Yugyung Lee

Ahmed Albishri, Syed Jawad Hussain Shah, Yugyung Lee et al.

Accurate detection of oral cancer is crucial for improving patient outcomes. However, the field faces two key challenges: the scarcity of deep learning-based image segmentation research specifically targeting oral cancer and the lack of annotated data. Our study proposes OCU-Net, a pioneering U-Net image segmentation architecture exclusively designed to detect oral cancer in hematoxylin and eosin (H&E) stained image datasets. OCU-Net incorporates advanced deep learning modules, such as the Channel and Spatial Attention Fusion (CSAF) module, a novel and innovative feature that emphasizes important channel and spatial areas in H&E images while exploring contextual information. In addition, OCU-Net integrates other innovative components such as Squeeze-and-Excite (SE) attention module, Atrous Spatial Pyramid Pooling (ASPP) module, residual blocks, and multi-scale fusion. The incorporation of these modules showed superior performance for oral cancer segmentation for two datasets used in this research. Furthermore, we effectively utilized the efficient ImageNet pre-trained MobileNet-V2 model as a backbone of our OCU-Net to create OCU-Netm, an enhanced version achieving state-of-the-art results. Comprehensive evaluation demonstrates that OCU-Net and OCU-Netm outperformed existing segmentation methods, highlighting their precision in identifying cancer cells in H&E images from OCDC and ORCA datasets.

Luke James Miller, Yugyung Lee

Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resolution inference scales poorly and forces most pipelines to rely on fixed regionization or downsampling, coupling computational cost to image resolution and attenuating boundary evidence precisely where minority structures are most informative. We introduce SEMIR (Semantic Minor-Induced Representation Learning), a representation framework that decouples inference from the native grid by learning a task-adapted, topology-preserving latent graph representation with exact decoding. SEMIR transforms the underlying grid graph into a compact, boundary-aligned graph minor through parameterized edge contraction, node deletion, and edge deletion, while preserving an exact lifting map from minor predictions to lattice labels. Minor construction is formalized as a few-shot structure learning problem that replaces hand-tuned preprocessing with a boundary-alignment objective: minor parameters are learned by maximizing agreement between predicted boundary elements and target-specific semantic edges under a boundary Dice criterion, and the induced minor is annotated with scale- and rotation-robust geometric and intensity descriptors and supports efficient region-level inference via message passing on a graph neural network (GNN) with relational edge features. We benchmark SEMIR on three tumor segmentation datasets -- BraTS 2021, KiTS23, and LiTS -- where targets exhibit high structural variability and distributional uncertainty. SEMIR yields consistent improvements in minority-structure Dice at practical runtime. More broadly, SEMIR establishes a framework for learning task-adapted, topology-preserving latent representations with exact decoding for high-resolution structured visual data.

Udiptaman Das, Krishnasai B. Atmakuri, Duy Ho et al.

Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy and semantic consistency, limitations that are especially problematic in oncology. We introduce an end-to-end framework for clinical KG construction and evaluation directly from free text using multi-agent prompting and a schema-constrained Retrieval-Augmented Generation (KG-RAG) strategy. Our pipeline integrates (1) prompt-driven entity, attribute, and relation extraction; (2) entropy-based uncertainty scoring; (3) ontology-aligned RDF/OWL schema generation; and (4) multi-LLM consensus validation for hallucination detection and semantic refinement. Beyond static graph construction, the framework supports continuous refinement and self-supervised evaluation, enabling iterative improvement of graph quality. Applied to two oncology cohorts (PDAC and BRCA), our method produces interpretable, SPARQL-compatible, and clinically grounded knowledge graphs without relying on gold-standard annotations. Experimental results demonstrate consistent gains in precision, relevance, and ontology compliance over baseline methods.

