no code implementations • 26 Mar 2024 • Wei Tao, Yucheng Zhou, Wenqiang Zhang, Yu Cheng
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.
1 code implementation • 28 Feb 2024 • Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Wenyi Wang, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Zongze Xu, Chenglin Wu
Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness.
no code implementations • 24 Jan 2024 • Wei Tao, Shenglin He, Kai Lu, Xiaoyang Qu, Guokuan Li, Jiguang Wan, Jianzong Wang, Jing Xiao
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.
1 code implementation • 16 Jan 2024 • Wei Tao, Yucheng Zhou, Yanlin Wang, Hongyu Zhang, Haofen Wang, Wenqiang Zhang
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.
no code implementations • 27 Jan 2023 • Wei Tao, Lei Bao, Sheng Long, Gaowei Wu, Qing Tao
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.
no code implementations • 8 Aug 2022 • Xin Liu, Wei Tao, Jun Wang, Zhisong Pan
Due to the simplicity and efficiency of the first-order gradient method, it has been widely used in training neural networks.
1 code implementation • 26 May 2022 • Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Chendong Zhao, Wei Tao, Jing Xiao
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.
no code implementations • 18 Apr 2022 • Xin Liu, Wei Tao, Zhisong Pan
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.
2 code implementations • 5 Mar 2022 • Ensheng Shi, Yanlin Wang, Wei Tao, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Hongbin Sun
Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.
1 code implementation • 12 Jul 2021 • Wei Tao, Yanlin Wang, Ensheng Shi, Lun Du, Shi Han, Hongyu Zhang, Dongmei Zhang, Wenqiang Zhang
We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods.
no code implementations • 5 Jul 2021 • Xin Liu, Zhisong Pan, Wei Tao
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.
no code implementations • 29 Apr 2021 • Tse-Wei Chen, Motoki Yoshinaga, Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Kinya Osa, Masami Kato
"Lightweight convolutional neural networks" is an important research topic in the field of embedded vision.
Ranked #1 on Face Detection on FDDB (Accuracy metric)
no code implementations • 29 Apr 2021 • Tse-Wei Chen, Wei Tao, Deyu Wang, Dongchao Wen, Kinya Osa, Masami Kato
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
no code implementations • 29 Apr 2021 • Tse-Wei Chen, Deyu Wang, Wei Tao, Dongchao Wen, Lingxiao Yin, Tadayuki Ito, Kinya Osa, Masami Kato
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
no code implementations • ICLR 2021 • Wei Tao, Sheng Long, Gaowei Wu, Qing Tao
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.
no code implementations • 29 Dec 2020 • Wei Tao, Wei Li, Zhisong Pan, Qing Tao
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.
no code implementations • 29 Sep 2020 • Junjie Liu, Dongchao Wen, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
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.
no code implementations • 10 Sep 2020 • Junjie Liu, Dongchao Wen, Deyu Wang, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
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
no code implementations • 19 Nov 2019 • Hongxing Gao, Wei Tao, Dongchao Wen, Tse-Wei Chen, Kinya Osa, Masami Kato
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
no code implementations • 13 Nov 2019 • Hongxing Gao, Wei Tao, Dongchao Wen, Junjie Liu, Tse-Wei Chen, Kinya Osa, Masami Kato
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)
no code implementations • 13 Nov 2019 • Junjie Liu, Dongchao Wen, Hongxing Gao, Wei Tao, Tse-Wei Chen, Kinya Osa, Masami Kato
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)