Search Results for author: Yi Liu

Found 168 papers, 57 papers with code

PP-StructureV2: A Stronger Document Analysis System

1 code implementation11 Oct 2022 Chenxia Li, Ruoyu Guo, Jun Zhou, Mengtao An, Yuning Du, Lingfeng Zhu, Yi Liu, Xiaoguang Hu, dianhai yu

For Table Recognition model, we utilize PP-LCNet, CSP-PAN and SLAHead to optimize the backbone module, feature fusion module and decoding module, respectively, which improved the table structure accuracy by 6\% with comparable inference speed.

 Ranked #1 on Network Pruning on CIFAR-100 (Inference Time (ms) metric)

Key Information Extraction Knowledge Distillation +3

PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector

2 code implementations4 Nov 2022 Xinxin Wang, Guanzhong Wang, Qingqing Dang, Yi Liu, Xiaoguang Hu, dianhai yu

With multi-scale training and testing, PP-YOLOE-R-l and PP-YOLOE-R-x further improve the detection precision to 80. 02 and 80. 73 mAP.

Object object-detection +3

DETRs Beat YOLOs on Real-time Object Detection

4 code implementations17 Apr 2023 Wenyu Lv, Yian Zhao, Shangliang Xu, Jinman Wei, Guanzhong Wang, Cheng Cui, Yuning Du, Qingqing Dang, Yi Liu

In this paper, we first analyze the influence of NMS in modern real-time object detectors on inference speed, and establish an end-to-end speed benchmark.

Object object-detection +1

PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation

1 code implementation15 Jan 2021 Yi Liu, Lutao Chu, Guowei Chen, Zewu Wu, Zeyu Chen, Baohua Lai, Yuying Hao

The toolkit aims to help both developers and researchers in the whole process of designing segmentation models, training models, optimizing performance and inference speed, and deploying models.

Autonomous Driving Human Part Segmentation +5

PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset

1 code implementation14 Dec 2021 Lutao Chu, Yi Liu, Zewu Wu, Shiyu Tang, Guowei Chen, Yuying Hao, Juncai Peng, Zhiliang Yu, Zeyu Chen, Baohua Lai, Haoyi Xiong

This work is the first to construct a large-scale video portrait dataset that contains 291 videos from 23 conference scenes with 14K fine-labeled frames and extensions to multi-camera teleconferencing.

Portrait Segmentation Segmentation +1

Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models

2 code implementations4 Jul 2022 Xuhong LI, Haoyi Xiong, Yi Liu, Dingfu Zhou, Zeyu Chen, Yaqing Wang, Dejing Dou

Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.

Classification Image Classification +3

EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle

1 code implementation17 Oct 2022 Yuying Hao, Yi Liu, Yizhou Chen, Lin Han, Juncai Peng, Shiyu Tang, Guowei Chen, Zewu Wu, Zeyu Chen, Baohua Lai

In recent years, the rapid development of deep learning has brought great advancements to image and video segmentation methods based on neural networks.

Image Segmentation Interactive Segmentation +4

PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices

1 code implementation11 Apr 2023 Shiyu Tang, Ting Sun, Juncai Peng, Guowei Chen, Yuying Hao, Manhui Lin, Zhihong Xiao, Jiangbin You, Yi Liu

To address this issue, we propose PP-MobileSeg, a semantic segmentation model that achieves state-of-the-art performance on mobile devices.

Semantic Segmentation valid

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

1 code implementation28 Nov 2023 Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, LiMin Wang, Yu Qiao

With the rapid development of Multi-modal Large Language Models (MLLMs), a number of diagnostic benchmarks have recently emerged to evaluate the comprehension capabilities of these models.

Fairness Multiple-choice +8

Spherical Message Passing for 3D Graph Networks

1 code implementation ICLR 2022 Yi Liu, Limei Wang, Meng Liu, Xuan Zhang, Bora Oztekin, Shuiwang Ji

Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning.

Drug Discovery Representation Learning

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

1 code implementation23 Mar 2021 Meng Liu, Youzhi Luo, Limei Wang, Yaochen Xie, Hao Yuan, Shurui Gui, Haiyang Yu, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan, Haoran Liu, Cong Fu, Bora Oztekin, Xuan Zhang, Shuiwang Ji

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning.

Benchmarking Graph Generation +1

ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

1 code implementation17 Jun 2022 Limei Wang, Yi Liu, Yuchao Lin, Haoran Liu, Shuiwang Ji

To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood.

Drug Discovery

Learning Hierarchical Protein Representations via Complete 3D Graph Networks

1 code implementation26 Jul 2022 Limei Wang, Haoran Liu, Yi Liu, Jerry Kurtin, Shuiwang Ji

In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations.

Representation Learning

InternVideo: General Video Foundation Models via Generative and Discriminative Learning

1 code implementation6 Dec 2022 Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang, LiMin Wang, Yu Qiao

Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications.

 Ranked #1 on Action Recognition on Something-Something V1 (using extra training data)

Action Classification Contrastive Learning +8

Periodic Graph Transformers for Crystal Material Property Prediction

2 code implementations23 Sep 2022 Keqiang Yan, Yi Liu, Yuchao Lin, Shuiwang Ji

Our Matformer is designed to be invariant to periodicity and can capture repeating patterns explicitly.

Band Gap Formation Energy +2

Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction

1 code implementation12 Jun 2023 Yuchao Lin, Keqiang Yan, Youzhi Luo, Yi Liu, Xiaoning Qian, Shuiwang Ji

This is enabled by our approximations of infinite potential summations, where we extend the Ewald summation for several potential series approximations with provable error bounds.

