no code implementations • 8 Mar 2024 • Zichong Meng, Jie Zhang, Changdi Yang, Zheng Zhan, Pu Zhao, Yanzhi Wang
On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data.
no code implementations • 8 Mar 2024 • Zichong Meng, Changdi Yang, Jun Liu, Hao Tang, Pu Zhao, Yanzhi Wang
In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction.
no code implementations • 27 Feb 2024 • Kaikai An, Fangkai Yang, Liqun Li, Zhixing Ren, Hao Huang, Lu Wang, Pu Zhao, Yu Kang, Hua Ding, QIngwei Lin, Saravan Rajmohan, Qi Zhang
Effective incident management is pivotal for the smooth operation of enterprises-level cloud services.
1 code implementation • 16 Feb 2024 • Xuan Shen, Zhenglun Kong, Changdi Yang, Zhaoyang Han, Lei Lu, Peiyan Dong, Cheng Lyu, Chih-hsiang Li, Xuehang Guo, Zhihao Shu, Wei Niu, Miriam Leeser, Pu Zhao, Yanzhi Wang
In this paper, we propose EdgeQAT, the Entropy and Distribution Guided QAT for the optimization of lightweight LLMs to achieve inference acceleration on Edge devices.
no code implementations • 30 Jan 2024 • Chenan Wang, Pu Zhao, Siyue Wang, Xue Lin
Deep Neural Network (DNN) models when implemented on executing devices as the inference engines are susceptible to Fault Injection Attacks (FIAs) that manipulate model parameters to disrupt inference execution with disastrous performance.
no code implementations • 13 Jan 2024 • Lu Wang, Chao Du, Pu Zhao, Chuan Luo, Zhangchi Zhu, Bo Qiao, Wei zhang, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
To correct the negative sampling bias, we propose a novel contrastive learning method named Positive-Unlabeled Contrastive Learning (PUCL).
no code implementations • 8 Jan 2024 • Haozhe Li, Minghua Ma, Yudong Liu, Pu Zhao, Lingling Zheng, Ze Li, Yingnong Dang, Murali Chintalapati, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang
Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.
1 code implementation • 29 Nov 2023 • Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang
TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.
no code implementations • 24 Oct 2023 • Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, QIngwei Lin, Kam-Fai Wong
Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards.
1 code implementation • 18 Aug 2023 • Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, JianGuang Lou, Chongyang Tao, Xiubo Geng, QIngwei Lin, Shifeng Chen, Dongmei Zhang
Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model.
Ranked #50 on Arithmetic Reasoning on GSM8K (using extra training data)
no code implementations • 3 Aug 2023 • Fangkai Yang, Wenjie Yin, Lu Wang, Tianci Li, Pu Zhao, Bo Liu, Paul Wang, Bo Qiao, Yudong Liu, Mårten Björkman, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang
However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance.
1 code implementation • 1 Aug 2023 • Zhangchi Zhu, Lu Wang, Pu Zhao, Chao Du, Wei zhang, Hang Dong, Bo Qiao, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang
To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first.
2 code implementations • 14 Jun 2023 • Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, QIngwei Lin, Daxin Jiang
Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+.
Ranked #3 on Code Generation on CodeContests (Test Set pass@1 metric)
1 code implementation • 19 May 2023 • Fangkai Yang, Pu Zhao, Zezhong Wang, Lu Wang, Jue Zhang, Mohit Garg, QIngwei Lin, Saravan Rajmohan, Dongmei Zhang
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge.
no code implementations • 19 May 2023 • Liting Chen, Lu Wang, Hang Dong, Yali Du, Jie Yan, Fangkai Yang, Shuang Li, Pu Zhao, Si Qin, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.
1 code implementation • 8 May 2023 • Ziyang Luo, Can Xu, Pu Zhao, Xiubo Geng, Chongyang Tao, Jing Ma, QIngwei Lin, Daxin Jiang
We demonstrate that our PKG framework can enhance the performance of "black-box" LLMs on a range of domain knowledge-intensive tasks that require factual (+7. 9%), tabular (+11. 9%), medical (+3. 0%), and multimodal (+8. 1%) knowledge.
