no code implementations • 10 Jun 2025 • Mingyuan Fan, Fuyi Wang, Cen Chen, Jianying Zhou
Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data.
1 code implementation • 21 May 2025 • Zhiwen Li, Die Chen, Mingyuan Fan, Cen Chen, Yaliang Li, Yanhao Wang, Wenmeng Zhou
In this paper, we propose a novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region.
no code implementations • 21 May 2025 • Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li
Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential.
no code implementations • 30 Apr 2025 • Guanghao Zhou, Panjia Qiu, Cen Chen, Jie Wang, Zheming Yang, Jian Xu, Minghui Qiu
The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area.
1 code implementation • 7 Mar 2025 • Run He, Di Fang, Yicheng Xu, Yawen Cui, Ming Li, Cen Chen, Ziqian Zeng, Huiping Zhuang
Specifically, the embeddings of old tasks shift in the embedding space after learning new tasks, and the classifier becomes biased towards new tasks due to training solely with new data, hindering the balance between old and new knowledge.
no code implementations • 23 Feb 2025 • Jianwei Wang, Junyao Yang, Haoran Li, Huiping Zhuang, Cen Chen, Ziqian Zeng
The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data.
1 code implementation • 18 Feb 2025 • Weikai Lu, Hao Peng, Huiping Zhuang, Cen Chen, Ziqian Zeng
Multimodal Large Language Models (MLLMs) have serious security vulnerabilities. While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to construct these datasets.
no code implementations • 18 Feb 2025 • Die Chen, Zhiwen Li, Cen Chen, Xiaodan Li, Jinyan Ye
At the tool level, we perform a detailed toxicity analysis of NSFW datasets and compare the performance of different NSFW classifiers, offering deeper insights into their performance alongside a compilation of comprehensive evaluation metrics.
no code implementations • 17 Feb 2025 • Guanghao Zhou, Panjia Qiu, Mingyuan Fan, Cen Chen, Mingyuan Chu, Xin Zhang, Jun Zhou
We define jailbreak attacks as an optimization problem within the embedding space of masked language models.
no code implementations • 22 Jan 2025 • Mingyuan Fan, Zhanyi Hu, Fuyi Wang, Cen Chen
Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL).
1 code implementation • 16 Jan 2025 • Dongyu Liu, Xuhong Wang, Cen Chen, Yanhao Wang, Shengyue Yao, Yilun Lin
In recent years, there has been an increasing interest in image anonymization, particularly focusing on the de-identification of faces and individuals.
1 code implementation • 17 Dec 2024 • Zhongjie Duan, Qianyi Zhao, Cen Chen, Daoyuan Chen, Wenmeng Zhou, Yaliang Li, Yingda Chen
This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost.
1 code implementation • 24 Sep 2024 • Wei Huang, Yinggui Wang, Cen Chen
In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs).
no code implementations • 28 Aug 2024 • Qianyi Zhao, Chen Qu, Cen Chen, Mingyuan Fan, Yanhao Wang
Specifically, FedMCP adds two lightweight adapter modules, i. e., the global adapter and the private adapter, to the frozen PLMs within clients.
2 code implementations • 19 Aug 2024 • Di Fang, Yinan Zhu, Runze Fang, Cen Chen, Ziqian Zeng, Huiping Zhuang
To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i. e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning.
no code implementations • 2 Aug 2024 • Die Chen, Zhiwen Li, Mingyuan Fan, Cen Chen, Wenmeng Zhou, Yaliang Li
Since image generation is conditioned on text, prompt purification serves as a straightforward solution for content safety.
no code implementations • 13 Jul 2024 • Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu
On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate.
1 code implementation • 20 Jun 2024 • Tao Zhang, Ziqian Zeng, Yuxiang Xiao, Huiping Zhuang, Cen Chen, James Foulds, SHimei Pan
Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories.
