Jihie Kim

Zhixuan Liu, Youeun Shin, Beverley-Claire Okogwu et al.

It has been shown that accurate representation in media improves the well-being of the people who consume it. By contrast, inaccurate representations can negatively affect viewers and lead to harmful perceptions of other cultures. To achieve inclusive representation in generated images, we propose a culturally-aware priming approach for text-to-image synthesis using a small but culturally curated dataset that we collected, known here as Cross-Cultural Understanding Benchmark (CCUB) Dataset, to fight the bias prevalent in giant datasets. Our proposed approach is comprised of two fine-tuning techniques: (1) Adding visual context via fine-tuning a pre-trained text-to-image synthesis model, Stable Diffusion, on the CCUB text-image pairs, and (2) Adding semantic context via automated prompt engineering using the fine-tuned large language model, GPT-3, trained on our CCUB culturally-aware text data. CCUB dataset is curated and our approach is evaluated by people who have a personal relationship with that particular culture. Our experiments indicate that priming using both text and image is effective in improving the cultural relevance and decreasing the offensiveness of generated images while maintaining quality.

Zahid Ullah, Muhammad Hilal, Eunsoo Lee et al.

Several review papers summarize cardiac imaging and DL advances, few works connect this overview to a unified and reproducible experimental benchmark. In this study, we combine a focused review of cardiac ultrasound segmentation literature with a controlled comparison of three influential architectures, U-Net, Attention U-Net, and TransUNet, on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) echocardiography dataset. Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining (SSL) on thousands of unlabeled cine frames. Using identical training splits, losses, and evaluation criteria, a plain U-Net achieved a 94% mean Dice when trained directly on NIfTI data (preserving native dynamic range), while the PNG-16-bit workflow reached 91% under similar conditions. Attention U-Net provided modest improvements on small or low-contrast regions, reducing boundary leakage, whereas TransUNet demonstrated the strongest generalization on challenging frames due to its ability to model global spatial context, particularly when initialized with SSL. Pseudo-labeling expanded the training set and improved robustness after confidence filtering. Overall, our contributions are threefold: a harmonized, apples-to-apples benchmark of U-Net, Attention U-Net, and TransUNet under standardized CAMUS preprocessing and evaluation; practical guidance on maintaining intensity fidelity, resolution consistency, and alignment when preparing ultrasound data; and an outlook on scalable self-supervision and emerging multimodal GPT-based annotation pipelines for rapid labeling, quality assurance, and targeted dataset curation.

Junghun Kim, Yoojin An, Jihie Kim

Attention has become one of the most commonly used mechanisms in deep learning approaches. The attention mechanism can help the system focus more on the feature space's critical regions. For example, high amplitude regions can play an important role for Speech Emotion Recognition (SER). In this paper, we identify misalignments between the attention and the signal amplitude in the existing multi-head self-attention. To improve the attention area, we propose to use a Focus-Attention (FA) mechanism and a novel Calibration-Attention (CA) mechanism in combination with the multi-head self-attention. Through the FA mechanism, the network can detect the largest amplitude part in the segment. By employing the CA mechanism, the network can modulate the information flow by assigning different weights to each attention head and improve the utilization of surrounding contexts. To evaluate the proposed method, experiments are performed with the IEMOCAP and RAVDESS datasets. Experimental results show that the proposed framework significantly outperforms the state-of-the-art approaches on both datasets.

Junghun Kim, Jihie Kim

Learning expressive representation is crucial in deep learning. In speech emotion recognition (SER), vacuum regions or noises in the speech interfere with expressive representation learning. However, traditional RNN-based models are susceptible to such noise. Recently, Graph Neural Network (GNN) has demonstrated its effectiveness for representation learning, and we adopt this framework for SER. In particular, we propose a cosine similarity-based graph as an ideal graph structure for representation learning in SER. We present a Cosine similarity-based Graph Convolutional Network (CoGCN) that is robust to perturbation and noise. Experimental results show that our method outperforms state-of-the-art methods or provides competitive results with a significant model size reduction with only 1/30 parameters.

Jinyeong Chae, Jihie Kim

Knowledge-based visual question answering (KVQA) task aims to answer questions that require additional external knowledge as well as an understanding of images and questions. Recent studies on KVQA inject an external knowledge in a multi-modal form, and as more knowledge is used, irrelevant information may be added and can confuse the question answering. In order to properly use the knowledge, this study proposes the following: 1) we introduce a novel semantic inconsistency measure computed from caption uncertainty and semantic similarity; 2) we suggest a new external knowledge assimilation method based on the semantic inconsistency measure and apply it to integrate explicit knowledge and implicit knowledge for KVQA; 3) the proposed method is evaluated with the OK-VQA dataset and achieves the state-of-the-art performance.