Band Gap Formation Energy +2

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

3 code implementations12 Oct 2022 Zeyu Qin, Yanbo Fan, Yi Liu, Li Shen, Yong Zhang, Jue Wang, Baoyuan Wu

Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability.

Adversarial Attack

CAMixerSR: Only Details Need More "Attention"

1 code implementation29 Feb 2024 Yan Wang, Yi Liu, Shijie Zhao, Junlin Li, Li Zhang

To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining.

Super-Resolution

The Deep Learning Compiler: A Comprehensive Survey

1 code implementation6 Feb 2020 Mingzhen Li, Yi Liu, Xiaoyan Liu, Qingxiao Sun, Xin You, Hailong Yang, Zhongzhi Luan, Lin Gan, Guangwen Yang, Depei Qian

In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations.

Lightweight Image Super-Resolution with Superpixel Token Interaction

1 code implementation ICCV 2023 Aiping Zhang, Wenqi Ren, Yi Liu, Xiaochun Cao

Our method employs superpixels to cluster local similar pixels to form the explicable local regions and utilizes intra-superpixel attention to enable local information interaction.

Image Super-Resolution Superpixels

How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View

1 code implementation24 Sep 2021 Ren Li, Yanan Cao, Qiannan Zhu, Guanqun Bi, Fang Fang, Yi Liu, Qian Li

However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate.

Knowledge Graph Completion Knowledge Graph Embedding +1

Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection

1 code implementation CVPR 2023 Luting Wang, Yi Liu, Penghui Du, Zihan Ding, Yue Liao, Qiaosong Qi, Biaolong Chen, Si Liu

When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects.

Object Open Vocabulary Object Detection

TempCompass: Do Video LLMs Really Understand Videos?

1 code implementation1 Mar 2024 Yuanxin Liu, Shicheng Li, Yi Liu, Yuxiang Wang, Shuhuai Ren, Lei LI, Sishuo Chen, Xu sun, Lu Hou

Motivated by these two problems, we propose the \textbf{TempCompass} benchmark, which introduces a diversity of temporal aspects and task formats.

MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction

1 code implementation21 Oct 2022 Wangjie Jiang, Zhihao Ye, Zijing Ou, Ruihui Zhao, Jianguang Zheng, Yi Liu, Siheng Li, Bang Liu, Yujiu Yang, Yefeng Zheng

In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples.

Optical Character Recognition Optical Character Recognition (OCR) +1

Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach

1 code implementation19 Mar 2020 Yi Liu, James J. Q. Yu, Jiawen Kang, Dusit Niyato, Shuyu Zhang

Through extensive case studies on a real-world dataset, it is shown that FedGRU's prediction accuracy is 90. 96% higher than the advanced deep learning models, which confirm that FedGRU can achieve accurate and timely traffic prediction without compromising the privacy and security of raw data.

Clustering Federated Learning +2

Image Processing and Quality Control for Abdominal Magnetic Resonance Imaging in the UK Biobank

2 code implementations2 Jul 2020 Nicolas Basty, Yi Liu, Madeleine Cule, E. Louise Thomas, Jimmy D. Bell, Brandon Whitcher

An end-to-end image analysis pipeline is presented for the abdominal MRI protocol used in the UK Biobank on the first 38, 971 participants.

DeepGate2: Functionality-Aware Circuit Representation Learning

1 code implementation25 May 2023 Zhengyuan Shi, Hongyang Pan, Sadaf Khan, Min Li, Yi Liu, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, Zhufei Chu, Qiang Xu

Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks.

Representation Learning

Employing Deep Part-Object Relationships for Salient Object Detection

1 code implementation ICCV 2019 Yi Liu, Qiang Zhang, Dingwen Zhang, Jungong Han

In the second step, we feed the primary capsules into two identical streams, within each of which low-level capsules (parts) will be assigned to their familiar high-level capsules (object) via a locally connected routing.

Object object-detection +2

Benchmarking Large Language Models on Controllable Generation under Diversified Instructions

1 code implementation1 Jan 2024 Yihan Chen, Benfeng Xu, Quan Wang, Yi Liu, Zhendong Mao

While large language models (LLMs) have exhibited impressive instruction-following capabilities, it is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions.

Benchmarking Instruction Following +1

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

1 code implementation21 May 2023 Yi Liu, Xiaohan Bi, Lei LI, Sishuo Chen, Wenkai Yang, Xu sun

However, as pre-trained language models (PLMs) continue to increase in size, the communication cost for transmitting parameters during synchronization has become a training speed bottleneck.

Clustering Federated Learning +2

An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

1 code implementation11 Jul 2022 Kunran Xu, Huawei Zhang, Yishi Li, Yuhao Zhang, Rui Lai, Yi Liu

Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic.

object-detection Object Detection

PR-NN: RNN-based Detection for Coded Partial-Response Channels

2 code implementations30 Jul 2020 Simeng Zheng, Yi Liu, Paul H. Siegel

In this paper, we investigate the use of recurrent neural network (RNN)-based detection of magnetic recording channels with inter-symbol interference (ISI).

Semi-Offline Reinforcement Learning for Optimized Text Generation

1 code implementation16 Jun 2023 Changyu Chen, Xiting Wang, Yiqiao Jin, Victor Ye Dong, Li Dong, Jie Cao, Yi Liu, Rui Yan

In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline.

