PyTorchKR Papers

최신 논문

총 1,907편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2504.05545

Extended Sensitivity-Aware Reactive Power Dispatch Algorithm for Smart Inverters with Multiple Control Modes

The increasing integration of Distributed Energy Resources (DERs) in distribution networks presents new challenges for voltage regulation and reactive power support. This paper extends a sensitivity-aware reactive power dispatch algorithm tailored to manage smart inverters operating under different control modes, including PQ, PV, and Volt-Var (VV). The proposed approach dynamically optimizes reactive power dispatch and voltage setpoints, enabling effective coordination among distribution systems as a virtual power plant (VPP) to support the transmission network. The algorithm is applied to the IEEE 13-bus and IEEE-123 bus test systems, and its performance is validated by comparing results with OpenDSS simulations across various operating scenarios. Results show that the maximum error in the voltages is less than 0.015 pu.

arXiv:2504.06928

Beyond Tools: Generative AI as Epistemic Infrastructure in Education

As generative AI rapidly integrates into educational infrastructures worldwide, it transforms how knowledge gets created, validated, and shared, yet current discourse inadequately addresses its implications as epistemic infrastructure mediating teaching and learning. This paper investigates how AI systems function as epistemic infrastructures in education and their impact on human epistemic agency. Adopting a situated cognition perspective and following a value-sensitive design approach, the study conducts a technical investigation of two representative AI systems in educational settings, analyzing their impact on teacher practice across three dimensions: affordances for skilled epistemic actions, support for epistemic sensitivity, and implications for long-term habit formation. The analysis reveals that current AI systems inadequately support teachers' skilled epistemic actions, insufficiently foster epistemic sensitivity, and potentially cultivate problematic habits that prioritize efficiency over epistemic agency. To address these challenges, the paper recommends recognizing the infrastructural transformation occurring in education, developing AI environments that stimulate skilled actions while upholding epistemic norms, and involving educators in AI design processes -- recommendations aimed at fostering AI integration that aligns with core educational values and maintains human epistemic agency.

arXiv:2504.07801

FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness

Recent advances in Large Language Models (LLMs) have enabled their application to recommender systems (RecLLMs), yet concerns remain regarding fairness across demographic and psychological user dimensions. We introduce FairEval, a novel evaluation framework to systematically assess fairness in LLM-based recommendations. FairEval integrates personality traits with eight sensitive demographic attributes,including gender, race, and age, enabling a comprehensive assessment of user-level bias. We evaluate models, including ChatGPT 4o and Gemini 1.5 Flash, on music and movie recommendations. FairEval's fairness metric, PAFS, achieves scores up to 0.9969 for ChatGPT 4o and 0.9997 for Gemini 1.5 Flash, with disparities reaching 34.79 percent. These results highlight the importance of robustness in prompt sensitivity and support more inclusive recommendation systems.

arXiv:2504.03439

Early detection of diabetes through transfer learning-based eye (vision) screening and improvement of machine learning model performance and advanced parameter setting algorithms

Diabetic Retinopathy (DR) is a serious and common complication of diabetes, caused by prolonged high blood sugar levels that damage the small retinal blood vessels. If left untreated, DR can progress to retinal vein occlusion and stimulate abnormal blood vessel growth, significantly increasing the risk of blindness. Traditional diabetes diagnosis methods often utilize convolutional neural networks (CNNs) to extract visual features from retinal images, followed by classification algorithms such as decision trees and k-nearest neighbors (KNN) for disease detection. However, these approaches face several challenges, including low accuracy and sensitivity, lengthy machine learning (ML) model training due to high data complexity and volume, and the use of limited datasets for testing and evaluation. This study investigates the application of transfer learning (TL) to enhance ML model performance in DR detection. Key improvements include dimensionality reduction, optimized learning rate adjustments, and advanced parameter tuning algorithms, aimed at increasing efficiency and diagnostic accuracy. The proposed model achieved an overall accuracy of 84% on the testing dataset, outperforming prior studies. The highest class-specific accuracy reached 89%, with a maximum sensitivity of 97% and an F1-score of 92%, demonstrating strong performance in identifying DR cases. These findings suggest that TL-based DR screening is a promising approach for early diagnosis, enabling timely interventions to prevent vision loss and improve patient outcomes.

