Search Results for author:
Found 25 papers, 11 papers with code
Refining Interactions: Enhancing Anisotropy in Graph Neural Networks with Language Semantics
The integration of Large Language Models (LLMs) with Graph Neural Networks (GNNs) has recently been explored to enhance the capabilities of Text Attribute Graphs (TAGs).
Collaborative Evolution: Multi-Round Learning Between Large and Small Language Models for Emergent Fake News Detection
The proliferation of fake news on social media platforms has exerted a substantial influence on society, leading to discernible impacts and deleterious consequences.
Asteroid shape inversion with light curves using deep learning
In addition, we used 3D point clouds to represent asteroid shapes and utilized the deviation between the light curves of non-convex asteroids and their convex hulls to predict the concave areas of non-convex asteroids.
Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in reasoning, planning, and decision-making.
MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution
In line with this insight, we introduce Multi-Range Attention Transformer (MAT) tailored for SR tasks.
Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
LLMs have demonstrated commendable performance across diverse domains.
Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
Multi-hop Question Answering (QA) necessitates complex reasoning by integrating multiple pieces of information to resolve intricate questions.
Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation
Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years.
Diff-Shadow: Global-guided Diffusion Model for Shadow Removal
Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images.
Large Kernel Distillation Network for Efficient Single Image Super-Resolution
Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years.
Improved Esophageal Varices Assessment from Non-Contrast CT Scans
Esophageal varices (EV), a serious health concern resulting from portal hypertension, are traditionally diagnosed through invasive endoscopic procedures.
LIDIA: Precise Liver Tumor Diagnosis on Multi-Phase Contrast-Enhanced CT via Iterative Fusion and Asymmetric Contrastive Learning
The early detection and precise diagnosis of liver tumors are tasks of critical clinical value, yet they pose significant challenges due to the high heterogeneity and variability of liver tumors.
Spiral Scanning and Self-Supervised Image Reconstruction Enable Ultra-Sparse Sampling Multispectral Photoacoustic Tomography
To address this challenge, we propose an ultra-sparse spiral sampling strategy for multispectral PAT, which we named U3S-PAT.
FineFake: A Knowledge-Enriched Dataset for Fine-Grained Multi-Domain Fake News Detection
Existing benchmarks for fake news detection have significantly contributed to the advancement of models in assessing the authenticity of news content.
LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
Experiments illustrate that LangGPT significantly enhances the performance of LLMs.
MixMobileNet: A Mixed Mobile Network for Edge Vision Applications
For global, we propose the global-feature aggregation encoder (GFAE), which employs a pooling strategy and computes the covariance matrix between channels instead of the spatial dimensions, changing the computational complexity from quadratic to linear, and this accelerates the inference of the model.
Enhancing Cognitive Diagnosis using Un-interacted Exercises: A Collaboration-aware Mixed Sampling Approach
Finally, we demonstrate the effectiveness and interpretability of our framework through comprehensive experiments on real-world datasets.
Deep learning acceleration of iterative model-based light fluence correction for photoacoustic tomography
Photoacoustic tomography (PAT) is a promising imaging technique that can visualize the distribution of chromophores within biological tissue.
Hi-ResNet: Edge Detail Enhancement for High-Resolution Remote Sensing Segmentation
In this work, we solve the above-mentioned problems by proposing a High-resolution remote sensing network (Hi-ResNet) with efficient network structure designs, which consists of a funnel module, a multi-branch module with stacks of information aggregation (IA) blocks, and a feature refinement module, sequentially, and Class-agnostic Edge Aware (CEA) loss.
Ranked #13 on
Semantic Segmentation
on LoveDA
CISum: Learning Cross-modality Interaction to Enhance Multimodal Semantic Coverage for Multimodal Summarization
Then, the visual description and text content are fused to generate the textual summary to capture the semantics of the multimodal content, and the most relevant image is selected as the visual summary.
Boosting Single Image Super-Resolution via Partial Channel Shifting
Specifically, it is inspired by the temporal shifting in video understanding and displaces part of the channels along the spatial dimensions, thus allowing the effective receptive field to be amplified and the feature diversity to be augmented at almost zero cost.
Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization
In this paper, we propose a hierarchical cross-modality semantic correlation learning model (HCSCL) to learn the intra- and inter-modal correlation existing in the multimodal data.
Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training
The recent trend of using large-scale deep neural networks (DNN) to boost performance has propelled the development of the parallel pipelining technique for efficient DNN training, which has resulted in the development of several prominent pipelines such as GPipe, PipeDream, and PipeDream-2BW.
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain.
K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining
Though pre-trained language models such as Bert and XLNet, have rapidly advanced the state-of-the-art on many NLP tasks, they implicit semantics only relying on surface information between words in corpus.