Offline RL reinforcement-learning +2

Incorporating Pre-trained Model Prompting in Multimodal Stock Volume Movement Prediction

1 code implementation11 Sep 2023 Ruibo Chen, Zhiyuan Zhang, Yi Liu, Ruihan Bao, Keiko Harimoto, Xu sun

Existing multimodal works that train models from scratch face the problem of lacking universal knowledge when modeling financial news.

Time Series

Towards Better Entity Linking with Multi-View Enhanced Distillation

1 code implementation27 May 2023 Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Denvy Deng, Qi Zhang

Aiming at learning entity representations that can match divergent mentions, this paper proposes a Multi-View Enhanced Distillation (MVD) framework, which can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders.

Entity Linking Knowledge Distillation +1

Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation

1 code implementation24 Oct 2023 Jiaang Li, Quan Wang, Yi Liu, Licheng Zhang, Zhendong Mao

We analyze this phenomenon and reveal that entity codes, the quantization outcomes for expressing entities, have higher entropy at the code level and Jaccard distance at the codeword level under random entity quantization.

Knowledge Graphs Quantization +1

A Small and Fast BERT for Chinese Medical Punctuation Restoration

1 code implementation24 Aug 2023 Tongtao Ling, Chen Liao, Zhipeng Yu, Lei Chen, Shilei Huang, Yi Liu

In clinical dictation, utterances after automatic speech recognition (ASR) without explicit punctuation marks may lead to the misunderstanding of dictated reports.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Activation functions are not needed: the ratio net

1 code implementation14 May 2020 Chi-Chun Zhou, Hai-Long Tu, Yue-Jie Hou, Zhen Ling, Yi Liu, Jian Hua

We compare the effectiveness and efficiency of the ratio net and that of the RBF and the MLP with various kinds of activation functions in the classification task on the mnist database of handwritten digits and the Internet Movie Database (IMDb) which is a binary sentiment analysis dataset.

General Classification Sentiment Analysis

Large-Scale Analysis of Iliopsoas Muscle Volumes in the UK Biobank

1 code implementation12 Aug 2020 Julie Fitzpatrick, Nicolas Basty, Madeleine Cule, Yi Liu, Jimmy D. Bell, E. Louise Thomas, Brandon Whitcher

We also found that iliopsoas volume was significantly related to height, BMI and age, and that there was an acceleration in muscle volume decrease in men with age.

Assessing the Effects of Hyperparameters on Knowledge Graph Embedding Quality

1 code implementation1 Jul 2022 Oliver Lloyd, Yi Liu, Tom Gaunt

We regressed the embedding quality on those hyperparameter configurations, using this model to generate Sobol sensitivity indices for each of the hyperparameters.

Knowledge Graph Embedding Knowledge Graphs +2

Multi-Modal Coreference Resolution with the Correlation between Space Structures

no code implementations21 Apr 2018 Qibin Zheng, Xingchun Diao, Jianjun Cao, Xiaolei Zhou, Yi Liu, Hongmei Li

In this paper, we bring a extrinsic correlation between the space structures of each modalities in coreference resolution.

coreference-resolution

Hierarchical compositional feature learning

no code implementations7 Nov 2016 Miguel Lázaro-Gredilla, Yi Liu, D. Scott Phoenix, Dileep George

We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images.

Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification

no code implementations14 Jul 2017 Yi Liu, Liang He, Yao Tian, Zhuzi Chen, Jia Liu, Michael T. Johnson

Additionally, we also find that even though bottleneck features perform well for text-independent speaker verification, they do not outperform MFCCs on the most challenging Imposter-Correct trials on RedDots.

Speaker Identification Speaker Recognition +2

Teaching Compositionality to CNNs

no code implementations CVPR 2017 Austin Stone, Huayan Wang, Michael Stark, Yi Liu, D. Scott Phoenix, Dileep George

Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions.

Object Recognition

Sparse Representation based Multi-sensor Image Fusion: A Review

no code implementations12 Feb 2017 Qiang Zhang, Yi Liu, Rick S. Blum, Jungong Han, DaCheng Tao

As a result of several successful applications in computer vision and image processing, sparse representation (SR) has attracted significant attention in multi-sensor image fusion.

Dictionary Learning Infrared And Visible Image Fusion

A backward pass through a CNN using a generative model of its activations

no code implementations8 Nov 2016 Huayan Wang, Anna Chen, Yi Liu, Dileep George, D. Scott Phoenix

Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space.

Object

An Efficient Bandit Algorithm for Realtime Multivariate Optimization

no code implementations22 Oct 2018 Daniel N. Hill, Houssam Nassif, Yi Liu, Anand Iyer, S. V. N. Vishwanathan

We further apply our algorithm to optimize a message that promotes adoption of an Amazon service.

DSNet: Deep and Shallow Feature Learning for Efficient Visual Tracking

no code implementations6 Nov 2018 Qiangqiang Wu, Yan Yan, Yanjie Liang, Yi Liu, Hanzi Wang

In recent years, Discriminative Correlation Filter (DCF) based tracking methods have achieved great success in visual tracking.

Image Classification Visual Tracking

Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models

no code implementations24 Nov 2018 Xinzhi Wang, Shengcheng Yuan, HUI ZHANG, Yi Liu

By contrast, in objective news bodies and titles, it is easy to regard text as caused love (gd).

Multi-glance Reading Model for Text Understanding

no code implementations WS 2018 Pengcheng Zhu, Yujiu Yang, Wenqiang Gao, Yi Liu

Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM).

