December 2025

Generative models have achieved remarkable success in producing realistic images and short video clips, but existing approaches struggle to maintain *persistent worldcoherence over long durations and across multiple modalities. We propose Multimodal Supervisory Graphs (MSG), a novel framework for world modeling that unifies geometry (3D structure), identity (consistent entities), physics (dynamic behavior), and interaction (user/agent inputs) in a single abstract representation. MSG represents the environment as a dynamic latent graph, factorized by these four aspects and trained with […]

Ver mais

Traditional e-commerce visualization relies on static 3D spins or pre-rendered videos, which fail to convey material properties such as stiffness, flexibility, or sole compression. This lack of tactile feedback creates a “trust gap” for online buyers. In this paper, we introduce PhysiGen, a “What If?” viewer that allows users to apply virtual forces to product models. Leveraging a novel Action-Conditional Reconstruction technique, our system utilizes a physics-informed world model to generate short video sequences of deformation (e.g., shoe […]

Ver mais

On the basis of the isomorphic algebraic structures of the field of complex numbers ℂ and the 2-dimensional Euclidean field of real vectors V₂, in terms of identical geometric products of elements, this paper brings integral identities for scalar and vector fields in V₂, which are vector analogues of the well-known integral identities of complex analysis. Consequently, in this paper, Theorem 1., which is a generalized fundamental theorem of integral calculus in the field V₂, is the vector […]

Ver mais

High-fidelity telepresence requires the reconstruction of photorealistic 3D avatars in real-time to facilitate immersive interaction. Current solutions face a dichotomy: they are either computationally expensive multi-view systems (e.g., Codec Avatars) or lightweight mesh-based approximations that suffer from the “uncanny valley” effect due to a lack of high-frequency detail. In this paper, we propose Mono-Splat, a novel framework for reconstructing high-fidelity, animatable human avatars from a single monocular webcam video stream. Our method leverages 3D Gaussian Splatting (3DGS) combined […]

Ver mais

Diminished Reality (DR)—the ability to visually remove real-world objects from a live Augmented Reality (AR) feed—is essential for reducing cognitive load and decluttering workspaces. However, existing techniques face a critical challenge: removing an object creates a visual void (“hole”) that must be filled with a plausible background. Traditional 2D inpainting methods lack temporal consistency, causing the background to flicker or slide as the user moves. In this paper, we propose Clean-Splat, a novel framework for real-time, multi-view consistent […]

Ver mais

This paper presents Sem4EDA, an ontology-driven and rule-based framework for automated fault diagnosis and energy-aware optimization in Electronic Design Automation (EDA) and Internet of Things (IoT) environments. The escalating complexity of modern hardware systems, particularly within IoT and embedded domains, presents formidable challenges for traditional EDA methodologies. While EDA tools excel at design and simulation, they often operate as siloed applications, lacking the semantic context necessary for intelligent fault diagnosis and system-level optimization. Sem4EDA addresses this gap by […]

Ver mais

Placental abruption is detachment of the placenta before delivery from the implantation site that may have a potential to develop life-threating emergency clinic syptoms. The multifactorial nature of this disorder and no lab testing or procedures that can diagnose placental abruption. makes it difficult to predict. Artificial intelligence (AI) and machine learning (ML) have the potential to enhance clinical decision-making and enable precise assessments. This study purposed on predictive 15 ML models for placental abruption high-lighting input characteristics, […]

Ver mais

Deep Learning (DL) has undergone widespread adoption for medical image analysis and diagnosis. Numerous studies have explored mammographic image analysis for breast cancer screening. For this study, we assessed the hypothesis that stratifying mammography images based on the presence or absence of a corresponding region of interest (ROI) improves classification accuracy for both normal–abnormal and benign–malignant classifications. Our methodology involves independently training models and performing predictions on each subgroup with subsequent integration of the results. We used several […]

Ver mais