arXiv:2504.03212

Mathematical Modeling of Soil-Transmitted Helminth Infection: Human-Animal Dynamics with Environmental Reservoirs

Soil-transmitted helminth (STH) infections, one of the most prevalent neglected tropical diseases, pose a significant threat to public health in tropical and subtropical areas. These parasites infect humans and animals through direct contact with contaminated soil or accidental ingestion. This study examines the dynamics of STH transmission using a deterministic compartmental model and nonlinear ordinary differential equations. Our model incorporates the roles humans, animals, and the environment play as reservoirs for spreading STH. We derived the basic reproduction number and demonstrate that the disease-free and endemic equilibrium points are asymptotically stable under specific thresholds. We also performed a sensitivity analysis to determine how each parameter affects the model's output. The sensitivity analysis identifies key parameters influencing infection rates, such as ingestion rate, disease progression rate, and shedding rate, all of which increase infection. Conversely, higher clearance and recovery rates decrease infection. The study also highlights the potential for cross-species transmission of STH infections between humans and animals, underscoring the One Health concept, which acknowledges the interdependence of human, animal, and environmental health.

arXiv:2503.20601

Pupillary reactions depend on disgust sensitivity in conceptual pavlovian disgust conditioning

Exposure-based interventions rely on inhibitory learning, often studied through Pavlovian conditioning. While disgust conditioning is increasingly linked to psychiatric disorders, it has been less researched than fear conditioning. In this study, we applied a categorical Pavlovian disgust conditioning paradigm with two CS categories (animals and tools) and disgusting images as US (e.g., feces). During categorization, acquisition, and extinction phases, we measured eye movements and pupil responses in 44 participants. Consistent with previous results, subjective disgust and US expectancy increased from categorization to acquisition for CS+, along with greater pupil dilation for CS+ than CS-. Higher disgust sensitivity was associated with more generalized and longer lasting disgust experiences, as well as higher expectancy for disgusting images. Pupil response during acquisition and extinction depended on disgust sensitivity: Participants with lower disgust sensitivity showed greater pupil dilation. These findings suggest that individuals with high disgust sensitivity and prolonged expectancy may exhibit physiological differences from less sensitive individuals as early as the acquisition phase. This could inform contamination-based OCD treatments by integrating interventions which focus on attentional deployment or physiological reactions. To our knowledge, this is the first study using pupillometry and eye tracking in categorical disgust conditioning.

arXiv:2503.19586

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment

Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension, asking whether LALMs process speaker-contextualized language in ways that parallel human cognitive mechanisms. We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses. Using surprisal and entropy metrics from the models, we analyzed their sensitivity to speaker-content incongruency across social stereotype violations (e.g., a man claiming to regularly get manicures) and biological knowledge violations (e.g., a man claiming to be pregnant). Results revealed that Qwen2-Audio exhibited increased surprisal for speaker-incongruent content and its surprisal values significantly predicted human N400 responses, while Ultravox 0.5 showed limited sensitivity to speaker characteristics. Importantly, neither model replicated the human-like processing distinction between social violations (eliciting N400 effects) and biological violations (eliciting P600 effects). These findings reveal both the potential and limitations of current LALMs in processing speaker-contextualized language, and suggest differences in social-linguistic processing mechanisms between humans and LALMs.

arXiv:2503.19860

Unpaired Translation of Chest X-ray Images for Lung Opacity Diagnosis via Adaptive Activation Masks and Cross-Domain Alignment