Document Classification Machine Translation +2

Normalization Gradients are Least-squares Residuals

no code implementations ICLR 2019 Yi Liu

Batch Normalization (BN) and its variants have seen widespread adoption in the deep learning community because they improve the training of deep neural networks.

Formula of Volume of Revolution with Integration by Parts and Extension

no code implementations4 Sep 2016 Yi Liu, Jingwei Liu

A calculation formula of volume of revolution with integration by parts of definite integral is derived based on monotone function, and extended to a general case that curved trapezoids is determined by continuous, piecewise strictly monotone and differential function.

MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks

no code implementations15 Jun 2019 Qi Xuan, Fuxian Li, Yi Liu, Yun Xiang

Experimental results on ModelNet10 and ModelNet40 datasets show that our MV-C3D technique can achieve outstanding performance with multi-view images which are captured from partial angles with less range.

3D Object Recognition

Global Pixel Transformers for Virtual Staining of Microscopy Images

no code implementations1 Jul 2019 Yi Liu, Hao Yuan, Zhengyang Wang, Shuiwang Ji

It is also shown that our proposed global pixel transformer layer is useful to improve the fluorescence image prediction results.

Open DNN Box by Power Side-Channel Attack

no code implementations21 Jul 2019 Yun Xiang, Zhuangzhi Chen, Zuohui Chen, Zebin Fang, Haiyang Hao, Jinyin Chen, Yi Liu, Zhefu Wu, Qi Xuan, Xiaoniu Yang

However, recent studies indicate that they are also vulnerable to adversarial attacks.

Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model

no code implementations17 Sep 2019 Yi Liu, Chao Pang, Zongqian Zhan, Xiaomeng Zhang, Xue Yang

In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and irregular boundaries.

Building change detection for remote sensing images Change Detection +3

PPGAN: Privacy-preserving Generative Adversarial Network

no code implementations4 Oct 2019 Yi Liu, Jialiang Peng, James J. Q. Yu, Yi Wu

To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure.

Generative Adversarial Network Privacy Preserving

THUEE system description for NIST 2019 SRE CTS Challenge

no code implementations25 Dec 2019 Yi Liu, Tianyu Liang, Can Xu, Xianwei Zhang, Xianhong Chen, Wei-Qiang Zhang, Liang He, Dandan song, Ruyun Li, Yangcheng Wu, Peng Ouyang, Shouyi Yin

This paper describes the systems submitted by the department of electronic engineering, institute of microelectronics of Tsinghua university and TsingMicro Co. Ltd. (THUEE) to the NIST 2019 speaker recognition evaluation CTS challenge.

Speaker Recognition

MulGAN: Facial Attribute Editing by Exemplar

no code implementations28 Dec 2019 Jingtao Guo, Zhenzhen Qian, Zuowei Zhou, Yi Liu

These methods encode attribute-related information in images into the predefined region of the latent feature space by employing a pair of images with opposite attributes as input to train model, the face attribute transfer between the input image and the exemplar can be achieved by exchanging their attribute-related latent feature region.

Attribute

A Secure Federated Learning Framework for 5G Networks

no code implementations12 May 2020 Yi Liu, Jialiang Peng, Jiawen Kang, Abdullah M. Iliyasu, Dusit Niyato, Ahmed A. Abd El-Latif

In this article, we propose a blockchain-based secure FL framework to create smart contracts and prevent malicious or unreliable participants from involving in FL.

Federated Learning

Exemplar-based Generative Facial Editing

no code implementations31 May 2020 Jingtao Guo, Yi Liu, Zhenzhen Qian, Zuowei Zhou

Image synthesis has witnessed substantial progress due to the increasing power of generative model.

Attribute Facial Editing +1

Federated Learning for 6G Communications: Challenges, Methods, and Future Directions

no code implementations4 Jun 2020 Yi Liu, Xingliang Yuan, Zehui Xiong, Jiawen Kang, Xiaofei Wang, Dusit Niyato

As the 5G communication networks are being widely deployed worldwide, both industry and academia have started to move beyond 5G and explore 6G communications.

Federated Learning

Variable Selection via Thompson Sampling

no code implementations1 Jul 2020 Yi Liu, Veronika Rockova

Thompson sampling is a heuristic algorithm for the multi-armed bandit problem which has a long tradition in machine learning.

BIG-bench Machine Learning Interpretable Machine Learning +3

Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

no code implementations19 Jul 2020 Yi Liu, Sahil Garg, Jiangtian Nie, Yang Zhang, Zehui Xiong, Jiawen Kang, M. Shamim Hossain

Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-\textit{k} selection to improve communication efficiency.

Anomaly Detection Federated Learning +2

Deep Learning of High-Order Interactions for Protein Interface Prediction

no code implementations18 Jul 2020 Yi Liu, Hao Yuan, Lei Cai, Shuiwang Ji

However, these methods do not incorporate the important sequential information from amino acid chains and the high-order pairwise interactions.

Protein Interface Prediction Vocal Bursts Intensity Prediction

Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms

no code implementations23 Jul 2020 Yi Liu, Jiangtian Nie, Xuandi Li, Syed Hassan Ahmed, Wei Yang Bryan Lim, Chunyan Miao

To this end, this paper proposes a new federated learning-based aerial-ground air quality sensing framework for fine-grained 3D air quality monitoring and forecasting.

