3463 papers
LangSurf introduces a Language-Embedded Surface Field that leverages a joint training strategy with geometry supervision and a Hierarchical-Context Awareness Module to accurately align 3D language fields with object surfaces, thereby significantly outperforming existing methods in open-vocabulary 2D/3D segmentation and enabling precise instance-level editing tasks.
This paper proposes a deep learning-based framework that integrates historical outage and weather data to predict event-level power system resilience, validated through both simulated and real-world datasets, to guide targeted investments in distributed energy resources for vulnerable regions.
This paper proposes a transfer learning approach using Twin Neural Networks to identify IoT firmware version changes by converting statistical packet flow features into images, achieving high accuracy in detecting subtle traffic differences with limited training data.
This case study evaluates the impact of the CGScholar AI Helper on the writing development of 11th-grade students in a low-income school, finding that the tool's customized AI feedback effectively supported student writing while also generating valuable suggestions for the tool's future improvement.
This paper presents a novel hybrid approach combining static graph transformation-based taint analysis with dynamic verification to systematically detect both direct and indirect broken access control vulnerabilities in Graph APIs, as demonstrated through an application to the GitHub GraphQL API.
This paper proposes a novel, problem-agnostic diffusion model that enhances inverse problems by decomposing the conditional score function into an unconditional pretrained component and a Gaussian-prior-based MAP-guided term, resulting in superior content preservation and structural coherence compared to state-of-the-art methods.
VL-Nav is a neuro-symbolic vision-language navigation system that integrates neural reasoning with symbolic guidance through a task planner and exploration module to enable autonomous robots to effectively decompose complex instructions and navigate unseen large-scale environments, achieving high success rates in both simulated and real-world scenarios.
This paper presents a technical framework and taxonomy to systematically analyze and critically assess the "security vs. interoperability" arguments used by big tech companies to resist regulatory mandates aimed at breaking market monopolies.
Prompt-SID is a self-supervised single-image denoising framework that leverages a latent diffusion-based structural representation generator and a scale replay training mechanism to preserve detailed structural information without relying on expensive paired datasets.
This comprehensive PRISMA-guided survey of 232 studies evaluates the current state of responsible generative AI across four system types, identifies critical gaps in benchmark coverage and evaluation methodologies, and proposes a structured framework of rubrics, KPIs, and a research agenda to align technical assessment with governance needs for safe and sustainable deployment.
This study proposes a high-accuracy glioma subclass classification framework that fuses 2D and 3D UNET-segmented multimodal MRI images using weighted averaging and classifies them via a pre-trained ResNet50 model, achieving a 99.25% accuracy rate.
This paper proposes a deep learning-based approach utilizing UNET, Inception, and ResNet architectures to achieve automatic 2D and 3D glioma segmentation on BraTS datasets, demonstrating that a ResNet model effectively balances computational efficiency and spatial accuracy to significantly improve diagnosis with high accuracy and Dice scores.
This paper introduces DEBT control, a joint routing and flow-control protocol for payment channel networks that uses price-based mechanisms and gradient descent optimization to guide the network toward an optimal steady-state operating condition while providing convergence guarantees.
The paper proposes the Diffusion Stabilizer Policy (DSP), a two-stage diffusion-based framework that enables surgical robots to learn from imperfect or failed trajectories by initially training on clean data and then continuously updating with a filtered mixture of clean and perturbed demonstrations to achieve robust performance in automated surgical tasks.
This paper proposes a novel dual-thread framework that enables concurrent planning and acting with interruptible execution for LLM-based multi-agent systems, overcoming the limitations of serialized paradigms to enhance real-time responsiveness and adaptability in dynamic environments like Minecraft.
This paper proposes a novel transformer-based geometric deep learning model that tokenizes tetrahedral meshes with anatomical landmarks to accurately classify Alzheimer's disease and predict brain amyloid positivity in medium-risk individuals, offering a robust alternative to costly and invasive PET scans.
ViLAM is a novel method that distills vision-language reasoning from large Vision-Language Models into spatial attention maps to guide socially compliant robot navigation, achieving significant improvements in success rates through real-world validation.
Snapmoji is an innovative avatar generation system that instantly creates animatable 3D avatars from user selfies by employing Gaussian Domain Adaptation for identity preservation and a novel dual-stylization process to apply secondary styles, all while overcoming the limitations of existing platforms through efficient mobile rendering.
The paper introduces iProg, an interactive tool that leverages a structured communication protocol between humans and large language models to decompose scientific data analysis tasks into declarative Data Flow Diagrams and generate corresponding code, thereby achieving significantly faster development, higher code quality, and better performance than traditional Low Code/No Code alternatives.
This paper introduces SceneEval, a comprehensive evaluation framework and benchmark (SceneEval-500) designed to assess text-conditioned 3D indoor scene synthesis by measuring both explicit user requirements and implicit plausibility expectations, revealing significant gaps in current generation methods.