Muhammad Imran, Chi Lee, Yugyung Lee

We introduce MATEX (Multi-scale Attention and Text-guided Explainability), a novel framework that advances interpretability in medical vision-language models by incorporating anatomically informed spatial reasoning. MATEX synergistically combines multi-layer attention rollout, text-guided spatial priors, and layer consistency analysis to produce precise, stable, and clinically meaningful gradient attribution maps. By addressing key limitations of prior methods, such as spatial imprecision, lack of anatomical grounding, and limited attention granularity, MATEX enables more faithful and interpretable model explanations. Evaluated on the MS-CXR dataset, MATEX outperforms the state-of-the-art M2IB approach in both spatial precision and alignment with expert-annotated findings. These results highlight MATEX's potential to enhance trust and transparency in radiological AI applications.

Mike Farmer, Abhinav Kochar, Yugyung Lee

Large language models (LLMs) that iteratively revise their outputs through mechanisms such as chain-of-thought reasoning, self-reflection, or multi-agent debate lack principled guarantees regarding the stability of their probability updates. We identify a consistent multiplicative scaling law that governs how instruction-tuned LLMs revise probability assignments over candidate answers, expressed as a belief revision exponent that controls how prior beliefs and verification evidence are combined during updates. We show theoretically that values of the exponent below one are necessary and sufficient for asymptotic stability under repeated revision. Empirical evaluation across 4,975 problems spanning graduate-level benchmarks (GPQA Diamond, TheoremQA, MMLU-Pro, and ARC-Challenge) and multiple model families (GPT-5.2 and Claude Sonnet 4) reveals near-Bayesian update behavior, with models operating slightly above the stability boundary in single-step revisions. However, multi-step experiments demonstrate that the exponent decreases over successive revisions, producing contractive long-run dynamics consistent with theoretical stability predictions. Token-level validation using Llama-3.3-70B further confirms similar behavior across both log-probability measurements and self-reported confidence elicitation. Analysis of update components exposes architecture-specific trust-ratio patterns, with GPT-5.2 showing balanced weighting between prior and evidence, while Claude modestly favors new evidence. This work characterizes observable inference-time update behavior rather than internal Bayesian reasoning, and introduces the α-law as a principled diagnostic for monitoring update stability and reasoning quality in LLM inference systems.

Yiyang Liu, James Chenhao Liang, Ruixiang Tang et al.

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues to grow, fully fine-tuning these models has become highly parameter-intensive. Although Parameter-Efficient Fine-Tuning (PEFT) methods have been introduced to reduce the number of tunable parameters, a significant performance gap remains compared to full fine-tuning. Furthermore, existing PEFT approaches are often highly parameterized, making them difficult to interpret and control. In light of this, we introduce Multimodal Representation Tuning (MRT), a novel approach that focuses on directly editing semantically rich multimodal representations to achieve strong performance and provide intuitive control over LMMs. Empirical results show that our method surpasses current state-of-the-art baselines with significant performance gains (e.g., 1580.40 MME score) while requiring substantially fewer tunable parameters (e.g., 0.03% parameters). Additionally, we conduct experiments on editing instrumental tokens within multimodal representations, demonstrating that direct manipulation of these representations enables simple yet effective control over network behavior.

Michael Farmer, Abhinav Kochar, Yugyung Lee

We show that Fisher-regularized Wasserstein gradient flows exhibit a previously unrecognized interference mechanism in their dissipation identity: a cross-dissipation term whose sign becomes positive when the state width falls below a critical scale. In this regime the geometric Fisher channel transiently opposes descent of the baseline free-energy functional, producing what we term the Fisher Paradox. Restricting the flow to the Gaussian manifold yields an exact Riccati-type variance equation with a closed-form trajectory, exposing three dynamical regimes separated by two critical scales: sigma = 1 (cross-dissipation sign flip) and sigma = sqrt(epsilon) (Fisher takeover). The variance potential V(u) = u^2 - 2u - epsilon ln(u) contains a logarithmic centrifugal barrier that shifts the equilibrium attractor by Delta sigma approx epsilon/4. The interference persists for a duration t_cross ~ D_KL, linking the dissipation delay directly to the initial information distance. Finite-difference simulations on a 512-point grid confirm all analytical predictions to within 5.21 x 10^-4 mean relative error. Numerical experiments with bimodal and Laplace initial conditions confirm the effect persists beyond Gaussian closure, with direct implications for information-geometric dissipative dynamics.