Federated Learning

Topology-Aware Graph Pooling Networks

no code implementations19 Oct 2020 Hongyang Gao, Yi Liu, Shuiwang Ji

In addition, graph topology is incorporated in global voting to compute the importance score of each node globally in the entire graph.

Graph Classification

Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework

no code implementations10 Aug 2020 Jiawen Kang, Zehui Xiong, Chunxiao Jiang, Yi Liu, Song Guo, Yang Zhang, Dusit Niyato, Cyril Leung, Chunyan Miao

This framework can achieve scalable and flexible decentralized FEL by individually manage local model updates or model sharing records for performance isolation.

Cryptography and Security

Assessing the Impact of COVID-19 on the Objective and Analysis of Oncology Clinical Trials -- Application of the Estimand Framework

no code implementations8 Jun 2020 Evgeny Degtyarev, Kaspar Rufibach, Yue Shentu, Godwin Yung, Michelle Casey, Stefan Englert, Feng Liu, Yi Liu, Oliver Sailer, Jonathan Siegel, Steven Sun, Rui Tang, Jiangxiu Zhou

We identify key intercurrent events that may occur due to COVID-19 in oncology clinical trials with a focus on time-to-event endpoints and discuss considerations pertaining to the other estimand attributes introduced in the ICH E9 addendum.

valid

A Systematic Literature Review on Federated Learning: From A Model Quality Perspective

no code implementations1 Dec 2020 Yi Liu, Li Zhang, Ning Ge, Guanghao Li

In this process, the server uses an incentive mechanism to encourage clients to contribute high-quality and large-volume data to improve the global model.

Federated Learning

Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses

no code implementations8 Dec 2020 Yi Liu, Xingliang Yuan, Ruihui Zhao, Cong Wang, Dusit Niyato, Yefeng Zheng

Extensive case studies have shown that our attacks are effective on different datasets and common semi-supervised learning methods.

Federated Learning Quantization

Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

no code implementations8 Dec 2020 Yi Liu, Ruihui Zhao, Jiawen Kang, Abdulsalam Yassine, Dusit Niyato, Jialiang Peng

Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes.

Edge-computing

CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy

no code implementations12 Jan 2021 Yi Liu, Shuiwang Ji

The effectiveness of our methods is evaluated on both online and offline tasks.

Social Media, Content Moderation, and Technology

no code implementations12 Jan 2021 Yi Liu, Pinar Yildirim, Z. John Zhang

This means that platforms under different revenue models can have different incentives to improve their content moderation technology.

Marketing

A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis

no code implementations14 Jan 2021 Yi Liu, Shuiwang Ji

The method is then integrated to the last stage of the proposed transfer learning framework to reuse the complex patterns learned from the same CT images.

Computed Tomography (CT) COVID-19 Diagnosis +3

The ADENUIM Telescope- A new beam telescope for the DESY II Test Beam Facility

no code implementations22 Feb 2021 Yi Liu, Yao Teng, Chenfei Yang, Changqing Feng, Ingrid-Maria Gregor, Lennart Huth, Marcel Stanitzki

The coincident signal of all scintillators is used as trigger and then used as a trigger and distributed to the entire system, including all the telescope planes and any devices under test from test beam users.

Instrumentation and Detectors Instrumentation and Methods for Astrophysics High Energy Physics - Experiment

Machine Learning Regression based Single Event Transient Modeling Method for Circuit-Level Simulation

no code implementations22 May 2021 Changqing Xu, Yi Liu, XinFang Liao, JiaLiang Cheng, YinTang Yang

A multilayer feedfordward neural network is used to build the SET pulse current model by learning the data from TCAD simulation.

BIG-bench Machine Learning regression

Efficiently Solving High-Order and Nonlinear ODEs with Rational Fraction Polynomial: the Ratio Net

no code implementations18 May 2021 Chenxin Qin, Ruhao Liu, Maocai Li, Shengyuan Li, Yi Liu, ChiChun Zhou

The ratio net holds promise for advancing the efficiency and effectiveness of solving differential equations.

Optical Mouse: 3D Mouse Pose From Single-View Video

no code implementations17 Jun 2021 Bo Hu, Bryan Seybold, Shan Yang, David Ross, Avneesh Sud, Graham Ruby, Yi Liu

We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos.

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

no code implementations CVPR 2021 Yi Liu, Xiaoyang Huo, Tianyi Chen, Xiangping Zeng, Si Wu, Zhiwen Yu, Hau-San Wong

Semi-supervised generative learning (SSGL) makes use of unlabeled data to achieve a trade-off between the data collection/annotation effort and generation performance, when adequate labeled data are not available.

Generative Adversarial Network Image Generation

A Map of Bandits for E-commerce

no code implementations1 Jul 2021 Yi Liu, Lihong Li

The rich body of Bandit literature not only offers a diverse toolbox of algorithms, but also makes it hard for a practitioner to find the right solution to solve the problem at hand.

Navigate

EGC2: Enhanced Graph Classification with Easy Graph Compression

1 code implementation16 Jul 2021 Jinyin Chen, Haiyang Xiong, Haibin Zhenga, Dunjie Zhang, Jian Zhang, Mingwei Jia, Yi Liu

To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness.

Graph Classification

BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver

no code implementations31 Jul 2021 Wei W. Xing, Xiang Jin, Yi Liu, Dan Niu, Weishen Zhao, Zhou Jin

One of the greatest challenges in IC design is the repeated executions of computationally expensive SPICE simulations, particularly when highly complex chip testing/verification is involved.