Chest X-ray radiographs (CXRs) play a pivotal role in diagnosing and monitoring cardiopulmonary diseases. However, lung opac- ities in CXRs frequently obscure anatomical structures, impeding clear identification of lung borders and complicating the localization of pathology. This challenge significantly hampers segmentation accuracy and precise lesion identification, which are crucial for diagnosis. To tackle these issues, our study proposes an unpaired CXR translation framework that converts CXRs with lung opacities into counterparts without lung opacities while preserving semantic features. Central to our approach is the use of adaptive activation masks to selectively modify opacity regions in lung CXRs. Cross-domain alignment ensures translated CXRs without opacity issues align with feature maps and prediction labels from a pre-trained CXR lesion classifier, facilitating the interpretability of the translation process. We validate our method using RSNA, MIMIC-CXR-JPG and JSRT datasets, demonstrating superior translation quality through lower Frechet Inception Distance (FID) and Kernel Inception Distance (KID) scores compared to existing meth- ods (FID: 67.18 vs. 210.4, KID: 0.01604 vs. 0.225). Evaluation on RSNA opacity, MIMIC acute respiratory distress syndrome (ARDS) patient CXRs and JSRT CXRs show our method enhances segmentation accuracy of lung borders and improves lesion classification, further underscoring its potential in clinical settings (RSNA: mIoU: 76.58% vs. 62.58%, Sensitivity: 85.58% vs. 77.03%; MIMIC ARDS: mIoU: 86.20% vs. 72.07%, Sensitivity: 92.68% vs. 86.85%; JSRT: mIoU: 91.08% vs. 85.6%, Sensitivity: 97.62% vs. 95.04%). Our approach advances CXR imaging analysis, especially in investigating segmentation impacts through image translation techniques.

arXiv:2503.19502

Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model

El Ni\~no-Southern Oscillation (ENSO) is a prominent mode of interannual climate variability with far-reaching global impacts. Its evolution is governed by intricate air-sea interactions, posing significant challenges for long-term prediction. In this study, we introduce CTEFNet, a multivariate deep learning model that synergizes convolutional neural networks and transformers to enhance ENSO forecasting. By integrating multiple oceanic and atmospheric predictors, CTEFNet extends the effective forecast lead time to 20 months while mitigating the impact of the spring predictability barrier, outperforming both dynamical models and state-of-the-art deep learning approaches. Furthermore, CTEFNet offers physically meaningful and statistically significant insights through gradient-based sensitivity analysis, revealing the key precursor signals that govern ENSO dynamics, which align with well-established theories and reveal new insights about inter-basin interactions among the Pacific, Atlantic, and Indian Oceans. The CTEFNet's superior predictive skill and interpretable sensitivity assessments underscore its potential for advancing climate prediction. Our findings highlight the importance of multivariate coupling in ENSO evolution and demonstrate the promise of deep learning in capturing complex climate dynamics with enhanced interpretability.

arXiv:2503.19384

Information geometry of chemical reaction networks: Cramer-Rao bound and absolute sensitivity revisited

Information geometry is based on classical Legendre duality but allows to incorporate additional structure such as algebraic constraints and Bregman divergence functions. It is naturally suited, and has been successfully used, to describe the thermodynamics of chemical reaction networks (CRNs) based on the Legendre duality between concentration and potential spaces, where algebraic constraints are enforced by the stoichiometry. In this article, the Riemannian geometrical aspects of the theory are explored. It is shown that duality between concentration and potential spaces and the natural parametrizations of equilibrium subspace are isometries, which leads to a multivariate Cramer-Rao bound through the comparison of two Riemannian metric tensors. In the subsequent part, the theory is applied to the recently introduced concept of absolute sensitivity. Using the Riemannian geometric tools, it is proven that the absolute sensitivity is a projection operator onto the tangent bundle of the equilibrium manifold. A linear algebraic characterization and explicit results on first order corrections to the thermodynamics of ideal solutions are provided. Finally, the theory is applied to the IDHKP-IDH glyoxylate bypass regulation system. The novelty of the theory is that it is applicable to CRNs with non-ideal thermodynamical behavior, which are prevalent in highly crowded cellular environments due to various interactions between the chemicals. Indeed, the analyzed example shows remarkable behavior ranging from hypersensitivity to negative-self regulations. These are effects which usually require strongly nonlinear reaction kinetics. However, here, they are obtained by tuning thermodynamical interactions providing a complementary, and physically well-founded, viewpoint on such phenomena.