1 code implementation • 20 Jun 2024 • Zhongjie Duan, Wenmeng Zhou, Cen Chen, Yaliang Li, Weining Qian
To evaluate the efficacy of our proposed post-tuning approach, we conduct extension training on the Stable Video Diffusion model.
no code implementations • 12 Jun 2024 • Yiping Wang, Yanhao Wang, Cen Chen
The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent $w$ items are used for analysis.
no code implementations • 3 Jun 2024 • Ziqian Zeng, Jianwei Wang, Junyao Yang, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen
The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers.
1 code implementation • 28 May 2024 • Huiping Zhuang, Di Fang, Kai Tong, Yuchen Liu, Ziqian Zeng, Xu Zhou, Cen Chen
One of these scenarios can be formulated as an online continual learning (OCL) problem.
1 code implementation • 8 Apr 2024 • Weikai Lu, Ziqian Zeng, Jianwei Wang, Zhengdong Lu, Zelin Chen, Huiping Zhuang, Cen Chen
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content.
1 code implementation • 26 Mar 2024 • Huiping Zhuang, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Zhiping Lin
The compensation stream is governed by a Dual-Activation Compensation (DAC) module.
2 code implementations • 23 Mar 2024 • Huiping Zhuang, Yizhu Chen, Di Fang, Run He, Kai Tong, Hongxin Wei, Ziqian Zeng, Cen Chen
The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i. e., closed-form) solution to the GCIL scenario.
1 code implementation • 23 Mar 2024 • Huiping Zhuang, Yuchen Liu, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Yi Wang, Lap-Pui Chau
In this paper, we propose an exemplar-free approach--Forward-only Online Analytic Learning (F-OAL).
no code implementations • 20 Mar 2024 • Run He, Huiping Zhuang, Di Fang, Yizhu Chen, Kai Tong, Cen Chen
The DS-BPT pretrains model in streams of both supervised learning and self-supervised contrastive learning (SSCL) for base knowledge extraction.
no code implementations • 29 Jan 2024 • Zhongjie Duan, Chengyu Wang, Cen Chen, Weining Qian, Jun Huang
Toon shading is a type of non-photorealistic rendering task of animation.
1 code implementation • 19 Dec 2023 • Ziqian Zeng, Yihuai Hong, Hongliang Dai, Huiping Zhuang, Cen Chen
We propose ConsistentEE, an early exiting method that is consistent in training and inference.
1 code implementation • 15 Nov 2023 • Zhongjie Duan, Chengyu Wang, Cen Chen, Weining Qian, Jun Huang, Mingyi Jin
In the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches.
no code implementations • 12 Nov 2023 • Ruyao Xu, Taolin Zhang, Chengyu Wang, Zhongjie Duan, Cen Chen, Minghui Qiu, Dawei Cheng, Xiaofeng He, Weining Qian
In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.
1 code implementation • 10 Nov 2023 • Mingyuan Fan, Xiaodan Li, Cen Chen, Wenmeng Zhou, Yaliang Li
A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its variants.
no code implementations • 21 Sep 2023 • Zhenzhen Chu, Jiayu Chen, Cen Chen, Chengyu Wang, Ziheng Wu, Jun Huang, Weining Qian
Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks.
no code implementations • 11 Sep 2023 • Chengyu Wang, Zhongjie Duan, Bingyan Liu, Xinyi Zou, Cen Chen, Kui Jia, Jun Huang
Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.
no code implementations • 29 Aug 2023 • Jianing Wang, Chengyu Wang, Cen Chen, Ming Gao, Jun Huang, Aoying Zhou
We propose TransPrompt v2, a novel transferable prompting framework for few-shot learning across similar or distant text classification tasks.
no code implementations • 7 Aug 2023 • Zhongjie Duan, Lizhou You, Chengyu Wang, Cen Chen, Ziheng Wu, Weining Qian, Jun Huang
In recent years, diffusion models have emerged as the most powerful approach in image synthesis.
no code implementations • 31 Jul 2023 • Mingyuan Fan, Chengyu Wang, Cen Chen, Yang Liu, Jun Huang
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life.
no code implementations • 29 Jul 2023 • Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao
To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA.
1 code implementation • 29 Jul 2023 • Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao
The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts.