Junghun Kim, Jihie Kim

Multimodal sentiment analysis has become an increasingly popular research area as the demand for multimodal online content is growing. For multimodal sentiment analysis, words can have different meanings depending on the linguistic context and non-verbal information, so it is crucial to understand the meaning of the words accordingly. In addition, the word meanings should be interpreted within the whole utterance context that includes nonverbal information. In this paper, we present a Context-driven Modality Shifting BERT with Contrastive Learning for linguistic, visual, acoustic Representations (CMSBERT-CLR), which incorporates the whole context's non-verbal and verbal information and aligns modalities more effectively through contrastive learning. First, we introduce a Context-driven Modality Shifting (CMS) to incorporate the non-verbal and verbal information within the whole context of the sentence utterance. Then, for improving the alignment of different modalities within a common embedding space, we apply contrastive learning. Furthermore, we use an exponential moving average parameter and label smoothing as optimization strategies, which can make the convergence of the network more stable and increase the flexibility of the alignment. In our experiments, we demonstrate that our approach achieves state-of-the-art results.

Jiho Park, Sieun Choi, Jaeyoon Seo et al.

Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizing pixel-based human-drawn sketches, a representative example of abstract expression. To combat these challenges, we propose StableSketcher, a novel framework that empowers diffusion models to generate hand-drawn sketches with high prompt fidelity. Within this framework, we fine-tune the variational autoencoder to optimize latent decoding, enabling it to better capture the characteristics of sketches. In parallel, we integrate a new reward function for reinforcement learning based on visual question answering, which improves text-image alignment and semantic consistency. Extensive experiments demonstrate that StableSketcher generates sketches with improved stylistic fidelity, achieving better alignment with prompts compared to the Stable Diffusion baseline. Additionally, we introduce SketchDUO, to the best of our knowledge, the first dataset comprising instance-level sketches paired with captions and question-answer pairs, thereby addressing the limitations of existing datasets that rely on image-label pairs. Our code and dataset will be made publicly available upon acceptance.

Sungmin Kang, Jaeha Song, Jihie Kim

Understanding the morphological structure of medical images and precisely segmenting the region of interest or abnormality is an important task that can assist in diagnosis. However, the unique properties of medical imaging make clear segmentation difficult,and the high cost and time-consuming task of labeling leads to a coarse-grained representation of ground truth. Facing with these problems, we propose a novel Diffusion Transformer Segmentation (DTS) model for robust segmentation in the presence of noise. We propose an alternative to the dominant Denoising U-Net encoder through experiments applying a transformer architecture, which captures global dependency through self-attention. Additionally, we propose k-neighbor label smoothing, reverse boundary attention, and self-supervised learning with morphology-driven learning to improve the ability to identify complex structures. Our model, which analyzes the morphological representation of images, shows better results than the previous models in various medical imaging modalities, including CT, MRI, and lesion images.

Minki Hong, Eunsoo Lee, Sohyun Park et al.

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.

Eunsoo Lee, Jeongwoo Lee, Minki Hong et al.

Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual grounding constitutes a major bottleneck for chart-based reasoning. We propose VisDoT, a framework that enhances visual reasoning through human-like interpretation grounding. We formalize four perceptual tasks based on the theory of graphical perception, including position and length. Building on this foundation, we introduce Decomposition-of-Thought (DoT) prompting, which sequentially separates questions into visual perception sub-questions and logic sub-questions. Fine-tuning InternVL with VisDoT achieves a +11.2% improvement on ChartQA and surpasses GPT-4o on the more challenging ChartQAPro benchmark. On the newly introduced VisDoTQA benchmark, the model improves by +33.2%. Furthermore, consistent zero-shot gains on diverse open-domain VQA benchmarks confirm the generalizability of the perception-logic separation strategy for visual question answering. VisDoT leverages human-like perception to enhance visual grounding, achieving state-of-the-art chart understanding and interpretable visual reasoning.

Zahid Ullah, Jihie Kim

Knee osteoarthritis (KOA) is a leading cause of disability worldwide, and accurate severity assessment using the Kellgren Lawrence (KL) grading system is critical for clinical decision making. However, radiographic distinctions between early disease stages, particularly KL1 and KL2, are subtle and frequently lead to inter-observer variability among radiologists. To address these challenges, we propose VLOrdinalFormer, a vision language guided ordinal learning framework for fully automated KOA grading from knee radiographs. The proposed method combines a ViT L16 backbone with CORAL based ordinal regression and a Contrastive Language Image Pretraining (CLIP) driven semantic alignment module, allowing the model to incorporate clinically meaningful textual concepts related to joint space narrowing, osteophyte formation, and subchondral sclerosis. To improve robustness and mitigate overfitting, we employ stratified five fold cross validation, class aware re weighting to emphasize challenging intermediate grades, and test time augmentation with global threshold optimization. Experiments conducted on the publicly available OAI kneeKL224 dataset demonstrate that VLOrdinalFormer achieves state of the art performance, outperforming CNN and ViT baselines in terms of macro F1 score and overall accuracy. Notably, the proposed framework yields substantial performance gains for KL1 and KL2 without compromising classification accuracy for mild or severe cases. In addition, interpretability analyses using Grad CAM and CLIP similarity maps confirm that the model consistently attends to clinically relevant anatomical regions. These results highlight the potential of vision language aligned ordinal transformers as reliable and interpretable tools for KOA grading and disease progression assessment in routine radiological practice.