arXiv:2503.08006

Injecting Imbalance Sensitivity for Multi-Task Learning

Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-shared representations in MTL. However, our paper empirically argues that these studies, specifically gradient-based ones, primarily emphasize the conflict issue while neglecting the potentially more significant impact of imbalance/dominance in MTL. In line with this perspective, we enhance the existing baseline method by injecting imbalance-sensitivity through the imposition of constraints on the projected norms. To demonstrate the effectiveness of our proposed IMbalance-sensitive Gradient (IMGrad) descent method, we evaluate it on multiple mainstream MTL benchmarks, encompassing supervised learning tasks as well as reinforcement learning. The experimental results consistently demonstrate competitive performance.

arXiv:2503.17752공식 코드 · Papers with Code

HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving

LiDAR point cloud semantic segmentation plays a crucial role in autonomous driving. In recent years, semi-supervised methods have gained popularity due to their significant reduction in annotation labor and time costs. Current semi-supervised methods typically focus on point cloud spatial distribution or consider short-term temporal representations, e.g., only two adjacent frames, often overlooking the rich long-term temporal properties inherent in autonomous driving scenarios. In driving experience, we observe that nearby objects, such as roads and vehicles, remain stable while driving, whereas distant objects exhibit greater variability in category and shape. This natural phenomenon is also captured by LiDAR, which reflects lower temporal sensitivity for nearby objects and higher sensitivity for distant ones. To leverage these characteristics, we propose HiLoTs, which learns high-temporal sensitivity and low-temporal sensitivity representations from continuous LiDAR frames. These representations are further enhanced and fused using a cross-attention mechanism. Additionally, we employ a teacher-student framework to align the representations learned by the labeled and unlabeled branches, effectively utilizing the large amounts of unlabeled data. Experimental results on the SemanticKITTI and nuScenes datasets demonstrate that our proposed HiLoTs outperforms state-of-the-art semi-supervised methods, and achieves performance close to LiDAR+Camera multimodal approaches. Code is available on https://github.com/rdlin118/HiLoTs

arXiv:2503.17786

Assessing workflow impact and clinical utility of AI-assisted brain aneurysm detection: a multi-reader study

Despite the plethora of AI-based algorithms developed for anomaly detection in radiology, subsequent integration into clinical setting is rarely evaluated. In this work, we assess the applicability and utility of an AI-based model for brain aneurysm detection comparing the performance of two readers with different levels of experience (2 and 13 years). We aim to answer the following questions: 1) Do the readers improve their performance when assisted by the AI algorithm? 2) How much does the AI algorithm impact routine clinical workflow? We reuse and enlarge our open-access, Time-Of-Flight Magnetic Resonance Angiography dataset (N=460). We use 360 subjects for training/validating our algorithm and 100 as unseen test set for the reading session. Even though our model reaches state-of-the-art results on the test set (sensitivity=74%, false positive rate=1.6), we show that neither the junior nor the senior reader significantly increase their sensitivity (p=0.59, p=1, respectively). In addition, we find that reading time for both readers is significantly higher in the "AI-assisted" setting than in the "Unassisted" (+15 seconds, on average; p=3x10^(-4) junior, p=3x10^(-5) senior). The confidence reported by the readers is unchanged across the two settings, indicating that the AI assistance does not influence the certainty of the diagnosis. Our findings highlight the importance of clinical validation of AI algorithms in a clinical setting involving radiologists. This study should serve as a reminder to the community to always examine the real-word effectiveness and workflow impact of proposed algorithms.

