1 code implementation • NAACL 2022 • Meihan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li
Event extraction aims to identify an event and then extract the arguments participating in the event.
1 code implementation • EMNLP (ClinicalNLP) 2020 • Yifan Peng, SungWon Lee, Daniel C. Elton, Thomas Shen, Yu-Xing Tang, Qingyu Chen, Shuai Wang, Yingying Zhu, Ronald Summers, Zhiyong Lu
We then introduce an end-to-end approach based on the combination of rules and transformer-based methods to detect these abdominal lymph node mentions and classify their types from the MRI radiology reports.
1 code implementation • 12 May 2025 • Zheng Yao, Shuai Wang, Guido Zuccon
Recent research has questioned the role of fine-tuning vs. that of pre-training within dense retrievers, specifically arguing that retrieval knowledge is primarily gained during pre-training, meaning knowledge not acquired during pre-training cannot be sub-sequentially acquired via fine-tuning.
no code implementations • 12 May 2025 • Shuai Wang, Harrisen Scells, Bevan Koopman, Guido Zuccon
Our results show that query effectiveness varies significantly across models and prompt designs, with guided query formulation benefiting from well-chosen seed studies.
no code implementations • 9 May 2025 • Shuai Wang, Ivona Najdenkoska, Hongyi Zhu, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition.
no code implementations • 1 May 2025 • Wei-Bin Kou, Guangxu Zhu, Bingyang Cheng, Shuai Wang, Ming Tang, Yik-Chung Wu
Street Scene Semantic Understanding (denoted as S3U) is a crucial but complex task for autonomous driving (AD) vehicles.
no code implementations • 30 Apr 2025 • Sangmin Woo, Kang Zhou, Yun Zhou, Shuai Wang, Sheng Guan, Haibo Ding, Lin Lee Cheong
Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability.
no code implementations • 25 Apr 2025 • Jiayi Chen, Shuai Wang, Guoliang Li, Wei Xu, Guangxu Zhu, Derrick Wing Kwan Ng, Chengzhong Xu
Existing solutions either rely on small models that struggle with generalization or large models that are resource-intensive.
no code implementations • 24 Apr 2025 • Qingyue Wang, Qi Pang, Xixun Lin, Shuai Wang, Daoyuan Wu
Accordingly, our attack, namely BadMoE, exploits the unique architecture of MoE models by 1) identifying dormant experts unrelated to the target task, 2) constructing a routing-aware loss to optimize the activation triggers of these experts, and 3) promoting dormant experts to dominating roles via poisoned training data.
no code implementations • 23 Apr 2025 • Hidde Makimei, Shuai Wang, Willem van Peursen
This triggers the discussion of whether AI can generate accurate images using text from the Bible with respect to the corresponding biblical contexts and backgrounds.
no code implementations • 18 Apr 2025 • Chenxuan Liu, He Li, Zongze Li, Shuai Wang, Wei Xu, Kejiang Ye, Derrick Wing Kwan Ng, Chengzhong Xu
Realizing green communication in robotic mixed reality (RoboMR) systems presents a challenge, due to the necessity of uploading high-resolution images at high frequencies through wireless channels.
1 code implementation • 16 Apr 2025 • Tianhui Song, Weixin Feng, Shuai Wang, Xubin Li, Tiezheng Ge, Bo Zheng, LiMin Wang
The success of text-to-image (T2I) generation models has spurred a proliferation of numerous model checkpoints fine-tuned from the same base model on various specialized datasets.
no code implementations • 14 Apr 2025 • Guanyuan Pan, Tiansheng Zhou, Bingtao Ma, Yaqi Wang, Jianxiang Zhao, Shuai Wang
Circuit link prediction identifying missing component connections from incomplete netlists is crucial in automating analog circuit design.
