through a dedicated embedding layer. A causal mixer is introduced to integrate information while maintaining temporal causality. We further develop a sequential anomaly-scoring method that accumulates evidence over time and refines anomaly boundaries. Our proposed model operates in an online fashion, making it suitable for real-time time-series anomaly detection. Experimental evaluations across six public benchmark datasets demonstrate that the proposed approach consistently achieves superior performance.

cs.LG↗

arXiv2026

Dynamic and Open-Set RF Fingerprinting and Localization in Crowded Indoor Environments through Contrastive Channel State Information Learning

Radio Frequency Fingerprinting (RFF) using deep learning has gained attention as a complementary approach to cryptographic authentication, offering resistance to spoofing, replay attacks, and key leakage. While most RFF approaches rely on In-Phase and Quadrature (IQ) samples, Channel State Information (CSI) has emerged as a more accessible alternative, enabling device authentication through physical-layer characteristics. In this work, we propose ContraCSI, a CSI-based contrastive learning framework for RFF using low-cost ESP32 devices. We investigate multiple encoder backbones, including a Vision Transformer (ViT), a lightweight 3D-CNN (Lite3D-CNN), and R3D18, to learn joint CSI and device-ID embeddings for transmitter authentication. For closed-set identification, the ViT variants achieve the best overall performance. We further study open-set authentication by applying a Geometric Entropy Minimization (GEM)-based anomaly score and sequential CUSUM (Cumulative Sum) test on embeddings learned by Lite3D-CNN-Contra, enabling rejection of unseen or non-enrolled transmitters rather than forcing a closed-set label. To evaluate robustness in highly dynamic and crowded indoor environments with human motion, multipath fading, and varying device orientations and distances, we conduct extensive experiments in a real-world setting. Our results demonstrate high authentication accuracy, strong generalization in non-ideal conditions, and effective rejection of unknown transmitters. Additionally, we explore CSI-based indoor localization via trilateration, illustrating the potential for integrated authentication and localization in practical indoor deployments.

eess.SP↗

arXiv2026

Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models

Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scenes. While this focus has led to improvements in scalability and multi-scene generalization, it has also shifted the field away from modeling the scene-specific and context-dependent nature of normal behavior. Contemporary approaches frequently rely on video-level weak supervision and opaque pretrained representations from multi-modal large language models (MLLMs), which encourage models to respond to familiar semantic anomaly categories rather than to deviations from the normal patterns of a particular environment. This trend suppresses spatial localization, introduces semantic bias, and reduces anomaly detection to a form of action recognition. In this paper, we examine whether these prevailing formulations align with the core requirements of real-world VAD, which is typically performed within a single scene where normality is determined by local geometry, semantics, and activity patterns. Through targeted visual analyses and empirical evaluations, we demonstrate the practical consequences of these limitations and show that meaningful progress in VAD requires renewed focus on single-scene, spatially-aware, and explainable formulations that capture the nuanced structure of normality within individual environments.

cs.CV↗

arXiv2026

Detecting Adversarial Data via Provable Adversarial Noise Amplification

The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathematical justification, to detect adversarial inputs and improve robustness. In this work, we study this phenomenon in detail and present a formal adversarial noise amplification theorem. We specify a set of sufficient conditions under which the adversarial noise amplification is mathematically guaranteed. Based on theoretical observations, we propose a novel training methodology with a custom spectral loss function and a specific architectural design to enhance the amplification signal for detecting adversarial data. Finally, we introduce a new, lightweight detection mechanism that leverages the enhanced amplification signal and operates entirely at inference time. To validate our approach, we demonstrate the detector's efficacy against both state-of-the-art attacks and a purpose-built adaptive attack, confirming that enhanced amplification can serve as a robust and reliable signal for adversarial defense.