Ahmed Alanazi, Duy Ho, Yugyung Lee

Robots navigating dynamic, cluttered, and semantically complex environments must integrate perception, symbolic reasoning, and spatial planning to generalize across diverse layouts and object categories. Existing methods often rely on static priors or limited memory, constraining adaptability under partial observability and semantic ambiguity. We present GRIP, Grid-based Relay with Intermediate Planning, a unified, modular framework with three scalable variants: GRIP-L (Lightweight), optimized for symbolic navigation via semantic occupancy grids; GRIP-F (Full), supporting multi-hop anchor chaining and LLM-based introspection; and GRIP-R (Real-World), enabling physical robot deployment under perceptual uncertainty. GRIP integrates dynamic 2D grid construction, open-vocabulary object grounding, co-occurrence-aware symbolic planning, and hybrid policy execution using behavioral cloning, D* search, and grid-conditioned control. Empirical results on AI2-THOR and RoboTHOR benchmarks show that GRIP achieves up to 9.6% higher success rates and over $2\times$ improvement in path efficiency (SPL and SAE) on long-horizon tasks. Qualitative analyses reveal interpretable symbolic plans in ambiguous scenes. Real-world deployment on a Jetbot further validates GRIP's generalization under sensor noise and environmental variation. These results position GRIP as a robust, scalable, and explainable framework bridging simulation and real-world navigation.

Muhammad Usman, Yugyung Lee

Dynamic trust evaluation in large, rapidly evolving graphs requires models that can capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-based Trust Evaluation Network) introduces a unified graph framework that achieves all three by combining uncertainty-aware message passing, expressive temporal modeling, and built-in defenses against trust-targeted attacks. It represents nodes and edges as Gaussian distributions so that both semantic signals and epistemic uncertainty propagate through the graph neural network, enabling risk-aware trust decisions rather than overconfident guesses. To model how trust evolves, it employs hybrid Absolute-Gaussian-Hourglass (HAGH) positional encoding with Kolmogorov-Arnold network-based unbiased multi-head attention, followed by an ordinary differential equation (ODE)-based residual learning module to jointly capture abrupt shifts and smooth trends. Robust adaptive ensemble coefficient analysis prunes or down-weights suspicious interactions using complementary cosine and Jaccard similarity measures, mitigating reputation laundering, sabotage, and on/off attacks. On two signed Bitcoin trust networks, DGTEN delivers significant improvements: in single-timeslot prediction on Bitcoin-Alpha, it improves MCC by 10.77% over the best dynamic baseline; in the cold-start scenario, it achieves a 16.41% MCC gain - the largest across all tasks and datasets. Under adversarial on/off attacks, it surpasses the baseline by up to 11.63% MCC. These results validate the effectiveness of the unified DGTEN framework.

Muhammad Imran, Yugyung Lee

Recent advances in vision-language models have significantly expanded the frontiers of automated image analysis. However, applying these models in safety-critical contexts remains challenging due to the complex relationships between objects, subtle visual cues, and the heightened demand for transparency and reliability. This paper presents the Multi-Modal Explainable Learning (MMEL) framework, designed to enhance the interpretability of vision-language models while maintaining high performance. Building upon prior work in gradient-based explanations for transformer architectures (Grad-eclip), MMEL introduces a novel Hierarchical Semantic Relationship Module that enhances model interpretability through multi-scale feature processing, adaptive attention weighting, and cross-modal alignment. Our approach processes features at multiple semantic levels to capture relationships between image regions at different granularities, applying learnable layer-specific weights to balance contributions across the model's depth. This results in more comprehensive visual explanations that highlight both primary objects and their contextual relationships with improved precision. Through extensive experiments on standard datasets, we demonstrate that by incorporating semantic relationship information into gradient-based attribution maps, MMEL produces more focused and contextually aware visualizations that better reflect how vision-language models process complex scenes. The MMEL framework generalizes across various domains, offering valuable insights into model decisions for applications requiring high interpretability and reliability.