Jiho Park, Sieun Choi, Jaeyoon Seo et al.

A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive power, quantifying the efficiency of semantic abstraction in sketches remains challenging. Existing evaluation methods that rely on reference images, low-level visual features, or recognition accuracy do not capture abstraction, the defining property of sketches. To address these limitations, we introduce SEA (Sketch Evaluation metric for Abstraction efficiency), a reference-free metric that assesses how economically a sketch represents class-defining visual elements while preserving semantic recognizability. These elements are derived per class from commonsense knowledge about features typically depicted in sketches. SEA leverages a visual question answering model to determine the presence of each element and returns a quantitative score that reflects semantic retention under visual economy. To support this metric, we present CommonSketch, the first semantically annotated sketch dataset, comprising 23,100 human-drawn sketches across 300 classes, each paired with a caption and element-level annotations. Experiments show that SEA aligns closely with human judgments and reliably discriminates levels of abstraction efficiency, while CommonSketch serves as a benchmark providing systematic evaluation of element-level sketch understanding across various vision-language models.

Zahid Ullah, Sieun Choi, Jihie Kim

Accurate cardiac ultrasound segmentation is essential for reliable assessment of ventricular function in intelligent healthcare systems. However, echocardiographic images are challenging due to low contrast, speckle noise, irregular boundaries, and domain shifts across devices and patient populations. Existing methods, largely based on appearance-driven learning, often fail to preserve boundary precision and structural consistency under these conditions. To address these issues, we propose a Contour-Guided Query Refinement Network (CGQR-Net) for boundary-aware cardiac ultrasound segmentation. The framework integrates multi-resolution feature representations with contour-derived structural priors. An HRNet backbone preserves high-resolution spatial details while capturing multi-scale context. A coarse segmentation is first generated, from which anatomical contours are extracted and encoded into learnable query embeddings. These contour-guided queries interact with fused feature maps via cross-attention, enabling structure-aware refinement that improves boundary delineation and reduces noise artifacts. A dual-head supervision strategy jointly optimizes segmentation and boundary prediction to enforce structural consistency. The proposed method is evaluated on the CAMUS dataset and further validated on the CardiacNet dataset to assess cross-dataset generalization. Experimental results demonstrate improved segmentation accuracy, enhanced boundary precision, and robust performance across varying imaging conditions. These results highlight the effectiveness of integrating contour-level structural information with feature-level representations for reliable cardiac ultrasound segmentation.

Jua Han, Jaeyoon Seo, Jungbin Min et al.

One mistake by an AI system in a safety-critical setting can cost lives. As Large Language Models (LLMs) become integral to robotics decision-making, the physical dimension of risk grows; a single wrong instruction can directly endanger human safety. This paper addresses the urgent need to systematically evaluate LLM performance in scenarios where even minor errors are catastrophic. Through a qualitative evaluation of a fire evacuation scenario, we identified critical failure cases in LLM-based decision-making. Based on these, we designed seven tasks for quantitative assessment, categorized into: Complete Information, Incomplete Information, and Safety-Oriented Spatial Reasoning (SOSR). Complete information tasks utilize ASCII maps to minimize interpretation ambiguity and isolate spatial reasoning from visual processing. Incomplete information tasks require models to infer missing context, testing for spatial continuity versus hallucinations. SOSR tasks use natural language to evaluate safe decision-making in life-threatening contexts. We benchmark various LLMs and Vision-Language Models (VLMs) across these tasks. Beyond aggregate performance, we analyze the implications of a 1% failure rate, highlighting how "rare" errors escalate into catastrophic outcomes. Results reveal serious vulnerabilities: several models achieved a 0% success rate in ASCII navigation, while in a simulated fire drill, models instructed robots to move toward hazardous areas instead of emergency exits. Our findings lead to a sobering conclusion: current LLMs are not ready for direct deployment in safety-critical systems. A 99% accuracy rate is dangerously misleading in robotics, as it implies one out of every hundred executions could result in catastrophic harm. We demonstrate that even state-of-the-art models cannot guarantee safety, and absolute reliance on them creates unacceptable risks.