cs.LG↗

arXiv2026

Improving Prostate Gland Segmentation Using Transformer based Architectures

Inter reader variability and cross site domain shift challenge the automatic segmentation of prostate anatomy using T2 weighted MRI images. This study investigates whether transformer models can retain precision amid such heterogeneity. We compare the performance of UNETR and SwinUNETR in prostate gland segmentation against our previous 3D UNet model [1], based on 546 MRI (T2weighted) volumes annotated by two independent experts. Three training strategies were analyzed: single cohort dataset, 5 fold cross validated mixed cohort, and gland size based dataset. Hyperparameters were tuned by Optuna. The test set, from an independent population of readers, served as the evaluation endpoint (Dice Similarity Coefficient). In single reader training, SwinUNETR achieved an average dice score of 0.816 for Reader#1 and 0.860 for Reader#2, while UNETR scored 0.8 and 0.833 for Readers #1 and #2, respectively, compared to the baseline UNets 0.825 for Reader #1 and 0.851 for Reader #2. SwinUNETR had an average dice score of 0.8583 for Reader#1 and 0.867 for Reader#2 in cross-validated mixed training. For the gland size-based dataset, SwinUNETR achieved an average dice score of 0.902 for Reader#1 subset and 0.894 for Reader#2, using the five-fold mixed training strategy (Reader#1, n=53; Reader#2, n=87) at larger gland size-based subsets, where UNETR performed poorly. Our findings demonstrate that global and shifted-window self-attention effectively reduces label noise and class imbalance sensitivity, resulting in improvements in the Dice score over CNNs by up to five points while maintaining computational efficiency. This contributes to the high robustness of SwinUNETR for clinical deployment.

eess.IV↗

arXiv2026

QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection

Video Anomaly Detection (VAD) is a fundamental challenge in computer vision, particularly due to the open-set nature of anomalies. While recent training-free approaches utilizing Vision-Language Models (VLMs) have shown promise, they typically rely on massive, resource-intensive foundation models to compensate for the ambiguity of static prompts. We argue that the bottleneck in VAD is not necessarily model capacity, but rather the static nature of inquiry. We propose QVAD, a question-centric agentic framework that treats VLM-LLM interaction as a dynamic dialogue. By iteratively refining queries based on visual context, our LLM agent guides smaller VLMs to produce high-fidelity captions and precise semantic reasoning without parameter updates. This ``prompt-updating" mechanism effectively unlocks the latent capabilities of lightweight models, enabling state-of-the-art performance on UCF-Crime, XD-Violence, and UBNormal using a fraction of the parameters required by competing methods. We further demonstrate exceptional generalizability on the single-scene ComplexVAD dataset. Crucially, QVAD achieves high inference speeds with minimal memory footprints, making advanced VAD capabilities deployable on resource-constrained edge devices.

cs.CV↗

arXiv2026

Preserving Vertical Structure in 3D-to-2D Projection for Permafrost Thaw Mapping

Forecasting permafrost thaw from aerial lidar requires projecting 3D point cloud features onto 2D prediction grids, yet naive aggregation methods destroy the vertical structure critical in forest environments where ground, understory, and canopy carry distinct information about subsurface conditions. We propose a projection decoder with learned height embeddings that enable height-dependent feature transformations, allowing the network to differentiate ground-level signals from canopy returns. Combined with stratified sampling that ensures all forest strata remain represented, our approach preserves the vertical information critical for predicting subsurface conditions. Our approach pairs this decoder with a Point Transformer V3 encoder to predict dense thaw depth maps from drone-collected lidar over boreal forest in interior Alaska. Experiments demonstrate that z-stratified projection outperforms standard averaging-based methods, particularly in areas with complex vertical vegetation structure. Our method enables scalable, high-resolution monitoring of permafrost degradation from readily deployable UAV platforms.

eess.IV↗

arXiv2026

Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization

As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instability when highly non-linear policies induce extreme local curvature in the inner maximization. Standard remedies that enforce global Jacobian bounds are overly conservative, suppressing sensitivity in all directions and inducing a large Price of Robustness. We introduce Adversarially-Aligned Jacobian Regularization (AAJR), a trajectory-aligned approach that controls sensitivity strictly along adversarial ascent directions. We prove that AAJR yields a strictly larger admissible policy class than global constraints under mild conditions, implying a weakly smaller approximation gap and reduced nominal performance degradation. Furthermore, we derive step-size conditions under which AAJR controls effective smoothness along optimization trajectories and ensures inner-loop stability. These results provide a structural theory for agentic robustness that decouples minimax stability from global expressivity restrictions.

cs.LG↗

arXiv2026

Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection

Existing semi-supervised video anomaly detection (VAD) methods often struggle with detecting complex anomalies involving object interactions and generally lack explainability. To overcome these limitations, we propose a novel VAD framework leveraging Multimodal Large Language Models (MLLMs). Unlike previous MLLM-based approaches that make direct anomaly judgments at the frame level, our method focuses on extracting and interpreting object activity and interactions over time. By querying an MLLM with visual inputs of object pairs at different moments, we generate textual descriptions of the activity and interactions from nominal videos. These textual descriptions serve as a high-level representation of the activity and interactions of objects in a video. They are used to detect anomalies during test time by comparing them to textual descriptions found in nominal training videos. Our approach inherently provides explainability and can be combined with many traditional VAD methods to further enhance their interpretability. Extensive experiments on benchmark datasets demonstrate that our method not only detects complex interaction-based anomalies effectively but also achieves state-of-the-art performance on datasets without interaction anomalies.