no code implementations • 10 Apr 2025 • ByteDance Seed, :, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi Lin, Mingxuan Wang, Chengyi Wang, Xiangpeng Wei, Wenyuan Xu, Yufeng Yuan, Yu Yue, Lin Yan, Qiying Yu, Xiaochen Zuo, Chi Zhang, Ruofei Zhu, Zhecheng An, Zhihao Bai, Yu Bao, Xingyan Bin, Jiangjie Chen, Feng Chen, Hongmin Chen, Riwei Chen, Liangqiang Chen, Zixin Chen, Jinsong Chen, Siyan Chen, Kaiyuan Chen, Zhi Chen, Jin Chen, Jiecao Chen, Jinxin Chi, Weinan Dai, Ning Dai, Jiahui Dai, Shihan Dou, Yantao Du, Zhengyin Du, Jianhui Duan, Chen Dun, Ting-Han Fan, Jiazhan Feng, Junda Feng, Ziyuan Feng, Yuwei Fu, Wenqi Fu, Hanjie Fu, Hao Ge, Hongyi Guo, Mingji Han, Li Han, Wenhao Hao, Xintong Hao, Qianyu He, Jerry He, Feng He, Wen Heng, Zehua Hong, Qi Hou, Liang Hu, Shengding Hu, Nan Hu, Kai Hua, Qi Huang, Ziyue Huang, Hongzhi Huang, Zihao Huang, Ting Huang, Wenhao Huang, Wei Jia, Bin Jia, Xiaoying Jia, Yuhua Jiang, Haobin Jiang, Ziheng Jiang, Kaihua Jiang, Chengquan Jiang, Jianpeng Jiao, Xiaoran Jin, Xing Jin, Xunhao Lai, Xiang Li, Liyi Li, Hongkai Li, Zheng Li, Shengxian Wan, Ya Wang, Yunshui Li, Chenggang Li, Niuniu Li, Siyu Li, Xi Li, Xiao Li, Aoyan Li, Yuntao Li, Nianning Liang, Xinnian Liang, Haibin Lin, Weijian Lin, Ye Lin, Zhicheng Liu, Guanlin Liu, Chenxiao Liu, Yan Liu, Gaohong Liu, Juncai Liu, Chundian Liu, Deyi Liu, Kaibo Liu, Siyao Liu, Qi Liu, Yongfei Liu, Kang Liu, Gan Liu, Boyi Liu, Rui Long, Weiqiang Lou, Chenwei Lou, Xiang Luo, Yao Luo, Caiping Lv, Heyang Lv, Bole Ma, Qianli Ma, Hongzhi Ma, Yiyuan Ma, Jin Ma, Wenchang Ma, Tingting Ma, Chen Mao, Qiyang Min, Zhe Nan, Guanghan Ning, Jinxiang Ou, Haojie Pan, Renming Pang, Yanghua Peng, Tao Peng, Lihua Qian, Mu Qiao, Meng Qu, Cheng Ren, Hongbin Ren, Yong Shan, Wei Shen, Ke Shen, Kai Shen, Guangming Sheng, Jinlong Shi, Wenlei Shi, Guang Shi, Shuai Shuai Cao, Yuxin Song, Zuquan Song, Jing Su, Yifan Sun, Tao Sun, Zewei Sun, Borui Wan, Xiaohui Wang, Xi Wang, Shuguang Wang, Jun Wang, Qinlong Wang, Chenyuan Wang, Shuai Wang, Zihan Wang, Changbao Wang, Jiaqiang Wang, Shihang Wang, Xuwu Wang, Zaiyuan Wang, Yuxuan Wang, Wenqi Wang, Taiqing Wang, Chengzhi Wei, Houmin Wei, Ziyun Wei, Shufa Wei, Zheng Wu, Yonghui Wu, Yangjun Wu, Bohong Wu, Shuang Wu, Jingqiao Wu, Ning Wu, Shuangzhi Wu, Jianmin Wu, Chenguang Xi, Fan Xia, Yuqiao Xian, Liang Xiang, Boren Xiang, Bowen Xiao, Zhen Xiao, Xia Xiao, Yongsheng Xiao, Chao Xin, Shulin Xin, Yuwen Xiong, Jingjing Xu, Ziwen Xu, Chenyin Xu, Jiayi Xu, Yifan Xu, Wei Xu, Yufei Xu, Shikun Xu, Shipeng Yan, Shen Yan, Qingping Yang, Xi Yang, Tianhao Yang, Yuehang Yang, Yuan Yang, Ximing Yang, Zeyu Yang, Guang Yang, Yifan Yang, Xuesong Yao, Bairen Yi, Fan Yin, Jianian Yin, Ziqiang Ying, Xiangyu Yu, Hongli Yu, Song Yu, Menghan Yu, Huan Yu, Siyu Yuan, Jun Yuan, Yutao Zeng, Tianyang Zhan, Zheng Zhang, Yun Zhang, Mofan Zhang, Wang Zhang, Ru Zhang, Zhi Zhang, Tianqi Zhang, Xinyi Zhang, Zhexi Zhang, Sijun Zhang, Wenqiang Zhang, Xiangxiang Zhang, Yongtao Zhang, Yuyu Zhang, Ge Zhang, He Zhang, Yue Zhang, Renjie Zheng, Ningxin Zheng, Zhuolin Zheng, Yaowei Zheng, Chen Zheng, Xiaoyun Zhi, Wanjun Zhong, Cheng Zhong, Zheng Zhong, Baoquan Zhong, Xun Zhou, Na Zhou, Huan Zhou, Hang Zhu, Defa Zhu, Wenjia Zhu, Lei Zuo
We introduce Seed1. 5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks.