1 code implementation • ICCV 2023 • Lizhao Liu, Zhuangwei Zhuang, Shangxin Huang, Xunlong Xiao, Tianhang Xiang, Cen Chen, Jingdong Wang, Mingkui Tan
CMT disentangles the learning of supervised segmentation and unsupervised masked context prediction for effectively learning the very limited labeled points and mass unlabeled points, respectively.
no code implementations • 16 Jul 2023 • Mingyuan Fan, Cen Chen, Chengyu Wang, Wenmeng Zhou, Jun Huang
Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i. e., sever and clients only hold partial sub-networks and exchange intermediate computations).
1 code implementation • 24 May 2023 • Zhongjie Duan, Chengyu Wang, Cen Chen, Jun Huang, Weining Qian
In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers.
1 code implementation • 4 Apr 2023 • Tianchen Zhou, Zhanyi Hu, Bingzhe Wu, Cen Chen
Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks.
1 code implementation • 20 Dec 2022 • Forrest Sheng Bao, Ruixuan Tu, Ge Luo, Yinfei Yang, Hebi Li, Minghui Qiu, Youbiao He, Cen Chen
Automated summary quality assessment falls into two categories: reference-based and reference-free.
no code implementations • 5 Dec 2022 • Mingyuan Fan, Cen Chen, Chengyu Wang, Xiaodan Li, Wenmeng Zhou
Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks.
no code implementations • 13 Aug 2022 • Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu, Wenzhong Guo
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones.
1 code implementation • 13 Aug 2022 • Mingyuan Fan, Cen Chen, Wenmeng Zhou, Yinggui Wang
In this paper, we explore the transferability of adversarial examples via the lens of Bayesian approach.
1 code implementation • 27 May 2022 • Tingting Liu, Chengyu Wang, Cen Chen, Ming Gao, Aoying Zhou
With top-$k$ sparse attention, the most crucial attention relation can be obtained with a lower computational cost.
no code implementations • 20 Apr 2022 • Mingyuan Fan, Yang Liu, Cen Chen
Specifically, the intuition stems from the fact that a very limited part of informative samples can contribute to most of model performance.
no code implementations • 24 Jan 2022 • Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma
First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model.
no code implementations • 2 Nov 2021 • Jamie Cui, Cen Chen, Tiandi Ye, Li Wang
Existing work fails to provide a loss-less scheme, or has impractical efficiency.
no code implementations • 11 Jul 2021 • Kai Zheng, Cen Chen
In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge.
no code implementations • 24 Jun 2021 • Yuchen Li, Yifan Bao, Liyao Xiang, Junhan Liu, Cen Chen, Li Wang, Xinbing Wang
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
1 code implementation • 3 Mar 2021 • Chen Qu, Liu Yang, Cen Chen, W. Bruce Croft, Kalpesh Krishna, Mohit Iyyer
Our method is more flexible as it can handle both span answers and freeform answers.
1 code implementation • 22 Jan 2021 • Ziyuan Zhao, Zeng Zeng, Kaixin Xu, Cen Chen, Cuntai Guan
We use the proposed criteria to select samples for strong and weak labelers to produce oracle labels and pseudo labels simultaneously at each active learning iteration in an ensemble learning manner, which can be examined with IoMT Platform.
no code implementations • 17 Dec 2020 • Jun Zhou, Longfei Zheng, Chaochao Chen, Yan Wang, Xiaolin Zheng, Bingzhe Wu, Cen Chen, Li Wang, Jianwei Yin
In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.
no code implementations • 25 Nov 2020 • Haojie Pan, Cen Chen, Chengyu Wang, Minghui Qiu, Liu Yang, Feng Ji, Jun Huang
More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.
no code implementations • 23 Nov 2020 • Yilun Lin, Chaochao Chen, Cen Chen, Li Wang
Federated learning (FL) has attracted increasing attention in recent years.