Bayesian Optimization Variational Inference

BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models

no code implementations EMNLP (sustainlp) 2021 Yi Liu, Guoan Zhang, Puning Yu, Jianlin Su, Shengfeng Pan

Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework.

TAG

Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation

no code implementations ICCV 2021 Tianyi Chen, Yi Liu, Yunfei Zhang, Si Wu, Yong Xu, Feng Liangbing, Hau San Wong

To ensure disentanglement among the variables, we maximize mutual information between the class-independent variable and synthesized images, map real images to the latent space of a generator to perform consistency regularization of cross-class attributes, and incorporate class semantic-based regularization into a discriminator's feature space.

Disentanglement Image Generation

Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction

no code implementations8 Oct 2021 Jinyin Chen, Haiyang Xiong, Haibin Zheng, Jian Zhang, Guodong Jiang, Yi Liu

Backdoor attacks induce the DLP methods to make wrong prediction by the malicious training data, i. e., generating a subgraph sequence as the trigger and embedding it to the training data.

Backdoor Attack Dynamic Link Prediction +1

Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations

no code implementations29 Sep 2021 Ke Sun, Yi Liu, Yingnan Zhao, Hengshuai Yao, Shangling Jui, Linglong Kong

In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.

Distributional Reinforcement Learning reinforcement-learning +1

Gaussian Differential Privacy Transformation: from identification to application

no code implementations29 Sep 2021 Yi Liu, Ke Sun, Bei Jiang, Linglong Kong

Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of individuals from machine learning models.

Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm

no code implementations29 Sep 2021 Ke Sun, Yingnan Zhao, Yi Liu, Enze Shi, Yafei Wang, Aref Sadeghi, Xiaodong Yan, Bei Jiang, Linglong Kong

Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation.

Atari Games Distributional Reinforcement Learning +2

Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis

no code implementations14 Oct 2021 Yi Liu, Yuanshao Zhu, James J. Q. Yu

Similarly, due to the heterogeneity of the connected remote devices, FEEL faces the challenge of heterogeneous data and non-IID (Independent and Identically Distributed) data.

Binary Classification Ensemble Learning +1

Locally Adaptive Structure and Texture Similarity for Image Quality Assessment

no code implementations16 Oct 2021 Keyan Ding, Yi Liu, Xueyi Zou, Shiqi Wang, Kede Ma

The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations.

Image Quality Assessment Image Super-Resolution +1

Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization

no code implementations NeurIPS 2021 Ke Sun, Yafei Wang, Yi Liu, Yingnan Zhao, Bo Pan, Shangling Jui, Bei Jiang, Linglong Kong

Anderson mixing has been heuristically applied to reinforcement learning (RL) algorithms for accelerating convergence and improving the sampling efficiency of deep RL.

reinforcement-learning Reinforcement Learning (RL)

Direct Training via Backpropagation for Ultra-low Latency Spiking Neural Networks with Multi-threshold

no code implementations25 Nov 2021 Changqing Xu, Yi Liu, YinTang Yang

In our proposed training method, we proposed three approximated derivative for spike activity to solve the problem of the non-differentiable issue which cause difficulties for direct training SNNs based on BP.

FamilySeer: Towards Optimized Tensor Codes by Exploiting Computation Subgraph Similarity

no code implementations1 Jan 2022 Shanjun Zhang, Mingzhen Li, Hailong Yang, Yi Liu, Zhongzhi Luan, Depei Qian

Currently, the DL compilers partition the input DL models into several subgraphs and leverage the auto-tuning to find the optimal tensor codes of these subgraphs.

Evolutionary Action Selection for Gradient-based Policy Learning

no code implementations12 Jan 2022 Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation. The evolutionary part in these hybrid methods maintains a population of policy networks. However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA. In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel hybrid method of EA and DRL. In EAS, we focus on optimizing the action chosen by the policy network and attempt to obtain high-quality actions to promote policy learning through an evolutionary algorithm.

Continuous Control Evolutionary Algorithms

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

no code implementations4 Feb 2022 Yifeng Zheng, Shangqi Lai, Yi Liu, Xingliang Yuan, Xun Yi, Cong Wang

In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation.

Federated Learning

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

no code implementations14 Mar 2022 Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li

Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.

Federated Learning Machine Unlearning

Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block

no code implementations18 Mar 2022 Changqing Xu, Yi Liu, YinTang Yang

We evaluate the proposed method for event streams classification tasks on neuromorphic N-MNIST, CIFAR10-DVS, DVS128 gesture datasets.

Classification

Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images

no code implementations2 Apr 2022 Siyang Wen, Wei Guo, Yi Liu, Ruijie Wu

The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions.

Object object-detection +1

Improved-Flow Warp Module for Remote Sensing Semantic Segmentation

no code implementations9 May 2022 Yinjie Zhang, Yi Liu, Wei Guo

Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation.

Segmentation Semantic Segmentation

Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning

no code implementations23 May 2022 Lei Zhang, Yu Pan, Yi Liu, Qibin Zheng, Zhisong Pan

In order to improve the defense ability of defender, a game model based on reward randomization reinforcement learning is proposed.

reinforcement-learning Reinforcement Learning (RL)

Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding

no code implementations21 Jun 2022 Junwen Pan, Guanlin Chen, Yi Liu, Jiexiang Wang, Cheng Bian, Pengfei Zhu, Zhicheng Zhang

Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images.

Question Answering Visual Grounding +1

Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator

no code implementations31 Jul 2022 Changqing Xu, Yijian Pei, Zili Wu, Yi Liu, YinTang Yang

Spiking neural network (SNN) is a brain-inspired model which has more spatio-temporal information processing capacity and computational energy efficiency.