1 code implementation • 8 Apr 2025 • Shuai Wang, Zhi Tian, Weilin Huang, LiMin Wang
For ImageNet $256\times256$, Our DDT-XL/2 achieves a new state-of-the-art performance of {1. 31 FID}~(nearly $4\times$ faster training convergence compared to previous diffusion transformers).
Ranked #5 on
Image Generation
on ImageNet 512x512
no code implementations • 3 Apr 2025 • Wupeng Wang, Zexu Pan, Xinke Li, Shuai Wang, Haizhou Li
The pretrained frontend employs a transformer decoder network with a causal convolutional encoder as the backbone and is pretrained in a self-supervised manner with two innovative pretext tasks: autoregressive hybrid prediction and contextual knowledge distillation.
no code implementations • 1 Apr 2025 • Wenxuan Wu, Xueyuan Chen, Shuai Wang, Jiadong Wang, Lingwei Meng, Xixin Wu, Helen Meng, Haizhou Li
Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues.
no code implementations • 29 Mar 2025 • Tianyu Hu, Shuai Wang, Yunhang Xie, Lingxiang Li, Zhi Chen, Boyu Ning, Wassim Hamidouche, Lina Bariah, Samson Lasaulce, Merouane Debbah
Integrated sensing and communication (ISAC) in the terahertz (THz) band enables obstacle detection, which in turn facilitates efficient beam management to mitigate THz signal blockage.
Generative Adversarial Network
Integrated sensing and communication
+1
no code implementations • 27 Mar 2025 • Arsham Gholamzadeh Khoee, Shuai Wang, Yinan Yu, Robert Feldt, Dhasarathy Parthasarathy
Ensuring the reliability and effectiveness of software release decisions is critical, particularly in safety-critical domains like automotive systems.
no code implementations • 23 Mar 2025 • Xunguang Wang, Wenxuan Wang, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Daoyuan Wu, Shuai Wang
Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms.
no code implementations • 9 Mar 2025 • Yimeng Shan, Zhenbang Ren, Haodi Wu, Wenjie Wei, Rui-Jie Zhu, Shuai Wang, Dehao Zhang, Yichen Xiao, Jieyuan Zhang, Kexin Shi, Jingzhinan Wang, Jason K. Eshraghian, Haicheng Qu, Jiqing Zhang, Malu Zhang, Yang Yang
Spiking Neural Networks (SNNs) naturally complement event data through discrete spike signals, making them ideal for event-based tracking.
1 code implementation • 5 Mar 2025 • Yuqi Zhou, Shuai Wang, Sunhao Dai, Qinglin Jia, Zhaocheng Du, Zhenhua Dong, Jun Xu
The subtask level, linking high-level goals with low-level executable actions, is crucial for task completion but faces two challenges: ineffective subtasks that lower-level agent cannot execute and inefficient subtasks that fail to contribute to the completion of the higher-level task.