2 code implementations • 18 Nov 2020 • Minghui Qiu, Peng Li, Chengyu Wang, Hanjie Pan, Ang Wang, Cen Chen, Xianyan Jia, Yaliang Li, Jun Huang, Deng Cai, Wei Lin
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
no code implementations • 14 Nov 2020 • Huiwen Wu, Cen Chen, Li Wang
In the era of big data, the need to expand the amount of data through data sharing to improve model performance has become increasingly compelling.
no code implementations • 24 Sep 2020 • Bin Zhang, Cen Chen, Li Wang
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models.
no code implementations • 4 Sep 2020 • Cen Chen, Bingzhe Wu, Minghui Qiu, Li Wang, Jun Zhou
To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue.
no code implementations • 29 May 2020 • Jianxi Yang, Likai Zhang, Cen Chen, Yangfan Li, Ren Li, Guiping Wang, Shixin Jiang, Zeng Zeng
Specifically, CNN is utilized to model the spatial relations and the short-term temporal dependencies among sensors, while the output features of CNN are fed into the GRU to learn the long-term temporal dependencies jointly.
1 code implementation • 22 May 2020 • Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer
We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
1 code implementation • NAACL 2022 • Forrest Sheng Bao, Hebi Li, Ge Luo, Minghui Qiu, Yinfei Yang, Youbiao He, Cen Chen
Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain.
no code implementations • 5 Mar 2020 • Cen Chen, Chen Liang, Jianbin Lin, Li Wang, Ziqi Liu, Xinxing Yang, Xiukun Wang, Jun Zhou, Yang Shuang, Yuan Qi
The insurance industry has been creating innovative products around the emerging online shopping activities.
1 code implementation • 3 Feb 2020 • Liu Yang, Minghui Qiu, Chen Qu, Cen Chen, Jiafeng Guo, Yongfeng Zhang, W. Bruce Croft, Haiqing Chen
We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.
no code implementations • 5 Oct 2019 • Bingzhe Wu, Chaochao Chen, Shiwan Zhao, Cen Chen, Yuan YAO, Guangyu Sun, Li Wang, Xiaolu Zhang, Jun Zhou
Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.
2 code implementations • 26 Aug 2019 • Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W. Bruce Croft, Mohit Iyyer
First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.
no code implementations • 18 Jun 2019 • Shaosheng Cao, Xinxing Yang, Cen Chen, Jun Zhou, Xiaolong Li, Yuan Qi
With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business.
no code implementations • 7 May 2019 • Xiaoman Zhang, Ziyuan Zhao, Cen Chen, Songyou Peng, Min Wu, Zhongyao Cheng, Singee Teo, Le Zhang, Zeng Zeng
In this study, we applied powerful deep neural network and explored a process in the forecast of skeletal bone age with the specifically combine joints images to increase the performance accuracy compared with the whole hand images.
1 code implementation • 12 Mar 2019 • Ziyuan Zhao, Xiaoman Zhang, Cen Chen, Wei Li, Songyou Peng, Jie Wang, Xulei Yang, Le Zhang, Zeng Zeng
Segmentation stands at the forefront of many high-level vision tasks.
no code implementations • 29 Aug 2018 • Cen Chen, Minghui Qiu, Yinfei Yang, Jun Zhou, Jun Huang, Xiaolong Li, Forrest Bao
Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.
no code implementations • NAACL 2018 • Cen Chen, Yinfei Yang, Jun Zhou, Xiaolong Li, Forrest Sheng Bao
With the growing amount of reviews in e-commerce websites, it is critical to assess the helpfulness of reviews and recommend them accordingly to consumers.
no code implementations • 26 May 2017 • Kingsley Kuan, Mathieu Ravaut, Gaurav Manek, Huiling Chen, Jie Lin, Babar Nazir, Cen Chen, Tse Chiang Howe, Zeng Zeng, Vijay Chandrasekhar
We present a deep learning framework for computer-aided lung cancer diagnosis.
no code implementations • EACL 2017 • Yinfei Yang, Cen Chen, Minghui Qiu, Forrest Bao
Recent work on aspect extraction is leveraging the hierarchical relationship between products and their categories.