Search Results for author:
Found 21 papers, 5 papers with code
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
Motivated by the empirical findings, we propose a novel LLM-based Multi-Agent framework for GitHub Issue reSolution, MAGIS, consisting of four kinds of agents customized for the software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents.
Data Interpreter: An LLM Agent For Data Science
Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness.
Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
In addition, for patches without outlier values, we utilize value-driven quantization search (VDQS) on the feature maps of their following dataflow branches to reduce search time.
KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation
However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i. e., good-practice commits), while the rest do not.
Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks
However, for solving this induced optimization problem, the state-of-the-art gradient-based methods such as FGSM, I-FGSM and MI-FGSM look different from their original methods especially in updating the direction, which makes it difficult to understand them and then leaves some theoretical issues to be addressed in viewpoint of optimization.
A high-resolution dynamical view on momentum methods for over-parameterized neural networks
Due to the simplicity and efficiency of the first-order gradient method, it has been widely used in training neural networks.
QSpeech: Low-Qubit Quantum Speech Application Toolkit
However, Quantum Neural Network (QNN) running on low-qubit quantum devices would be difficult since it is based on Variational Quantum Circuit (VQC), which requires many qubits.
A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks
To the best of our knowledge, this is the first theoretical guarantee for the convergence of NAG to the global minimum in training deep neural networks.
RACE: Retrieval-Augmented Commit Message Generation
Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.
On the Evaluation of Commit Message Generation Models: An Experimental Study
We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods.
Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks
Despite the fact that the objective function is non-convex and non-smooth, we show that NAG converges to a global minimum at a non-asymptotic linear rate $(1-\Theta(1/\sqrt{\kappa}))^t$, where $\kappa > 1$ is the condition number of a gram matrix and $t$ is the number of the iterations.
Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps
"Lightweight convolutional neural networks" is an important research topic in the field of embedded vision.
Ranked #1 on
Face Detection
on FDDB
(Accuracy metric)
Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions
In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essential building blocks for embedded-computer-vision algorithms.
Ranked #1 on
Face Detection
on WIDER FACE
CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications
In this paper, we propose a network module, Cascaded and Separable Structure of Dilated (CASSOD) Convolution, and a special hardware system to handle the CASSOD networks efficiently.
Ranked #1 on
Face Detection
on ADE20K
The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods
In this paper, we fill this theory-practice gap by investigating the convergence of the last iterate (referred to as individual convergence), which is a more difficult task than convergence analysis of the averaged solution.
Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization
In order to remove this factor, we first develop gradient descent averaging (GDA), which is a general projection-based dual averaging algorithm in the strongly convex setting.
BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
In this paper, we provide an explicit convex optimization example where training the BNNs with the traditionally adaptive optimization methods still faces the risk of non-convergence, and identify that constraining the range of gradients is critical for optimizing the deep binary model to avoid highly suboptimal solutions.
QuantNet: Learning to Quantize by Learning within Fully Differentiable Framework
Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks.
Ranked #927 on
Image Classification
on ImageNet
IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded Vision
Furthermore, based on YOLOv2, we design IFQ-Tinier-YOLO face detector which is a fixed-point network with 256x reduction in model size (246k Bytes) than Tiny-YOLO.
Ranked #10 on
Face Detection
on FDDB
DupNet: Towards Very Tiny Quantized CNN with Improved Accuracy for Face Detection
Firstly, we employ weights with duplicated channels for the weight-intensive layers to reduce the model size.
Ranked #1 on
Face Detection
on WIDER Face
(GFLOPs metric)
Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation
Despite the recent works on knowledge distillation (KD) have achieved a further improvement through elaborately modeling the decision boundary as the posterior knowledge, their performance is still dependent on the hypothesis that the target network has a powerful capacity (representation ability).
Ranked #182 on
Image Classification
on CIFAR-10
(using extra training data)