Sumaiya Tabassum Nimi, Md Adnan Arefeen, Md Yusuf Sarwar Uddin et al.

Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e.g., images) to a server (i.e., cloud) where the heavy deep learning models run. While this setup works cost-effectively for successful inferences, it severely underperforms when the model faces input samples on which the model was not trained (known as Out-of-Distribution (OOD) samples). If the edge devices could, at least, detect that an input sample is an OOD, that could potentially save communication and computation resources by not uploading those inputs to the server for inference workload. In this paper, we propose a novel lightweight OOD detection approach that mines important features from the shallow layers of a pretrained CNN model and detects an input sample as ID (In-Distribution) or OOD based on a distance function defined on the reduced feature space. Our technique (a) works on pretrained models without any retraining of those models, and (b) does not expose itself to any OOD dataset (all detection parameters are obtained from the ID training dataset). To this end, we develop EARLIN (EARLy OOD detection for Collaborative INference) that takes a pretrained model and partitions the model at the OOD detection layer and deploys the considerably small OOD part on an edge device and the rest on the cloud. By experimenting using real datasets and a prototype implementation, we show that our technique achieves better results than other approaches in terms of overall accuracy and cost when tested against popular OOD datasets on top of popular deep learning models pretrained on benchmark datasets.

Mohamoud Ali, Yugyung Lee, Praveen Rao

Dynamic networks have intrinsic structural, computational, and multidisciplinary advantages. Link prediction estimates the next relationship in dynamic networks. However, in the current link prediction approaches, only bipartite or non-bipartite but homogeneous networks are considered. The use of adjacency matrix to represent dynamically evolving networks limits the ability to analytically learn from heterogeneous, sparse, or forming networks. In the case of a heterogeneous network, modeling all network states using a binary-valued matrix can be difficult. On the other hand, sparse or currently forming networks have many missing edges, which are represented as zeros, thus introducing class imbalance or noise. We propose a time-parameterized matrix (TP-matrix) and empirically demonstrate its effectiveness in non-bipartite, heterogeneous networks. In addition, we propose a predictive influence index as a measure of a node's boosting or diminishing predictive influence using backward and forward-looking maximization over the temporal space of the n-degree neighborhood. We further propose a new method of canonically representing heterogeneous time-evolving activities as a temporally parameterized network model (TPNM). The new method robustly enables activities to be represented as a form of a network, thus potentially inspiring new link prediction applications, including intelligent business process management systems and context-aware workflow engines. We evaluated our model on four datasets of different network systems. We present results that show the proposed model is more effective in capturing and retaining temporal relationships in dynamically evolving networks. We also show that our model performed better than state-of-the-art link prediction benchmark results for networks that are sensitive to temporal evolution.

Somaieh Goudarzvand, Gharib Gharibi, Yugyung Lee

We present a k-competitive learning approach for textual autoencoders named Second Chance Autoencoder (SCAT). SCAT selects the $k$ largest and smallest positive activations as the winner neurons, which gain the activation values of the loser neurons during the learning process, and thus focus on retrieving well-representative features for topics. Our experiments show that SCAT achieves outstanding performance in classification, topic modeling, and document visualization compared to LDA, K-Sparse, NVCTM, and KATE.