1 code implementation • 4 Mar 2025 • Haoyang Li, Shang Wu, Xiaokang Zhang, Xinmei Huang, Jing Zhang, Fuxin Jiang, Shuai Wang, Tieying Zhang, Jianjun Chen, Rui Shi, Hong Chen, Cuiping Li
Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases.
no code implementations • 3 Mar 2025 • Ziqian Ning, Huakang Chen, Yuepeng Jiang, Chunbo Hao, Guobin Ma, Shuai Wang, Jixun Yao, Lei Xie
To address these challenges, we propose DiffRhythm, the first latent diffusion-based song generation model capable of synthesizing complete songs with both vocal and accompaniment for durations of up to 4m45s in only ten seconds, maintaining high musicality and intelligibility.
no code implementations • 26 Feb 2025 • Shuai Wang, Shihao Zhang, Jiaqi Wu, Zijian Tian, Wei Chen, Tongzhu Jin, Miaomiao Xue, Zehua Wang, Fei Richard Yu, Victor C. M. Leung
Clear monitoring images are crucial for the safe operation of coal mine Internet of Video Things (IoVT) systems.
no code implementations • 25 Feb 2025 • Dehao Zhang, Shuai Wang, Yichen Xiao, Wenjie Wei, Yimeng Shan, Malu Zhang, Yang Yang
In this study, we first identify a new underlying cause for this decline: the loss of historical information due to the quantized membrane potential.
no code implementations • 24 Feb 2025 • Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks.
no code implementations • 24 Feb 2025 • Ruixuan Huang, Xunguang Wang, Zongjie Li, Daoyuan Wu, Shuai Wang
Some jailbreak methods that claim to achieve over 90% attack success rate (ASR) on other benchmarks only reach a maximum of 30. 2% on our benchmark, providing a higher ceiling for more advanced jailbreak research; furthermore, using our scoring system reduces the variance of disagreements between different evaluator LLMs by up to 76. 33%.
1 code implementation • 20 Feb 2025 • Yu Liang, Wenjie Wei, Ammar Belatreche, Honglin Cao, Zijian Zhou, Shuai Wang, Malu Zhang, Yang Yang
Binary Spiking Neural Networks (BSNNs) inherit the eventdriven paradigm of SNNs, while also adopting the reduced storage burden of binarization techniques.
no code implementations • 17 Feb 2025 • Shuqi Yang, Mingrui Jing, Shuai Wang, Jiaxin Kou, Manfei Shi, Weijie Xing, Yan Hu, Zheng Zhu
This study reviewed the use of Large Language Models (LLMs) in healthcare, focusing on their training corpora, customization techniques, and evaluation metrics.
no code implementations • 16 Feb 2025 • Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao, Jen-tse Huang, Youliang Yuan, Pinjia He, Shuai Wang, Zhaopeng Tu
Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.
no code implementations • 14 Feb 2025 • Kuan Li, Liwen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Shuai Wang, Minhao Cheng
However, the advancements in context window size for LLMs offer an alternative approach, raising the question of whether RAG remains necessary for effectively handling external knowledge.
no code implementations • 13 Feb 2025 • Shuai Wang, Ang Li
To estimate these probabilities for subpopulations with insufficient data, we propose using machine learning models that draw insights from subpopulations with sufficient data.
no code implementations • 11 Feb 2025 • Tianyu Hu, Yunhang Xie, Shuai Wang, Boyu Ning, Lingxiang Li, Zhi Chen
To solve such a problem, we propose a THz-based generative radio environment awareness framework, in which obstacle information is obtained directly from the aware radio environment.
no code implementations • 6 Feb 2025 • Shuai Wang, Yinan Yu, Robert Feldt, Dhasarathy Parthasarathy
Vehicle API testing verifies whether the interactions between a vehicle's internal systems and external applications meet expectations, ensuring that users can access and control various vehicle functions and data.
no code implementations • 5 Feb 2025 • Wei-Bin Kou, Guangxu Zhu, Rongguang Ye, Shuai Wang, Ming Tang, Yik-Chung Wu
To mitigate this cost of manual labeling, we propose a Label Anything Model (denoted as LAM), serving as an interpretable, high-fidelity, and prompt-free data annotator.
no code implementations • 24 Jan 2025 • Shuai Wang, Yang Xu, Hui Zheng, Baotian Li
Detecting fabric defects in the textile industry remains a challenging task due to the diverse and complex nature of defect patterns.