Youngsik Yun, Jihie Kim

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the cultural elements depicted in the images, such as the traditional clothing worn by people from Asian cultural groups. In this paper, we propose a new framework, Culturally-aware Image Captioning (CIC), that generates captions and describes cultural elements extracted from cultural visual elements in images representing cultures. Inspired by methods combining visual modality and Large Language Models (LLMs) through appropriate prompts, our framework (1) generates questions based on cultural categories from images, (2) extracts cultural visual elements from Visual Question Answering (VQA) using generated questions, and (3) generates culturally-aware captions using LLMs with the prompts. Our human evaluation conducted on 45 participants from 4 different cultural groups with a high understanding of the corresponding culture shows that our proposed framework generates more culturally descriptive captions when compared to the image captioning baseline based on VLPs. Resources can be found at https://shane3606.github.io/cic..

Yanggyu Lee, Suchae Jeong, Jihie Kim

LLMs trained in the understanding of programming syntax are now providing effective assistance to developers and are being used in programming education such as in generation of coding problem examples or providing code explanations. A key aspect of programming education is understanding and dealing with error message. However, 'logical errors' in which the program operates against the programmer's intentions do not receive error messages from the compiler. In this study, building on existing research on programming errors, we first define the types of logical errors that can occur in programming in general. Based on the definition, we propose an effective approach for detecting logical errors with LLMs that makes use of relations among error types in the Chain-of-Thought and Tree-of-Thought prompts. The experimental results indicate that when such logical error descriptions in the prompt are used, the average classifition performance is about 21% higher than the ones without them. We also conducted an experiment for exploiting the relations among errors in generating a new logical error dataset using LLMs. As there is very limited dataset for logical errors such benchmark dataset can be very useful for various programming related applications. We expect that our work can assist novice programmers in identifying the causes of code errors and correct them more effectively.

Huichan Seo, Minki Hong, Sieun Choi et al.

Demographic bias in text-to-image (T2I) generation is well studied, yet demographic-conditioned failures in instruction-guided image-to-image (I2I) editing remain underexplored. We examine whether identical edit instructions yield systematically different outcomes across subject demographics in open-weight I2I editors. We formalize two failure modes: Soft Erasure, where edits are silently weakened or ignored in the output image, and Stereotype Replacement, where edits introduce unrequested, stereotype-consistent attributes. We introduce a controlled benchmark that probes demographic-conditioned behavior by generating and editing portraits conditioned on race, gender, and age using a diagnostic prompt set, and evaluate multiple editors with vision-language model (VLM) scoring and human evaluation. Our analysis shows that identity preservation failures are pervasive, demographically uneven, and shaped by implicit social priors, including occupation-driven gender inference. Finally, we demonstrate that a prompt-level identity constraint, without model updates, can substantially reduce demographic change for minority groups while leaving majority-group portraits largely unchanged, revealing asymmetric identity priors in current editors. Together, our findings establish identity preservation as a central and demographically uneven failure mode in I2I editing and motivate demographic-robust editing systems. Project page: https://seochan99.github.io/i2i-demographic-bias

Yanggyu Lee, Jihie Kim

In the realm of Large Language Model (LLM) functionalities, providing reliable information is paramount, yet reports suggest that LLM outputs lack consistency. This inconsistency, often at-tributed to randomness in token sampling, under-mines user trust as it leads to varying responses even for identical queries. In this paper, we present a new approach for evaluating semantic consistencies of LLM including comparison of alternative tech-niques. Our approach evaluates whether LLM re-sponses are semantically congruent for a given question, recognizing that as syntactically different sentences may convey the same meaning. Here-tofore, To enhance LLM consistency, two main approaches have been explored: Leverage external knowledge as context like the RAG pattern or use Zero-shot-CoT to improve performance of LLM itself. We apply our evaluation approach to these techniques, and demonstrate to compare the im-pact of these methods on LLM response con-sistency across different domains of question an-swering tasks. Using the TruthfulQA dataset to assess LLM responses, the study induces N re-sponses per question from the LLM and clusters semantically equivalent sentences to measure semantic consistency across 37 categories. Through this, it quantitatively analyzes the effectiveness of the aforementioned methods in improving LLM performance before and after their adoption.