arXiv:2503.16759

elaTCSF: A Temporal Contrast Sensitivity Function for Flicker Detection and Modeling Variable Refresh Rate Flicker

The perception of flicker has been a prominent concern in illumination and electronic display fields for over a century. Traditional approaches often rely on Critical Flicker Frequency (CFF), primarily suited for high-contrast (full-on, full-off) flicker. To tackle varying contrast flicker, the International Committee for Display Metrology (ICDM) introduced a Temporal Contrast Sensitivity Function TCSF$_{IDMS}$ within the Information Display Measurements Standard (IDMS). Nevertheless, this standard overlooks crucial parameters: luminance, eccentricity, and area. Existing models incorporating these parameters are inadequate for flicker detection, especially at low spatial frequencies. To address these limitations, we extend the TCSF$_{IDMS}$ and combine it with a new spatial probability summation model to incorporate the effects of luminance, eccentricity, and area (elaTCSF). We train the elaTCSF on various flicker detection datasets and establish the first variable refresh rate flicker detection dataset for further verification. Additionally, we contribute to resolving a longstanding debate on whether the flicker is more visible in peripheral vision. We demonstrate how elaTCSF can be used to predict flicker due to low-persistence in VR headsets, identify flicker-free VRR operational ranges, and determine flicker sensitivity in lighting design.

arXiv:2503.13684

FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models

Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to assess model sensitivity to hyperparameters. Fine-grained video editing is crucial for enabling precise, object-level modifications while maintaining context and temporal consistency. To address this, we introduce FiVE, a Fine-grained Video Editing Benchmark for evaluating emerging diffusion and rectified flow models. Our benchmark includes 74 real-world videos and 26 generated videos, featuring 6 fine-grained editing types, 420 object-level editing prompt pairs, and their corresponding masks. Additionally, we adapt the latest rectified flow (RF) T2V generation models, Pyramid-Flow and Wan2.1, by introducing FlowEdit, resulting in training-free and inversion-free video editing models Pyramid-Edit and Wan-Edit. We evaluate five diffusion-based and two RF-based editing methods on our FiVE benchmark using 15 metrics, covering background preservation, text-video similarity, temporal consistency, video quality, and runtime. To further enhance object-level evaluation, we introduce FiVE-Acc, a novel metric leveraging Vision-Language Models (VLMs) to assess the success of fine-grained video editing. Experimental results demonstrate that RF-based editing significantly outperforms diffusion-based methods, with Wan-Edit achieving the best overall performance and exhibiting the least sensitivity to hyperparameters. More video demo available on the anonymous website: https://sites.google.com/view/five-benchmark

arXiv:2503.12637

Understanding Driver Cognition and Decision-Making Behaviors in High-Risk Scenarios: A Drift Diffusion Perspective

Ensuring safe interactions between autonomous vehicles (AVs) and human drivers in mixed traffic systems remains a major challenge, particularly in complex, high-risk scenarios. This paper presents a cognition-decision framework that integrates individual variability and commonalities in driver behavior to quantify risk cognition and model dynamic decision-making. First, a risk sensitivity model based on a multivariate Gaussian distribution is developed to characterize individual differences in risk cognition. Then, a cognitive decision-making model based on the drift diffusion model (DDM) is introduced to capture common decision-making mechanisms in high-risk environments. The DDM dynamically adjusts decision thresholds by integrating initial bias, drift rate, and boundary parameters, adapting to variations in speed, relative distance, and risk sensitivity to reflect diverse driving styles and risk preferences. By simulating high-risk scenarios with lateral, longitudinal, and multidimensional risk sources in a driving simulator, the proposed model accurately predicts cognitive responses and decision behaviors during emergency maneuvers. Specifically, by incorporating driver-specific risk sensitivity, the model enables dynamic adjustments of key DDM parameters, allowing for personalized decision-making representations in diverse scenarios. Comparative analysis with IDM, Gipps, and MOBIL demonstrates that DDM more precisely captures human cognitive processes and adaptive decision-making in high-risk scenarios. These findings provide a theoretical basis for modeling human driving behavior and offer critical insights for enhancing AV-human interaction in real-world traffic environments.