4 code implementations • 24 Apr 2023 • Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Daxin Jiang
In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans.
no code implementations • 23 Feb 2023 • Yize Li, Pu Zhao, Xue Lin, Bhavya Kailkhura, Ryan Goldhahn
Deep neural networks (DNNs) are sensitive to adversarial examples, resulting in fragile and unreliable performance in the real world.
1 code implementation • 6 Feb 2023 • Ziyang Luo, Pu Zhao, Can Xu, Xiubo Geng, Tao Shen, Chongyang Tao, Jing Ma, Qingwen Lin, Daxin Jiang
The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios.
1 code implementation • ICCV 2023 • Ziyang Luo, Pu Zhao, Can Xu, Xiubo Geng, Tao Shen, Chongyang Tao, Jing Ma, QIngwei Lin, Daxin Jiang
To address this issue, we propose a novel sparse retrieval paradigm for ITR that exploits sparse representations in the vocabulary space for images and texts.
no code implementations • CVPR 2023 • Changdi Yang, Pu Zhao, Yanyu Li, Wei Niu, Jiexiong Guan, Hao Tang, Minghai Qin, Bin Ren, Xue Lin, Yanzhi Wang
With the ever-increasing popularity of edge devices, it is necessary to implement real-time segmentation on the edge for autonomous driving and many other applications.
no code implementations • 9 Dec 2022 • Yifan Gong, Zheng Zhan, Pu Zhao, Yushu Wu, Chao Wu, Caiwen Ding, Weiwen Jiang, Minghai Qin, Yanzhi Wang
By re-configuring the model to the corresponding pruning ratio for a specific execution frequency (and voltage), we are able to achieve stable inference speed, i. e., keeping the difference in speed performance under various execution frequencies as small as possible.
1 code implementation • 10 Nov 2022 • Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, QIngwei Lin
First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x.
Ranked #2 on Multimodal Intent Recognition on MMDialog
1 code implementation • 8 Oct 2022 • Yihua Zhang, Yuguang Yao, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, Sijia Liu
To reduce the computation overhead, various efficient 'one-shot' pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP.
no code implementations • 26 Sep 2022 • Hao Cheng, Pu Zhao, Yize Li, Xue Lin, James Diffenderfer, Ryan Goldhahn, Bhavya Kailkhura
Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full precision neural networks.
1 code implementation • 25 Jul 2022 • Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, Yanzhi Wang
Instead of measuring the speed on mobile devices at each iteration during the search process, a speed model incorporated with compiler optimizations is leveraged to predict the inference latency of the SR block with various width configurations for faster convergence.
1 code implementation • 2 Jun 2022 • Yanyu Li, Pu Zhao, Geng Yuan, Xue Lin, Yanzhi Wang, Xin Chen
By combining the structural reparameterization and PaS, we successfully searched out a new family of VGG-like and lightweight networks, which enable the flexibility of arbitrary width with respect to each layer instead of each stage.
no code implementations • 22 Nov 2021 • Yifan Gong, Geng Yuan, Zheng Zhan, Wei Niu, Zhengang Li, Pu Zhao, Yuxuan Cai, Sijia Liu, Bin Ren, Xue Lin, Xulong Tang, Yanzhi Wang
Weight pruning is an effective model compression technique to tackle the challenges of achieving real-time deep neural network (DNN) inference on mobile devices.
no code implementations • ICCV 2021 • Zheng Zhan, Yifan Gong, Pu Zhao, Geng Yuan, Wei Niu, Yushu Wu, Tianyun Zhang, Malith Jayaweera, David Kaeli, Bin Ren, Xue Lin, Yanzhi Wang
Though recent years have witnessed remarkable progress in single image super-resolution (SISR) tasks with the prosperous development of deep neural networks (DNNs), the deep learning methods are confronted with the computation and memory consumption issues in practice, especially for resource-limited platforms such as mobile devices.