Zahid Ullah, Dragan Pamucar, Jihie Kim

Magnetic Resonance Imaging (MRI) is widely recognized as the most reliable tool for detecting tumors due to its capability to produce detailed images that reveal their presence. However, the accuracy of diagnosis can be compromised when human specialists evaluate these images. Factors such as fatigue, limited expertise, and insufficient image detail can lead to errors. For example, small tumors might go unnoticed, or overlap with healthy brain regions could result in misidentification. To address these challenges and enhance diagnostic precision, this study proposes a novel double ensembling framework, consisting of ensembled pre-trained deep learning (DL) models for feature extraction and ensembled fine-tuned hyperparameter machine learning (ML) models to efficiently classify brain tumors. Specifically, our method includes extensive preprocessing and augmentation, transfer learning concepts by utilizing various pre-trained deep convolutional neural networks and vision transformer networks to extract deep features from brain MRI, and fine-tune hyperparameters of ML classifiers. Our experiments utilized three different publicly available Kaggle MRI brain tumor datasets to evaluate the pre-trained DL feature extractor models, ML classifiers, and the effectiveness of an ensemble of deep features along with an ensemble of ML classifiers for brain tumor classification. Our results indicate that the proposed feature fusion and classifier fusion improve upon the state of the art, with hyperparameter fine-tuning providing a significant enhancement over the ensemble method. Additionally, we present an ablation study to illustrate how each component contributes to accurate brain tumor classification.

Minsik Lee, Seoi Hong, Chongmin Lee et al.

Despite recent progress in automatic speech recognition (ASR), elderly ASR (EASR) remains challenging due to limited training data and the distinct acoustic and linguistic characteristics of elderly speech. In this work, we address data scarcity in EASR through a data augmentation pipeline that combines large language model (LLM)-based transcript paraphrasing with text-to-speech (TTS) synthesis. Given an elderly speech dataset, the LLM first generates elderly-contextual paraphrases of the original transcripts, and the TTS model then synthesizes corresponding speech using elderly reference speakers. The resulting synthetic audio-text pairs are merged with the original data to fine-tune Whisper without architectural modification. We further analyze the effects of augmentation ratio and reference-speaker composition in low-resource EASR. Experiments on English and Korean elderly speech datasets from speakers aged 70 and above show that the proposed method consistently improves performance over conventional augmentation baselines, achieving up to a 58.2% reduction in word error rate (WER) compared with the Whisper baseline.

Zahid Ullah, Jihie Kim

Accurate brain tumor classification is crucial in medical imaging to ensure reliable diagnosis and effective treatment planning. This study introduces a novel double ensembling framework that synergistically combines pre-trained deep learning (DL) models for feature extraction with optimized machine learning (ML) classifiers for robust classification. The framework incorporates comprehensive preprocessing and data augmentation of brain magnetic resonance images (MRI), followed by deep feature extraction using transfer learning with pre-trained Vision Transformer (ViT) networks. The novelty lies in the dual-level ensembling strategy: feature-level ensembling, which integrates deep features from the top-performing ViT models, and classifier-level ensembling, which aggregates predictions from hyperparameter-optimized ML classifiers. Experiments on two public Kaggle MRI brain tumor datasets demonstrate that this approach significantly surpasses state-of-the-art methods, underscoring the importance of feature and classifier fusion. The proposed methodology also highlights the critical roles of hyperparameter optimization (HPO) and advanced preprocessing techniques in improving diagnostic accuracy and reliability, advancing the integration of DL and ML for clinically relevant medical image analysis.

Suchae Jeong, Inseong Choi, Youngsik Yun et al.

Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to produce appropriate images for the cultural concepts or objects that are not well known or underrepresented in western cultures, such as `hangari' (Korean utensil). In this paper, we propose a novel approach, Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement (Culture-TRIP), which refines the prompt in order to improve the alignment of the image with such culture nouns in text-to-image models. Our approach (1) retrieves cultural contexts and visual details related to the culture nouns in the prompt and (2) iteratively refines and evaluates the prompt based on a set of cultural criteria and large language models. The refinement process utilizes the information retrieved from Wikipedia and the Web. Our user survey, conducted with 66 participants from eight different countries demonstrates that our proposed approach enhances the alignment between the images and the prompts. In particular, C-TRIP demonstrates improved alignment between the generated images and underrepresented culture nouns. Resource can be found at https://shane3606.github.io/Culture-TRIP.

Zahid Ullah, Jihie Kim

Deep learning-based cardiac segmentation has seen significant advancements over the years. Many studies have tackled the challenge of anatomically incorrect segmentation predictions by introducing auxiliary modules. These modules either post-process segmentation outputs or enforce consistency between specific points to ensure anatomical correctness. However, such approaches often increase network complexity, require separate training for these modules, and may lack robustness in scenarios with poor visibility. To address these limitations, we propose a novel transformer-based architecture that leverages dense associative networks to learn and retain specific patterns inherent to cardiac inputs. Unlike traditional methods, our approach restricts the network to memorize a limited set of patterns. During forward propagation, a weighted sum of these patterns is used to enforce anatomical correctness in the output. Since these patterns are input-independent, the model demonstrates enhanced robustness, even in cases with poor visibility. The proposed pipeline was evaluated on two publicly available datasets, CAMUS and CardiacNet. Experimental results indicate that our model consistently outperforms baseline approaches across all metrics, highlighting its effectiveness and reliability for cardiac segmentation tasks.