arXiv:2503.12755

Cohort-attention Evaluation Metric against Tied Data: Studying Performance of Classification Models in Cancer Detection

Artificial intelligence (AI) has significantly improved medical screening accuracy, particularly in cancer detection and risk assessment. However, traditional classification metrics often fail to account for imbalanced data, varying performance across cohorts, and patient-level inconsistencies, leading to biased evaluations. We propose the Cohort-Attention Evaluation Metrics (CAT) framework to address these challenges. CAT introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity. Key metrics like CATSensitivity (CATSen), CATSpecificity (CATSpe), and CATMean ensure balanced and fair evaluation across diverse populations. This approach enhances predictive reliability, fairness, and interpretability, providing a robust evaluation method for AI-driven medical screening models.

arXiv:2503.11160

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective

Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original gradients. However, these methods lack a solid theoretical foundation and exhibit perplexing behaviors, such as reduced sensitivity to parameter randomization, raising concerns about their reliability and highlighting the need for theoretical justification. In this work, we present a unified theoretical framework for methods like GBP, RectGrad, LRP, and DTD, demonstrating that they achieve input alignment by combining the weights of activated neurons. This alignment improves the visualization quality and reduces sensitivity to weight randomization. Our contributions include: (1) Providing a unified explanation for multiple behaviors, rather than focusing on just one. (2) Accurately predicting novel behaviors. (3) Offering insights into decision-making processes, including layer-wise information changes and the relationship between attributions and model decisions.

arXiv:2503.08229공식 코드 · Papers with Code

Modeling Variants of Prompts for Vision-Language Models

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt template design. Although prompt learning methods can address the sensitivity issue by replacing natural language prompts with learnable ones, they are incomprehensible to humans. Ensuring consistent performance across various prompt templates enables models to adapt seamlessly to diverse phrasings, enhancing their ability to handle downstream tasks without requiring extensive prompt engineering. In this work, we introduce the RobustPrompt Benchmark, a systematic benchmark to evaluate robustness to different prompt templates for VLMs. It includes a dataset with hundreds of carefully designed prompt templates, divided into six types, covering a wide variety of commonly used templates. Beside the benchmark, we propose Modeling Variants of Prompts (MVP), a simple yet effective method that mitigates sensitivity by modeling variants of prompt structures. The innovation of MVP lies in decoupling prompts into templates and class names, and using Variational Autoencoders (VAE) to model the distribution of diverse prompt structures. Experiments across 11 datasets demonstrate that MVP can greatly enhance model robustness to variations in input prompts without a drop in performance. The code is available at https://github.com/liaolea/MVP.

arXiv:2503.08693

Liquidity-adjusted Return and Volatility, and Autoregressive Models

We construct liquidity-adjusted return and volatility using purposely designed liquidity metrics (liquidity jump and liquidity diffusion) that incorporate additional liquidity information. Based on these measures, we introduce a liquidity-adjusted ARMA-GARCH framework to address the limitations of traditional ARMA-GARCH models, which are not effectively in modeling illiquid assets with high liquidity variability, such as cryptocurrencies. We demonstrate that the liquidity-adjusted model improves model fit for cryptocurrencies, with greater volatility sensitivity to past shocks and reduced volatility persistence of erratic past volatility. Our model is validated by the empirical evidence that the liquidity-adjusted mean-variance (LAMV) portfolios outperform the traditional mean-variance (TMV) portfolios.