no code implementations • 22 Jan 2025 • Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Yuefeng Huang, Wulong Liu, Xinzhi Wang, Defu Lian, Baoqun Yin, Yasheng Wang, Wu Liu
Normal evaluates function calls in basic scenarios; Special evaluates function calls in scenarios with vague or incomplete instructions; Agent introduces multi-agent interactions to simulate function calling evaluation in real-world multi-turn interactions.
no code implementations • 20 Jan 2025 • Shuai Wang, Yanqing Xu, Chaoqun You, Mingjie Shao, Tony Q. S. Quek
In this paper, we propose a novel communication-efficient FL algorithm, named FedQVR, which relies on a sophisticated variance-reduced scheme to achieve heterogeneity-robustness in the presence of quantized transmission and heterogeneous local updates among active edge devices.
no code implementations • 18 Jan 2025 • Jialun Cao, Yuk-Kit Chan, Zixuan Ling, Wenxuan Wang, Shuqing Li, Mingwei Liu, Ruixi Qiao, Yuting Han, Chaozheng Wang, Boxi Yu, Pinjia He, Shuai Wang, Zibin Zheng, Michael R. Lyu, Shing-Chi Cheung
We propose How2Bench, which is comprised of a 55-criteria checklist as a set of guidelines to govern the development of code-related benchmarks comprehensively.
no code implementations • 14 Jan 2025 • Shuai Wang, Liang Ding, Yibing Zhan, Yong Luo, Zheng He, Dapeng Tao
Automated code generation using large language models (LLMs) has gained attention due to its efficiency and adaptability.
1 code implementation • 10 Jan 2025 • Yi Ma, Shuai Wang, Tianchi Liu, Haizhou Li
Furthermore, we investigate phonetic traits from within-speaker and between-speaker variation perspectives to determine which trait is most effective for speaker verification, marking an important step towards explainable speaker verification.
no code implementations • 3 Jan 2025 • Wei-Bin Kou, Qingfeng Lin, Ming Tang, Shuai Wang, Rongguang Ye, Guangxu Zhu, Yik-Chung Wu
Specifically, as the fitted data volume grows to exceed the the AD model's fitting capacities, the AD model is prone to under-fitting.
no code implementations • 18 Dec 2024 • Chenyu Yang, Shuai Wang, Hangting Chen, Jianwei Yu, Wei Tan, Rongzhi Gu, Yaoxun Xu, Yizhi Zhou, Haina Zhu, Haizhou Li
The emergence of novel generative modeling paradigms, particularly audio language models, has significantly advanced the field of song generation.
1 code implementation • 18 Dec 2024 • Elif Ayten, Shuai Wang, Hjalmar Snoep
Recent advances in generative AI make it convenient to create different types of content, including text, images, and code.
no code implementations • 17 Dec 2024 • Tiannan Wang, Meiling Tao, Ruoyu Fang, Huilin Wang, Shuai Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou
In this work, we introduce the task of life-long personalization of large language models.
1 code implementation • 15 Dec 2024 • Zhuo Wu, Qinglin Jia, Chuhan Wu, Zhaocheng Du, Shuai Wang, Zan Wang, Zhenhua Dong
More specifically, for each sample we use LLM to generate a user profile description based on user behavior history or off-the-shelf profile features, which is used to guide LLM to play the role of this user and evaluate the relative preference for two recommendation results generated by different models.
no code implementations • 11 Dec 2024 • Junjie Li, Ke Zhang, Shuai Wang, Kong Aik Lee, Man-Wai Mak, Haizhou Li
Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues.
no code implementations • 4 Dec 2024 • Shuai Wang, Huiyan Kong, Baotian Li, Fa Zheng
Effective defect detection is critical for ensuring the quality, functionality, and economic value of textile products.
1 code implementation • 29 Nov 2024 • Zhi Li, Kai Zhao, Yaqi Wang, Shuai Wang
To mitigate memory bottlenecks and optimize prompt frame selection during the inference of 2D image sequences, we developed an automated system, the Adaptive Frame Selection Engine (AFSE).
1 code implementation • 26 Nov 2024 • Shuai Wang, Shengyao Zhuang, Bevan Koopman, Guido Zuccon
In this reproducibility study, we implement and evaluate both versions of 2D Matryoshka Training on STS tasks and extend our analysis to retrieval tasks.