Huichan Seo, Sieun Choi, Minki Hong et al.

Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a unified evaluation across six countries, an 8-category/36-subcategory schema, and era-aware prompts, auditing both T2I generation and I2I editing under a standardized protocol that yields comparable diagnostics. Using open models with fixed settings, we derive cross-country, cross-era, and cross-category evaluations. Our framework combines standard automatic metrics, a culture-aware retrieval-augmented VQA, and expert human judgments collected from native reviewers. To enable reproducibility, we release the complete image corpus, prompts, and configurations. Our study reveals three findings: (1) under country-agnostic prompts, models default to Global-North, modern-leaning depictions that flatten cross-country distinctions; (2) iterative I2I editing erodes cultural fidelity even when conventional metrics remain flat or improve; and (3) I2I models apply superficial cues (palette shifts, generic props) rather than era-consistent, context-aware changes, often retaining source identity for Global-South targets. These results highlight that culture-sensitive edits remain unreliable in current systems. By releasing standardized data, prompts, and human evaluation protocols, we provide a reproducible, culture-centered benchmark for diagnosing and tracking cultural bias in generative image models.

Minki Hong, Jangho Choi, Jihie Kim

Social norms govern culturally appropriate behavior in communication, enabling dialogue systems to produce responses that are not only coherent but also socially acceptable. We present NormGenesis, a multicultural framework for generating and annotating socially grounded dialogues across English, Chinese, and Korean. To model the dynamics of social interaction beyond static norm classification, we propose a novel dialogue type, Violation-to-Resolution (V2R), which models the progression of conversations following norm violations through recognition and socially appropriate repair. To improve pragmatic consistency in underrepresented languages, we implement an exemplar-based iterative refinement early in the dialogue synthesis process. This design introduces alignment with linguistic, emotional, and sociocultural expectations before full dialogue generation begins. Using this framework, we construct a dataset of 10,800 multi-turn dialogues annotated at the turn level for norm adherence, speaker intent, and emotional response. Human and LLM-based evaluations demonstrate that NormGenesis significantly outperforms existing datasets in refinement quality, dialogue naturalness, and generalization performance. We show that models trained on our V2R-augmented data exhibit improved pragmatic competence in ethically sensitive contexts. Our work establishes a new benchmark for culturally adaptive dialogue modeling and provides a scalable methodology for norm-aware generation across linguistically and culturally diverse languages.

Zahid Ullah, Minki Hong, Tahir Mahmood et al.

Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this limitation, we systematically integrate attention mechanisms into five widely adopted CNN architectures, namely, VGG16, ResNet18, InceptionV3, DenseNet121, and EfficientNetB5, to enhance their ability to focus on salient regions and improve discriminative performance. Specifically, each baseline model is augmented with either a Squeeze and Excitation block or a hybrid Convolutional Block Attention Module, allowing adaptive recalibration of channel and spatial feature representations. The proposed models are evaluated on two distinct medical imaging datasets, a brain tumor MRI dataset comprising multiple tumor subtypes, and a Products of Conception histopathological dataset containing four tissue categories. Experimental results demonstrate that attention augmented CNNs consistently outperform baseline architectures across all metrics. In particular, EfficientNetB5 with hybrid attention achieves the highest overall performance, delivering substantial gains on both datasets. Beyond improved classification accuracy, attention mechanisms enhance feature localization, leading to better generalization across heterogeneous imaging modalities. This work contributes a systematic comparative framework for embedding attention modules in diverse CNN architectures and rigorously assesses their impact across multiple medical imaging tasks. The findings provide practical insights for the development of robust, interpretable, and clinically applicable deep learning based decision support systems.

Zahid Ullah, Jihie Kim

Continual learning (CL), the ability of a model to learn new tasks without forgetting previously acquired knowledge, remains a critical challenge in artificial intelligence, particularly for vision transformers (ViTs) utilizing Multilayer Perceptrons (MLPs) for global representation learning. Catastrophic forgetting, where new information overwrites prior knowledge, is especially problematic in these models. This research proposes replacing MLPs in ViTs with Kolmogorov-Arnold Network (KANs) to address this issue. KANs leverage local plasticity through spline-based activations, ensuring that only a subset of parameters is updated per sample, thereby preserving previously learned knowledge. The study investigates the efficacy of KAN-based ViTs in CL scenarios across benchmark datasets (MNIST, CIFAR100), focusing on their ability to retain accuracy on earlier tasks while adapting to new ones. Experimental results demonstrate that KAN-based ViTs significantly mitigate catastrophic forgetting, outperforming traditional MLP-based ViTs in knowledge retention and task adaptation. This novel integration of KANs into ViTs represents a promising step toward more robust and adaptable models for dynamic environments.