Mayanka Chandrashekar, Yugyung Lee

Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real (unseen) data in applications. Recent works including Zero-Shot Learning (ZSL), have attempted to deal with this problem of overcoming the apparent gap through transfer learning. In this paper, we propose a novel model, called Class Representative Learning Model (CRL), that can be especially effective in image classification influenced by ZSL. In the CRL model, first, the learning step is to build class representatives to represent classes in datasets by aggregating prominent features extracted from a Convolutional Neural Network (CNN). Second, the inferencing step in CRL is to match between the class representatives and new data. The proposed CRL model demonstrated superior performance compared to the current state-of-the-art research in ZSL and mobile deep learning. The proposed CRL model has been implemented and evaluated in a parallel environment, using Apache Spark, for both distributed learning and recognition. An extensive experimental study on the benchmark datasets, ImageNet-1K, CalTech-101, CalTech-256, CIFAR-100, shows that CRL can build a class distribution model with drastic improvement in learning and recognition performance without sacrificing accuracy compared to the state-of-the-art performances in image classification.

Ahmed Awad Albishri, Syed Jawad Hussain Shah, Anthony Schmiedler et al.

In recent years, Deep Learning (DL) has shown promising results in conducting AI tasks such as computer vision and image segmentation. Specifically, Convolutional Neural Network (CNN) models in DL have been applied to prevention,detection, and diagnosis in predictive medicine. Image segmentation plays a significant role in disease detection and prevention.However, there are enormous challenges in performing DL-based automatic segmentation due to the nature of medical images such as heterogeneous modalities and formats, insufficient labeled training data, and the high-class imbalance in the labeled data. Furthermore, automating segmentation of medical images,like magnetic resonance images (MRI), becomes a challenging task. The need for automated segmentation or annotation is what motivates our work. In this paper, we propose a fully automated approach that aims to segment the human claustrum for analytical purposes. We applied a U-Net CNN model to segment the claustrum (Cl) from a MRI dataset. With this approach, we have achieved an average Dice per case score of 0.72 for Cl segmentation, with K=5 for cross-validation. The expert in the medical domain also evaluates these results.

Feichen Shen, Yugyung Lee

Biomedical ontology refers to a shared conceptualization for a biomedical domain of interest that has vastly improved data management and data sharing through the open data movement. The rapid growth and availability of biomedical data make it impractical and computationally expensive to perform manual analysis and query processing with the large scale ontologies. The lack of ability in analyzing ontologies from such a variety of sources, and supporting knowledge discovery for clinical practice and biomedical research should be overcome with new technologies. In this study, we developed a Medical Topic discovery and Query generation framework (MedTQ), which was composed by a series of approaches and algorithms. A predicate neighborhood pattern-based approach introduced has the ability to compute the similarity of predicates (relations) in ontologies. Given a predicate similarity metric, machine learning algorithms have been developed for automatic topic discovery and query generation. The topic discovery algorithm, called the hierarchical K-Means algorithm was designed by extending an existing supervised algorithm (K-means clustering) for the construction of a topic hierarchy. In the hierarchical K-Means algorithm, a level-by-level optimization strategy was selected for consistent with the strongly association between elements within a topic. Automatic query generation was facilitated for discovered topic that could be guided users for interactive query design and processing. Evaluation was conducted to generate topic hierarchy for DrugBank ontology as a case study. Results demonstrated that the MedTQ framework can enhance knowledge discovery by capturing underlying structures from domain specific data and ontologies.

Sourish Dasgupta, Satish Bhat, Yugyung Lee

Service discovery is one of the key problems that has been widely researched in the area of Service Oriented Architecture (SOA) based systems. Service category learning is a technique for efficiently facilitating service discovery. Most approaches for service category learning are based on suitable similarity distance measures using thresholds. Threshold selection is essentially difficult and often leads to unsatisfactory accuracy. In this paper, we have proposed a self-organizing based clustering algorithm called Semantic Taxonomical Clustering (STC) for taxonomically organizing services with self-organizing information and knowledge. We have tested the STC algorithm on both randomly generated data and the standard OWL-S TC dataset. We have observed promising results both in terms of classification accuracy and runtime performance compared to existing approaches.