Quantization

DeepGen: Diverse Search Ad Generation and Real-Time Customization

no code implementations6 Aug 2022 Konstantin Golobokov, Junyi Chai, Victor Ye Dong, Mandy Gu, Bingyu Chi, Jie Cao, Yulan Yan, Yi Liu

In addition, our system creates a customized ad in real-time in response to the user's search query, therefore highlighting different aspects of the same product based on what the user is looking for.

Text Generation

SATformer: Transformer-Based UNSAT Core Learning

no code implementations2 Sep 2022 Zhengyuan Shi, Min Li, Yi Liu, Sadaf Khan, Junhua Huang, Hui-Ling Zhen, Mingxuan Yuan, Qiang Xu

This paper introduces SATformer, a novel Transformer-based approach for the Boolean Satisfiability (SAT) problem.

Multi-Task Learning

A Nonparametric Contextual Bandit with Arm-level Eligibility Control for Customer Service Routing

no code implementations8 Sep 2022 Ruofeng Wen, Wenjun Zeng, Yi Liu

Routing contacts to eligible SMEs turns out to be a non-trivial problem because SMEs' domain eligibility is subject to training quality and can change over time.

Thompson Sampling

FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training

no code implementations6 Oct 2022 Junyi Chai, Reid Pryzant, Victor Ye Dong, Konstantin Golobokov, Chenguang Zhu, Yi Liu

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length.

Attribute Causal Inference +2

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction

no code implementations COLING 2022 Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu

Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text.

Document-level Event Extraction Event Extraction

VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection

no code implementations20 Oct 2022 Yi Liu, Xuan Zhang, Ying Li, Guixin Liang, Yabing Jiang, Lixia Qiu, Haiping Tang, Fei Xie, Wei Yao, Yi Dai, Yu Qiao, Yali Wang

For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.

Temporal Defect Localization Video Defect Classification

Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning

no code implementations14 Nov 2022 Yi Liu, Song Guo, Jie Zhang, Qihua Zhou, Yingchun Wang, Xiaohan Zhao

We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.

Feature Correlation Federated Learning +4

CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming

no code implementations15 Nov 2022 Qihua Zhou, Ruibin Li, Song Guo, Peiran Dong, Yi Liu, Jingcai Guo, Zhenda Xu

Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth.

Denoising Super-Resolution

Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning

no code implementations7 Dec 2022 Yingchun Wang, Song Guo, Jingcai Guo, Weizhan Zhang, Yida Xu, Jie Zhang, Yi Liu

Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.

Network Pruning Variational Inference

SIRL: Similarity-based Implicit Representation Learning

no code implementations2 Jan 2023 Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan

This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not.

Contrastive Learning Data Augmentation +1

Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models

no code implementations11 Jan 2023 Yi Liu, Gaurav Datta, Ellen Novoseller, Daniel S. Brown

In particular, we provide evidence that a learned dynamics model offers the following benefits when performing PbRL: (1) preference elicitation and policy optimization require significantly fewer environment interactions than model-free PbRL, (2) diverse preference queries can be synthesized safely and efficiently as a byproduct of standard model-based RL, and (3) reward pre-training based on suboptimal demonstrations can be performed without any environmental interaction.

reinforcement-learning Reinforcement Learning (RL)

Knowledge Enhancement for Contrastive Multi-Behavior Recommendation

no code implementations13 Jan 2023 Hongrui Xuan, Yi Liu, Bohan Li, Hongzhi Yin

In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items.

Contrastive Learning Recommendation Systems +1

Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks

no code implementations24 Feb 2023 Yuxuan Zhang, Qingzhong Wang, Jiang Bian, Yi Liu, Yanwu Xu, Dejing Dou, Haoyi Xiong

Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?

Classification Data Augmentation +3

Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencent

no code implementations6 Mar 2023 Xiaonan Nie, Yi Liu, Fangcheng Fu, Jinbao Xue, Dian Jiao, Xupeng Miao, Yangyu Tao, Bin Cui

Recent years have witnessed the unprecedented achievements of large-scale pre-trained models, especially the Transformer models.

Management Scheduling

AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions

no code implementations5 May 2023 Jiaming Guo, Xueyi Zou, Yuyi Chen, Yi Liu, Jia Hao, Jianzhuang Liu, Youliang Yan

In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR.

Super-Resolution

SegGPT Meets Co-Saliency Scene

no code implementations8 May 2023 Yi Liu, Shoukun Xu, Dingwen Zhang, Jungong Han

Co-salient object detection targets at detecting co-existed salient objects among a group of images.

Co-Salient Object Detection Object +2

SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization

no code implementations19 May 2023 Yingchun Wang, Jingcai Guo, Yi Liu, Song Guo, Weizhan Zhang, Xiangyong Cao, Qinghua Zheng

Based on the idea that in-distribution (ID) data with spurious features may have a lower experience risk, in this paper, we propose a novel Spurious Feature-targeted model Pruning framework, dubbed SFP, to automatically explore invariant substructures without referring to the above drawbacks.

Out-of-Distribution Generalization

Automatic Code Summarization via ChatGPT: How Far Are We?

no code implementations22 May 2023 Weisong Sun, Chunrong Fang, Yudu You, Yun Miao, Yi Liu, Yuekang Li, Gelei Deng, Shenghan Huang, Yuchen Chen, Quanjun Zhang, Hanwei Qian, Yang Liu, Zhenyu Chen

To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for a given code snippet.