Tze Ho Elden Tse, Runyang Feng, Linfang Zheng et al.

With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise seen actions on unseen objects due to the limitations in representing object shape and movement using 3D bounding boxes. Additionally, the reliance on object templates at test time limits their generalisability to unseen objects. To address these challenges, we propose to leverage superquadrics as an alternative 3D object representation to bounding boxes and demonstrate their effectiveness on both template-free object reconstruction and action recognition tasks. Moreover, as we find that pure appearance-based methods can outperform the unified methods, the potential benefits from 3D geometric information remain unclear. Therefore, we study the compositionality of actions by considering a more challenging task where the training combinations of verbs and nouns do not overlap with the testing split. We extend H2O and FPHA datasets with compositional splits and design a novel collaborative learning framework that can explicitly reason about the geometric relations between hands and the manipulated object. Through extensive quantitative and qualitative evaluations, we demonstrate significant improvements over the state-of-the-arts in (compositional) action recognition.

Chongmin Lee, Jihie Kim

Certain cancer types, notably pancreatic cancer, are difficult to detect at an early stage, motivating robust biomarker-based screening. Liquid biopsies enable non-invasive monitoring of circulating biomarkers, but typical machine learning pipelines for high-dimensional tabular data (e.g., random forests, SVMs) rely on expensive hyperparameter tuning and can be brittle under class imbalance. We leverage a meta-trained Hyperfast model for classifying cancer, accomplishing the highest AUC of 0.9929 and simultaneously achieving robustness especially on highly imbalanced datasets compared to other ML algorithms in several binary classification tasks (e.g. breast invasive carcinoma; BRCA vs. non-BRCA). We also propose a novel ensemble model combining pre-trained Hyperfast model, XGBoost, and LightGBM for multi-class classification tasks, achieving an incremental increase in accuracy (0.9464) while merely using 500 PCA features; distinguishable from previous studies where they used more than 2,000 features for similar results. Crucially, we demonstrate robustness under class imbalance: empirically via balanced accuracy and minority-class recall across cancer-vs.-noncancer and cancer-vs.-rest settings, and theoretically by showing (i) a prototype-form final layer for Hyperfast that yields prior-insensitive decisions under bounded bias, and (ii) minority-error reductions for majority vote under mild error diversity. Together, these results indicate that pre-trained tabular models and simple ensembling can deliver state-of-the-art accuracy and improved minority-class performance with far fewer features and no additional tuning.

JinKyu Lee, Jihie Kim

Understanding commonsense knowledge is crucial in the field of Natural Language Processing (NLP). However, the presence of demographic terms in commonsense knowledge poses a potential risk of compromising the performance of NLP models. This study aims to investigate and propose methods for enhancing the performance and effectiveness of a commonsense polarization classifier by mitigating the influence of demographic terms. Three methods are introduced in this paper: (1) hierarchical generalization of demographic terms (2) threshold-based augmentation and (3) integration of hierarchical generalization and threshold-based augmentation methods (IHTA). The first method involves replacing demographic terms with more general ones based on a term hierarchy ontology, aiming to mitigate the influence of specific terms. To address the limited bias-related information, the second method measures the polarization of demographic terms by comparing the changes in the model's predictions when these terms are masked versus unmasked. This method augments commonsense sentences containing terms with high polarization values by replacing their predicates with synonyms generated by ChatGPT. The third method combines the two approaches, starting with threshold-based augmentation followed by hierarchical generalization. The experiments show that the first method increases the accuracy over the baseline by 2.33%, and the second one by 0.96% over standard augmentation methods. The IHTA techniques yielded an 8.82% and 9.96% higher accuracy than threshold-based and standard augmentation methods, respectively.

Zhixuan Liu, Peter Schaldenbrand, Beverley-Claire Okogwu et al.

Accurate representation in media is known to improve the well-being of the people who consume it. Generative image models trained on large web-crawled datasets such as LAION are known to produce images with harmful stereotypes and misrepresentations of cultures. We improve inclusive representation in generated images by (1) engaging with communities to collect a culturally representative dataset that we call the Cross-Cultural Understanding Benchmark (CCUB) and (2) proposing a novel Self-Contrastive Fine-Tuning (SCoFT) method that leverages the model's known biases to self-improve. SCoFT is designed to prevent overfitting on small datasets, encode only high-level information from the data, and shift the generated distribution away from misrepresentations encoded in a pretrained model. Our user study conducted on 51 participants from 5 different countries based on their self-selected national cultural affiliation shows that fine-tuning on CCUB consistently generates images with higher cultural relevance and fewer stereotypes when compared to the Stable Diffusion baseline, which is further improved with our SCoFT technique.

