A cross-attention-based bipartite GNN predicts coupled nodal displacement increments and elemental thinning directly on their native mesh domains for sheet material forming.
Title resolution pending
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
representative citing papers
KAConvNet introduces a Kolmogorov-Arnold Convolutional Layer to build networks competitive with ViTs and CNNs while offering stronger theoretical interpretability.
DuoServe-MoE decouples prefill and decode phases in MoE LLM inference with a two-stream CUDA pipeline for prefill and an offline-trained predictor for decode, reporting up to 5.34x TTFT and 7.55x end-to-end latency gains.
Student models distilled from code language models often fail to deeply mimic teachers, showing up to 62% behavioral discrepancies and 285% worse drops under attacks that accuracy metrics miss.
Integrates LLMs with domain ontologies and SHACL constraints to produce accurate, explainable structured outputs from cybersecurity logs for threat intelligence.
A physics-informed GNN-transformer model performs unsupervised modal decomposition and identification for populations of structures from sparse dynamic measurements.
UGCP is a differentiable plug-in that performs uncertainty-guided local logit updates to refine vessel segmentations, reduce disconnections, and improve structural consistency on 2D and 3D medical datasets.
Fisher vector encoding integrated into CNN-ViT hybrids outperforms benchmarks on MedMNIST datasets and matches literature results on other medical image sets.
A new CNN-Transformer hybrid with twin-branch 3D/2D convolution, hybrid pooling attention, cascade spectral transformers, and cross-layer fusion reports higher accuracy than prior methods on standard hyperspectral datasets.
U-GLAD models learner uncertainty with Gaussian LSTMs and uses cognition-adaptive diffusion to generate goal-aligned learning path recommendations that outperform baselines on public datasets.
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
Uni-TSA applies a pre-trained generative Transformer with channel-independent data processing, freeze-and-finetune adaptation, and scheduled sampling to achieve zero-shot and data-efficient universal transient stability prediction across power systems.
HSANet uses Efficient Global Attention and hybrid upsampling in a Swin-based architecture to achieve better simultaneous denoising of low-dose PET/CT images than prior methods with a compact model.
citing papers explorer
-
Cross-attention-based bipartite graph neural network for coupled nodal and elemental field prediction in large-deformation sheet material forming
A cross-attention-based bipartite GNN predicts coupled nodal displacement increments and elemental thinning directly on their native mesh domains for sheet material forming.
-
KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition
KAConvNet introduces a Kolmogorov-Arnold Convolutional Layer to build networks competitive with ViTs and CNNs while offering stronger theoretical interpretability.
-
DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance
DuoServe-MoE decouples prefill and decode phases in MoE LLM inference with a two-stream CUDA pipeline for prefill and an offline-trained predictor for decode, reporting up to 5.34x TTFT and 7.55x end-to-end latency gains.
-
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?
Student models distilled from code language models often fail to deeply mimic teachers, showing up to 62% behavioral discrepancies and 285% worse drops under attacks that accuracy metrics miss.
-
Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
Integrates LLMs with domain ontologies and SHACL constraints to produce accurate, explainable structured outputs from cybersecurity logs for threat intelligence.
-
Modal Decomposition and Identification for a Population of Structures Using Physics-Informed Graph Neural Networks and Transformers
A physics-informed GNN-transformer model performs unsupervised modal decomposition and identification for populations of structures from sparse dynamic measurements.
-
Uncertainty-Guided Conservative Propagation for Structured Inference in Vessel Segmentation
UGCP is a differentiable plug-in that performs uncertainty-guided local logit updates to refine vessel segmentations, reduce disconnections, and improve structural consistency on 2D and 3D medical datasets.
-
Deep neural networks with Fisher vector encoding for medical image classification
Fisher vector encoding integrated into CNN-ViT hybrids outperforms benchmarks on MedMNIST datasets and matches literature results on other medical image sets.
-
A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification
A new CNN-Transformer hybrid with twin-branch 3D/2D convolution, hybrid pooling attention, cascade spectral transformers, and cross-layer fusion reports higher accuracy than prior methods on standard hyperspectral datasets.
-
Uncertainty-aware Generative Learning Path Recommendation with Cognition-Adaptive Diffusion
U-GLAD models learner uncertainty with Gaussian LSTMs and uses cognition-adaptive diffusion to generate goal-aligned learning path recommendations that outperform baselines on public datasets.
-
ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
-
Universal Transient Stability Analysis: A Pre-trained Generative Transformer-Enabled Power System Dynamics Prediction Framework
Uni-TSA applies a pre-trained generative Transformer with channel-independent data processing, freeze-and-finetune adaptation, and scheduled sampling to achieve zero-shot and data-efficient universal transient stability prediction across power systems.
-
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
HSANet uses Efficient Global Attention and hybrid upsampling in a Swin-based architecture to achieve better simultaneous denoising of low-dose PET/CT images than prior methods with a compact model.