Search Results for author:
Found 38 papers, 7 papers with code
ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers
As large language models (LLMs) grow in size, traditional full fine-tuning becomes increasingly impractical due to its high computational and storage costs.
Vision Mamba Distillation for Low-resolution Fine-grained Image Classification
Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the super-resolution techniques and knowledge distillation methods.
Paying more attention to local contrast: improving infrared small target detection performance via prior knowledge
To effectively guide the model to focus on targets' spatial features, this paper proposes the Local Contrast Attention Enhanced infrared small target detection Network (LCAE-Net), combining prior knowledge with data-driven deep learning methods.
Graph-Augmented Relation Extraction Model with LLMs-Generated Support Document
This study introduces a novel approach to sentence-level relation extraction (RE) that integrates Graph Neural Networks (GNNs) with Large Language Models (LLMs) to generate contextually enriched support documents.
Aggressive Post-Training Compression on Extremely Large Language Models
The increasing size and complexity of Large Language Models (LLMs) pose challenges for their deployment on personal computers and mobile devices.
Robust Real-time Segmentation of Bio-Morphological Features in Human Cherenkov Imaging during Radiotherapy via Deep Learning
To address the challenge of limited annotation of these features in Cherenkov images, a transfer learning strategy was applied.
Cherenkov Imaged Bio-morphological Features Verify Patient Positioning with Deformable Tissue Translocation in Breast Radiotherapy
This approach quantified positioning variations in two parts: a global shift from rigid registration and a two-dimensional variation map of loco-regional deformation from non-rigid registration.
Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networks
Experimental results on Cifar100 and ImageNet datasets exhibit that \methodname~provides up to a \textbf{50. 00\%} reduction in training time and attains up to a \textbf{6. 94\%} enhancement in accuracy when contrasted with baseline methods across diverse models and tasks.
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts.
Local Conditional Controlling for Text-to-Image Diffusion Models
It focuses on controlling specific local region according to user-defined image conditions, while the remaining regions are only conditioned by the original text prompt.
AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions
Computers calculate transcendental functions by approximating them through the composition of a few limited-precision instructions.
Towards Automatic Scoring of Spinal X-ray for Ankylosing Spondylitis
In this study, we address this challenge by prototyping a 2-step auto-grading pipeline, called VertXGradeNet, to automatically predict mSASSS scores for the cervical and lumbar vertebral units (VUs) in X-ray spinal imaging.
Federated Learning for Metaverse: A Survey
In this paper, we review some of the early advances of FL4M, which will be a research direction with unlimited development potential.
VertXNet: An Ensemble Method for Vertebrae Segmentation and Identification of Spinal X-Ray
Our experimental results have shown that the proposed pipeline outperformed two SOTA segmentation models on our test dataset (MEASURE 1) with a mean Dice of 0. 90, vs. a mean Dice of 0. 73 for Mask R-CNN and 0. 72 for U-Net.
Federated Learning Attacks and Defenses: A Survey
For the purpose of advancing the research in this field, building a robust FL system, and realizing the wide application of FL, this paper sorts out the possible attacks and corresponding defenses of the current FL system systematically.
Contrast Pattern Mining: A Survey
Contrast pattern mining (CPM) is an important and popular subfield of data mining.
Fluorescence molecular optomic signatures improve identification of tumors in head and neck specimens
In this study, a radiomics approach was extended to optical fluorescence molecular imaging data for tissue classification, termed 'optomics'.
HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation
In this study, we propose HiKonv, a unified solution that maximizes the throughput of convolution on a given underlying processing unit with low-bitwidth quantized data inputs through novel bit-wise management and parallel computation.
VertXNet: Automatic Segmentation and Identification of Lumbar and Cervical Vertebrae from Spinal X-ray Images
Manual annotation of vertebrae on spinal X-ray imaging is costly and time-consuming due to bone shape complexity and image quality variations.
Compilation and Optimizations for Efficient Machine Learning on Embedded Systems
Deep Neural Networks (DNNs) have achieved great success in a variety of machine learning (ML) applications, delivering high-quality inferencing solutions in computer vision, natural language processing, and virtual reality, etc.
HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs.
YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency.
Inferential Wasserstein Generative Adversarial Networks
The Wasserstein GAN (WGAN) leverages the Wasserstein distance to avoid the caveats in the minmax two-player training of GANs but has other defects such as mode collapse and lack of metric to detect the convergence.
Free Lunch for Co-Saliency Detection: Context Adjustment
We hope that the scale, diversity, and quality of our dataset can benefit researchers in this area and beyond.
WinoCNN: Kernel Sharing Winograd Systolic Array for Efficient Convolutional Neural Network Acceleration on FPGAs
We implement our proposed accelerator on multiple FPGAs, which outperforms the state-of-the-art designs in terms of both throughput and DSP efficiency.
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration
This paper emphasizes the importance and efficacy of training, quantization and accelerator design, and calls for more research breakthroughs in the area for AI on the edge.
MöbiusE: Knowledge Graph Embedding on Möbius Ring
In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called M\"{o}biusE, in which the entities and relations are embedded to the surface of a M\"{o}bius ring.
Effective Algorithm-Accelerator Co-design for AI Solutions on Edge Devices
High quality AI solutions require joint optimization of AI algorithms, such as deep neural networks (DNNs), and their hardware accelerators.
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization
Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs.
EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions
We formulate the co-search problem by fusing DNN search variables and hardware implementation variables into one solution space, and maximize both algorithm accuracy and hardware implementation quality.
TAG : Type Auxiliary Guiding for Code Comment Generation
Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e. g., operator, string, etc.
GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization
Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems.
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks.
NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving
The rapidly growing demands for powerful AI algorithms in many application domains have motivated massive investment in both high-quality deep neural network (DNN) models and high-efficiency implementations.
iWGAN: an Autoencoder WGAN for Inference
We further provide a rigorous probabilistic interpretation of our model under the framework of maximum likelihood estimation.
A Bi-Directional Co-Design Approach to Enable Deep Learning on IoT Devices
Developing deep learning models for resource-constrained Internet-of-Things (IoT) devices is challenging, as it is difficult to achieve both good quality of results (QoR), such as DNN model inference accuracy, and quality of service (QoS), such as inference latency, throughput, and power consumption.
Data Poisoning Attack against Unsupervised Node Embedding Methods
In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods.
Local Region Sparse Learning for Image-on-Scalar Regression
Identification of regions of interest (ROI) associated with certain disease has a great impact on public health.