no code implementations • 28 Jun 2021 • Pu Zhao, Wei Niu, Geng Yuan, Yuxuan Cai, Bin Ren, Yanzhi Wang, Xue Lin
Object detection plays an important role in self-driving cars for security development.
no code implementations • 30 May 2021 • Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang
In this paper, we propose a compression-compilation co-design framework that can guarantee the identified model to meet both resource and real-time specifications of mobile devices.
no code implementations • 14 May 2021 • Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin
This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-transferability to unassociated models.
no code implementations • 26 Dec 2020 • Pu Zhao, Wei Niu, Geng Yuan, Yuxuan Cai, Hsin-Hsuan Sung, Sijia Liu, Xipeng Shen, Bin Ren, Yanzhi Wang, Xue Lin
3D object detection is an important task, especially in the autonomous driving application domain.
no code implementations • CVPR 2021 • Zhengang Li, Geng Yuan, Wei Niu, Pu Zhao, Yanyu Li, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu, Kaiyuan Yang, Bin Ren, Yanzhi Wang, Xue Lin
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce unnecessary computation and increase the execution speed.
no code implementations • 29 Sep 2020 • Pu Zhao, Parikshit Ram, Songtao Lu, Yuguang Yao, Djallel Bouneffouf, Xue Lin, Sijia Liu
The resulting scheme for meta-learning a UAP generator (i) has better performance (50% higher ASR) than baselines such as Projected Gradient Descent, (ii) has better performance (37% faster) than the vanilla L2O and MAML frameworks (when applicable), and (iii) is able to simultaneously handle UAP generation for different victim models and image data sources.
no code implementations • 15 Sep 2020 • Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang
Our framework can guarantee the identified model to meet both resource and real-time specifications of mobile devices, thus achieving real-time execution of large transformer-based models like BERT variants.
3 code implementations • ICLR 2020 • Pu Zhao, Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, Xue Lin
In this work, we propose to employ mode connectivity in loss landscapes to study the adversarial robustness of deep neural networks, and provide novel methods for improving this robustness.
no code implementations • 22 Apr 2020 • Wei Niu, Pu Zhao, Zheng Zhan, Xue Lin, Yanzhi Wang, Bin Ren
High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications.
no code implementations • 26 Feb 2020 • Kaidi Xu, Sijia Liu, Pin-Yu Chen, Pu Zhao, Xue Lin
Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks.
1 code implementation • 18 Feb 2020 • Pu Zhao, Pin-Yu Chen, Siyue Wang, Xue Lin
Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability.
no code implementations • 23 Jan 2020 • Xiaolong Ma, Zhengang Li, Yifan Gong, Tianyun Zhang, Wei Niu, Zheng Zhan, Pu Zhao, Jian Tang, Xue Lin, Bin Ren, Yanzhi Wang
Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem.
1 code implementation • ICCV 2019 • Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations.
no code implementations • 28 May 2019 • Pu Zhao, Siyue Wang, Cheng Gongye, Yanzhi Wang, Yunsi Fei, Xue Lin
Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability. We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters.
no code implementations • 3 Apr 2019 • Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun, Pu Zhao, Quanfu Fan, Chuang Gan, Xue Lin
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers.
no code implementations • 13 Sep 2018 • Siyue Wang, Xiao Wang, Pu Zhao, Wujie Wen, David Kaeli, Peter Chin, Xue Lin
Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples. We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout.
1 code implementation • ICLR 2019 • Kaidi Xu, Sijia Liu, Pu Zhao, Pin-Yu Chen, huan zhang, Quanfu Fan, Deniz Erdogmus, Yanzhi Wang, Xue Lin
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example.
no code implementations • 9 Apr 2018 • Pu Zhao, Sijia Liu, Yanzhi Wang, Xue Lin
In the literature, the added distortions are usually measured by L0, L1, L2, and L infinity norms, namely, L0, L1, L2, and L infinity attacks, respectively.