cs.CV↗

arXiv2026

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade system-level performance. We propose Socially-Weighted Alignment (SWA), a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare via a social weight $λ\in[0,1]$. In a shared-resource congestion game with $n$ agents and congestion severity $β$, we show that SWA induces a critical threshold $λ^*=(n-β)/(n-1)$ above which agents no longer have marginal incentive to increase demand under overload, yielding a phase transition from persistent congestion to stable operation near capacity. We further provide an inference-time algorithmic instantiation of SWA that does not require parameter updates or multi-agent reinforcement learning, and use a multi-agent simulation to empirically validate the predicted threshold behavior.

cs.MA↗

arXiv2026

Agentic AI-Empowered Dynamic Survey Framework

Survey papers play a central role in synthesizing and organizing scientific knowledge, yet they are increasingly strained by the rapid growth of research output. As new work continues to appear after publication, surveys quickly become outdated, contributing to redundancy and fragmentation in the literature. We reframe survey writing as a long-horizon maintenance problem rather than a one-time generation task, treating surveys as living documents that evolve alongside the research they describe. We propose an agentic Dynamic Survey Framework that supports the continuous updating of existing survey papers by incrementally integrating new work while preserving survey structure and minimizing unnecessary disruption. Using a retrospective experimental setup, we demonstrate that the proposed framework effectively identifies and incorporates emerging research while preserving the coherence and structure of existing surveys.

cs.LG↗

arXiv2025

HoneyBee: A Scalable Modular Framework for Creating Multimodal Oncology Datasets with Foundational Embedding Models

HONeYBEE (Harmonized ONcologY Biomedical Embedding Encoder) is an open-source framework that integrates multimodal biomedical data for oncology applications. It processes clinical data (structured and unstructured), whole-slide images, radiology scans, and molecular profiles to generate unified patient-level embeddings using domain-specific foundation models and fusion strategies. These embeddings enable survival prediction, cancer-type classification, patient similarity retrieval, and cohort clustering. Evaluated on 11,400+ patients across 33 cancer types from The Cancer Genome Atlas (TCGA), clinical embeddings showed the strongest single-modality performance with 98.5% classification accuracy and 96.4% precision@10 in patient retrieval. They also achieved the highest survival prediction concordance indices across most cancer types. Multimodal fusion provided complementary benefits for specific cancers, improving overall survival prediction beyond clinical features alone. Comparative evaluation of four large language models revealed that general-purpose models like Qwen3 outperformed specialized medical models for clinical text representation, though task-specific fine-tuning improved performance on heterogeneous data such as pathology reports.

cs.LG↗

arXiv2025

LLM-Guided Agentic Object Detection for Open-World Understanding

Object detection traditionally relies on fixed category sets, requiring costly re-training to handle novel objects. While Open-World and Open-Vocabulary Object Detection (OWOD and OVOD) improve flexibility, OWOD lacks semantic labels for unknowns, and OVOD depends on user prompts, limiting autonomy. We propose an LLM-guided agentic object detection (LAOD) framework that enables fully label-free, zero-shot detection by prompting a Large Language Model (LLM) to generate scene-specific object names. These are passed to an open-vocabulary detector for localization, allowing the system to adapt its goals dynamically. We introduce two new metrics, Class-Agnostic Average Precision (CAAP) and Semantic Naming Average Precision (SNAP), to separately evaluate localization and naming. Experiments on LVIS, COCO, and COCO-OOD validate our approach, showing strong performance in detecting and naming novel objects. Our method offers enhanced autonomy and adaptability for open-world understanding.

cs.CV↗

arXiv2025

Universal and Efficient Detection of Adversarial Data through Nonuniform Impact on Network Layers

Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against these attacks are relatively understudied. Existing defense approaches either focus on improving DNN robustness by negating the effects of perturbations or use a secondary model to detect adversarial data. Although equally important, the attack detection approach, which is studied in this work, provides a more practical defense compared to the robustness approach. We show that the existing detection methods are either ineffective against the state-of-the-art attack techniques or computationally inefficient for real-time processing. We propose a novel universal and efficient method to detect adversarial examples by analyzing the varying degrees of impact of attacks on different DNN layers. {Our method trains a lightweight regression model that predicts deeper-layer features from early-layer features, and uses the prediction error to detect adversarial samples.} Through theoretical arguments and extensive experiments, we demonstrate that our detection method is highly effective, computationally efficient for real-time processing, compatible with any DNN architecture, and applicable across different domains, such as image, video, and audio.

cs.LG↗