1 code implementation • 15 Nov 2024 • Luoyu MEI, Ruofeng Liu, Zhimeng Yin, Qingchuan Zhao, Wenchao Jiang, Shuai Wang, Kangjie Lu, Tian He
The mmSpyVR demonstrates the capability to extract critical VR privacy from the mmWave signals that have penetrated through obstacles.
no code implementations • 7 Nov 2024 • Shuai Wang, Weiwen Liu, Jingxuan Chen, Yuqi Zhou, Weinan Gan, Xingshan Zeng, Yuhan Che, Shuai Yu, Xinlong Hao, Kun Shao, Bin Wang, Chuhan Wu, Yasheng Wang, Ruiming Tang, Jianye Hao
Recent advances in foundation models, particularly Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs), have facilitated the development of intelligent agents capable of performing complex tasks.
1 code implementation • 5 Nov 2024 • Wupeng Wang, Zexu Pan, Xinke Li, Shuai Wang, Haizhou Li
As a result, there exists a domain gap between real and synthetic data when deploying speech separation models in real-world applications.
1 code implementation • 1 Nov 2024 • Chumeng Jiang, Jiayin Wang, Weizhi Ma, Charles L. A. Clarke, Shuai Wang, Chuhan Wu, Min Zhang
We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders.
no code implementations • 31 Oct 2024 • Kangxiang Xia, Dake Guo, Jixun Yao, Liumeng Xue, Hanzhao Li, Shuai Wang, Zhao Guo, Lei Xie, Qingqing Zhang, Lei Luo, Minghui Dong, Peng Sun
The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge aims to benchmark and advance zero-shot spontaneous style voice cloning, particularly focusing on generating spontaneous behaviors in conversational speech.
no code implementations • 30 Oct 2024 • Shuai Wang, Zexian Li, Tianhui Song, Xubin Li, Tiezheng Ge, Bo Zheng, LiMin Wang
Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality.
no code implementations • 22 Oct 2024 • Wen Huang, Bing Han, Zhengyang Chen, Shuai Wang, Yanmin Qian
In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning.
1 code implementation • 21 Oct 2024 • Ke Zhang, Junjie Li, Shuai Wang, Yangjie Wei, Yi Wang, Yannan Wang, Haizhou Li
In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue.
1 code implementation • 19 Oct 2024 • Jingxuan Chen, Derek Yuen, Bin Xie, Yuhao Yang, Gongwei Chen, Zhihao Wu, Li Yixing, Xurui Zhou, Weiwen Liu, Shuai Wang, Kaiwen Zhou, Rui Shao, Liqiang Nie, Yasheng Wang, Jianye Hao, Jun Wang, Kun Shao
SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption.
1 code implementation • 17 Oct 2024 • Shengyao Zhuang, Shuai Wang, Bevan Koopman, Guido Zuccon
Effective approaches that can scale embedding model depth (i. e. layers) and embedding size allow for the creation of models that are highly scalable across different computational resources and task requirements.
1 code implementation • 10 Oct 2024 • Yuanqing Yu, Zhefan Wang, Weizhi Ma, Zhicheng Guo, Jingtao Zhan, Shuai Wang, Chuhan Wu, Zhiqiang Guo, Min Zhang
Despite having powerful reasoning and inference capabilities, Large Language Models (LLMs) still need external tools to acquire real-time information retrieval or domain-specific expertise to solve complex tasks, which is referred to as tool learning.
no code implementations • 4 Oct 2024 • Wenxuan Wang, Kuiyi Gao, Zihan Jia, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng Tu
To assess the safety of existing models, we introduce a novel jailbreaking method called Chain-of-Jailbreak (CoJ) attack, which compromises image generation models through a step-by-step editing process.
no code implementations • 29 Sep 2024 • Wei-Bin Kou, Qingfeng Lin, Ming Tang, Rongguang Ye, Shuai Wang, Guangxu Zhu, Yik-Chung Wu
Unfortunately, it suffers from slow convergence because data from different cities are with disparate statistical properties.
no code implementations • 27 Sep 2024 • Ruiqi Liang, Shuai Wang, Yiying Dong, Liu Li, Ying Kuang, Bohan Zhang, Yuanmu Yang
Recently, to address the challenges in processing speed and power consumption of conventional digital convolution operations, many optical components have been suggested to replace the digital convolution layer in the neural network, accelerating various machine vision tasks.
no code implementations • 24 Sep 2024 • Shuai Wang, Pengcheng Zhu, Haizhou Li
Fixed-dimensional speaker embeddings have become the dominant approach in speaker modeling, typically spanning hundreds to thousands of dimensions.