Jinyeong Chae, Ki Yong Hong, Jihie Kim

Increasing numbers of patients with disabilities or elderly people with mobility issues often suffer from a pressure ulcer. The affected areas need regular checks, but they have a difficulty in accessing a hospital. Some remote diagnosis systems are being used for them, but there are limitations in checking a patient's status regularly. In this paper, we present a remote medical assistant that can help pressure ulcer management with image processing techniques. The proposed system includes a mobile application with a deep learning model for wound segmentation and analysis. As there are not enough data to train the deep learning model, we make use of a pretrained model from a relevant domain and data augmentation that is appropriate for this task. First of all, an image preprocessing method using bilinear interpolation is used to resize images and normalize the images. Second, for data augmentation, we use rotation, reflection, and a watershed algorithm. Third, we use a pretrained deep learning model generated from skin wound images similar to pressure ulcer images. Finally, we added an attention module that can provide hints on the pressure ulcer image features. The resulting model provides an accuracy of 99.0%, an intersection over union (IoU) of 99.99%, and a dice similarity coefficient (DSC) of 93.4% for pressure ulcer segmentation, which is better than existing results.

Heriberto Cuayáhuitl, Donghyeon Lee, Seonghan Ryu et al.

Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an open question. This article describes a novel ensemble-based approach applied to value-based DRL chatbots, which use finite action sets as a form of meaning representation. In our approach, while dialogue actions are derived from sentence clustering, the training datasets in our ensemble are derived from dialogue clustering. The latter aim to induce specialised agents that learn to interact in a particular style. In order to facilitate neural chatbot training using our proposed approach, we assume dialogue data in raw text only -- without any manually-labelled data. Experimental results using chitchat data reveal that (1) near human-like dialogue policies can be induced, (2) generalisation to unseen data is a difficult problem, and (3) training an ensemble of chatbot agents is essential for improved performance over using a single agent. In addition to evaluations using held-out data, our results are further supported by a human evaluation that rated dialogues in terms of fluency, engagingness and consistency -- which revealed that our proposed dialogue rewards strongly correlate with human judgements.

Heriberto Cuayáhuitl, Donghyeon Lee, Seonghan Ryu et al.

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infinite actions, and a simple but promising reward function based on human-likeness scores derived from human-human dialogue data. We train Deep Reinforcement Learning (DRL) agents using chitchat data in raw text---without any manual annotations. Experimental results using different splits of training data report the following. First, that our agents learn reasonable policies in the environments they get familiarised with, but their performance drops substantially when they are exposed to a test set of unseen dialogues. Second, that the choice of sentence embedding size between 100 and 300 dimensions is not significantly different on test data. Third, that our proposed human-likeness rewards are reasonable for training chatbots as long as they use lengthy dialogue histories of >=10 sentences.

Heriberto Cuayáhuitl, Seonghan Ryu, Donghyeon Lee et al.

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given that the amount of dialogue history and corresponding representations can play an important role in the overall performance of a conversational system. This paper studies the amount of history required by conversational agents for reliably predicting dialogue rewards. The task of dialogue reward prediction is chosen for investigating the effects of varying amounts of dialogue history and their impact on system performance. Experimental results using a dataset of 18K human-human dialogues report that lengthy dialogue histories of at least 10 sentences are preferred (25 sentences being the best in our experiments) over short ones, and that lengthy histories are useful for training dialogue reward predictors with strong positive correlations between target dialogue rewards and predicted ones.

Seunghak Yu, Nilesh Kulkarni, Haejun Lee et al.

Language models for agglutinative languages have always been hindered in past due to myriad of agglutinations possible to any given word through various affixes. We propose a method to diminish the problem of out-of-vocabulary words by introducing an embedding derived from syllables and morphemes which leverages the agglutinative property. Our model outperforms character-level embedding in perplexity by 16.87 with 9.50M parameters. Proposed method achieves state of the art performance over existing input prediction methods in terms of Key Stroke Saving and has been commercialized.

Seunghak Yu, Nilesh Kulkarni, Haejun Lee et al.

Recent developments in deep learning with application to language modeling have led to success in tasks of text processing, summarizing and machine translation. However, deploying huge language models for mobile device such as on-device keyboards poses computation as a bottle-neck due to their puny computation capacities. In this work we propose an embedded deep learning based word prediction method that optimizes run-time memory and also provides a real time prediction environment. Our model size is 7.40MB and has average prediction time of 6.47 ms. We improve over the existing methods for word prediction in terms of key stroke savings and word prediction rate.