Code Summarization

Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

no code implementations23 May 2023 Yi Liu, Gelei Deng, Zhengzi Xu, Yuekang Li, Yaowen Zheng, Ying Zhang, Lida Zhao, Tianwei Zhang, Kailong Wang, Yang Liu

Our study investigates three key research questions: (1) the number of different prompt types that can jailbreak LLMs, (2) the effectiveness of jailbreak prompts in circumventing LLM constraints, and (3) the resilience of ChatGPT against these jailbreak prompts.

Prompt Engineering

Prompt Injection attack against LLM-integrated Applications

no code implementations8 Jun 2023 Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, ZiHao Wang, XiaoFeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Yang Liu

We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection.

SLSSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion

no code implementations14 Jul 2023 Changqing Xu, Yi Liu, YinTang Yang

Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest due to their low power features, high biological plausibility, and strong spatiotemporal information processing capability.

Self-Supervised Dynamic Hypergraph Recommendation based on Hyper-Relational Knowledge Graph

no code implementations15 Aug 2023 Yi Liu, Hongrui Xuan, Bohan Li, Meng Wang, Tong Chen, Hongzhi Yin

However, the long-tail distribution of entities leads to sparsity in supervision signals, which weakens the quality of item representation when utilizing KG enhancement.

Collaborative Filtering Knowledge-Aware Recommendation +2

Distribution-Aware Continual Test Time Adaptation for Semantic Segmentation

no code implementations24 Sep 2023 Jiayi Ni, Senqiao Yang, Jiaming Liu, Xiaoqi Li, Wenyu Jiao, ran Xu, Zehui Chen, Yi Liu, Shanghang Zhang

In this paper, we propose a distribution-aware tuning (DAT) method to make the semantic segmentation CTTA efficient and practical in real-world applications.

Autonomous Driving Semantic Segmentation +1

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts

no code implementations3 Oct 2023 Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong LI, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou

In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.

Continual Learning Representation Learning +1

RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge

no code implementations14 Nov 2023 Yi Liu, Lianzhe Huang, Shicheng Li, Sishuo Chen, Hao Zhou, Fandong Meng, Jie zhou, Xu sun

Therefore, to evaluate the ability of LLMs to discern the reliability of external knowledge, we create a benchmark from existing knowledge bases.

counterfactual Knowledge Graphs +2

Gaussian Differential Privacy on Riemannian Manifolds

1 code implementation NeurIPS 2023 Yangdi Jiang, Xiaotian Chang, Yi Liu, Lei Ding, Linglong Kong, Bei Jiang

We develop an advanced approach for extending Gaussian Differential Privacy (GDP) to general Riemannian manifolds.

MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding

no code implementations8 Dec 2023 Hongjie Zhang, Yi Liu, Lu Dong, Yifei HUANG, Zhen-Hua Ling, Yali Wang, LiMin Wang, Yu Qiao

While several long-form VideoQA datasets have been introduced, the length of both videos used to curate questions and sub-clips of clues leveraged to answer those questions have not yet reached the criteria for genuine long-form video understanding.

Question Answering Video Question Answering +1

Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning

no code implementations1 Jan 2024 Kaibin Tian, Yanhua Cheng, Yi Liu, Xinglin Hou, Quan Chen, Han Li

To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase.

Representation Learning Retrieval +3

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training

no code implementations1 Jan 2024 Haodong Li, Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu, Guoai Xu, Guosheng Xu, Haoyu Wang

In this paper, we introduce a detailed framework designed to detect and assess the presence of content from potentially copyrighted books within the training datasets of LLMs.

Language Modelling Large Language Model +1

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

no code implementations30 Jan 2024 Jie Li, Yi Liu, Chongyang Liu, Ling Shi, Xiaoning Ren, Yaowen Zheng, Yang Liu, Yinxing Xue

To address this research gap, we conducted an extensive empirical study on Multilingual Jailbreak attacks.

Text Generation

Generative AI to Generate Test Data Generators

no code implementations31 Jan 2024 Benoit Baudry, Khashayar Etemadi, Sen Fang, Yogya Gamage, Yi Liu, Yuxin Liu, Martin Monperrus, Javier Ron, André Silva, Deepika Tiwari

The results show that LLMs can successfully generate realistic test data generators in a wide range of domains at all three levels of integrability.

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

no code implementations14 Feb 2024 Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

With the development of LLMs, the security threats of LLMs are getting more and more attention.

LLM Jailbreak Attack versus Defense Techniques -- A Comprehensive Study

no code implementations21 Feb 2024 Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, Stjepan Picek

Large Language Models (LLMS) have increasingly become central to generating content with potential societal impacts.

Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing

no code implementations22 Feb 2024 Hao Li, Mengqi Huang, Lei Zhang, Bo Hu, Yi Liu, Zhendong Mao

GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes.

Attribute

Neural Field Classifiers via Target Encoding and Classification Loss

no code implementations2 Mar 2024 Xindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun

We successfully propose a novel Neural Field Classifier (NFC) framework which formulates existing neural field methods as classification tasks rather than regression tasks.

Classification Multi-Label Classification +2

Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis

no code implementations8 Mar 2024 Muxi Chen, Yi Liu, Jian Yi, Changran Xu, Qiuxia Lai, Hongliang Wang, Tsung-Yi Ho, Qiang Xu

In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis.

Defect Detection Fairness +1

Cannot find the paper you are looking for? You can Submit a new open access paper.