1 code implementation • 24 Sep 2024 • Shuai Wang, Ke Zhang, Shaoxiong Lin, Junjie Li, Xuefei Wang, Meng Ge, Jianwei Yu, Yanmin Qian, Haizhou Li
Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem.
no code implementations • 14 Sep 2024 • Zhijun Liu, Shuai Wang, Pengcheng Zhu, Mengxiao Bi, Haizhou Li
This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation.
no code implementations • 12 Sep 2024 • Kangyang Luo, Shuai Wang, Yexuan Fu, Renrong Shao, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu
In dual-model distillation, the trained dual generators work together to provide the training data for updates of the global model.
no code implementations • 11 Sep 2024 • Kangyang Luo, Shuai Wang, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu
Federated Learning (FL) is gaining popularity as a distributed learning framework that only shares model parameters or gradient updates and keeps private data locally.
no code implementations • 9 Sep 2024 • Shuai Wang, Yibing Zhan, Yong Luo, Han Hu, Wei Yu, Yonggang Wen, DaCheng Tao
This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks.
no code implementations • 9 Sep 2024 • Shuai Wang, Liang Ding, Li Shen, Yong Luo, Zheng He, Wei Yu, DaCheng Tao
Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt.
no code implementations • 3 Sep 2024 • Yiwei Guo, Zhihan Li, Junjie Li, Chenpeng Du, Hankun Wang, Shuai Wang, Xie Chen, Kai Yu
To amend the loss of speaker timbre in the content tokens, vec2wav 2. 0 utilizes the WavLM features to provide strong timbre-dependent information.
1 code implementation • 2 Sep 2024 • Luoyu MEI, Yun Cheng, Ruofeng Liu, Zhimeng Yin, Wenchao Jiang, Shuai Wang, Wei Gong
Notably, ESP-PCT achieves a remarkable accuracy of 93. 2% while reducing the computational requirements (FLOPs) by 76. 9% and memory usage by 78. 2% compared to the existing Point Transformer model simultaneously.
no code implementations • 2 Sep 2024 • Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Zhengying Liu, Yuanqing Yu, Zezhong Wang, Yuxian Wang, Wu Ning, Yutai Hou, Bin Wang, Chuhan Wu, Xinzhi Wang, Yong liu, Yasheng Wang, Duyu Tang, Dandan Tu, Lifeng Shang, Xin Jiang, Ruiming Tang, Defu Lian, Qun Liu, Enhong Chen
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability.
no code implementations • 28 Aug 2024 • Ziqian Ning, Shuai Wang, Yuepeng Jiang, Jixun Yao, Lei He, Shifeng Pan, Jie Ding, Lei Xie
Rap, a prominent genre of vocal performance, remains underexplored in vocal generation.
no code implementations • 23 Aug 2024 • Chengyu Wu, Yatao Zhang, Yaqi Wang, Qifeng Wang, Shuai Wang
In this work, we propose a novel autoencoder-based deep learning model to predict the overall survival of the ESCC.
1 code implementation • 22 Aug 2024 • Shuang Zeng, Pengxin Guo, Shuai Wang, Jianbo Wang, Yuyin Zhou, Liangqiong Qu
To mitigate the impact of data heterogeneity on FL performance, we start with analyzing how FL training influence FL performance by decomposing the global loss into three terms: local loss, distribution shift loss and aggregation loss.
no code implementations • 15 Aug 2024 • Zongjie Li, Daoyuan Wu, Shuai Wang, Zhendong Su
Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataScope, an API-guided dataset synthesis framework designed to enhance the SFT process for LCMs in both general and domain-specific scenarios.
no code implementations • 3 Aug 2024 • Zifeng Li, Wenzhong Tang, Shijun Gao, Shuai Wang, Yanxiang Wang
Deepfake detection faces increasing challenges since the fast growth of generative models in developing massive and diverse Deepfake technologies.
no code implementations • 21 Jul 2024 • Shuai Wang, Zhengyang Chen, Kong Aik Lee, Yanmin Qian, Haizhou Li
Speaker individuality information is among the most critical elements within speech signals.
no code implementations • 18 Jul 2024 • Yaqi Wang, Yifan Zhang, Xiaodiao Chen, Shuai Wang, Dahong Qian, Fan Ye, Feng Xu, Hongyuan Zhang, Qianni Zhang, Chengyu Wu, Yunxiang Li, Weiwei Cui, Shan Luo, Chengkai Wang, TianHao Li, Yi Liu, Xiang Feng, Huiyu Zhou, Dongyun Liu, Qixuan Wang, Zhouhao Lin, Wei Song, Yuanlin Li, Bing Wang, Chunshi Wang, Qiupu Chen, Mingqian Li
The Semi-supervised Teeth Segmentation (STS) Challenge, a pioneering event in tooth segmentation, was held as a part of the MICCAI 2023 ToothFairy Workshop on the Alibaba Tianchi platform.
no code implementations • 12 Jul 2024 • David Rau, Shuai Wang, Hervé Déjean, Stéphane Clinchant
We address this challenge by presenting COCOM, an effective context compression method, reducing long contexts to only a handful of Context Embeddings speeding up the generation time by a large margin.
no code implementations • 7 Jul 2024 • Shuai Wang, Dehao Zhang, Ammar Belatreche, Yichen Xiao, Hongyu Qing, Wenjie We, Malu Zhang, Yang Yang
QT-SNN, compatible with ternary spike trains from the TAE method, quantifies both membrane potentials and synaptic weights to reduce memory requirements while maintaining performance.
no code implementations • 4 Jul 2024 • Bohan Li, Feiyu Shen, Yiwei Guo, Shuai Wang, Xie Chen, Kai Yu
Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM).
1 code implementation • 4 Jul 2024 • Zipei Yan, Zhile Liang, Zhengji Liu, Shuai Wang, Rachel Ka-Man Chun, Jizhou Li, Chea-su Kee, Dong Liang
High myopia significantly increases the risk of irreversible vision loss.
1 code implementation • 1 Jul 2024 • David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Vassilina Nikoulina, Stéphane Clinchant
In response to the recent popularity of generative LLMs, many RAG approaches have been proposed, which involve an intricate number of different configurations such as evaluation datasets, collections, metrics, retrievers, and LLMs.
1 code implementation • 26 Jun 2024 • Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang
In this work, we introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers.
1 code implementation • 25 Jun 2024 • Mikel De Iturrate Reyzabal, Dionysios Malas, Shuai Wang, Sebastien Ourselin, Hongbin Liu
Using internal movements generated by natural processes like breathing or the cardiac cycle, we infer the image-space basis of the motion on the frequency domain.
1 code implementation • 20 Jun 2024 • Shuoqi Sun, Shengyao Zhuang, Shuai Wang, Guido Zuccon
We provide a systematic understanding of the impact of specific components and wordings used in prompts on the effectiveness of rankers based on zero-shot Large Language Models (LLMs).
no code implementations • 19 Jun 2024 • Shuai Wang, Dehao Zhang, Kexin Shi, Yuchen Wang, Wenjie Wei, Jibin Wu, Malu Zhang
Here, we take advantage of spiking neural networks' energy efficiency and propose an end-to-end lightweight KWS model.
no code implementations • 15 Jun 2024 • Pingchuan Ma, Rui Ding, Qiang Fu, Jiaru Zhang, Shuai Wang, Shi Han, Dongmei Zhang
Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs.
no code implementations • 12 Jun 2024 • Ziqian Ning, Shuai Wang, Pengcheng Zhu, Zhichao Wang, Jixun Yao, Lei Xie, Mengxiao Bi
With speaker-independent semantic tokens to guide the training of the content encoder, the dependency on ASR is removed and the model can operate under extremely small chunks, with cascading errors eliminated.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
1 code implementation • 9 Jun 2024 • Linhan Ma, Dake Guo, Kun Song, Yuepeng Jiang, Shuai Wang, Liumeng Xue, Weiming Xu, Huan Zhao, BinBin Zhang, Lei Xie
Furthermore, we have created subsets of varying sizes, categorized by segment quality scores to allow for TTS model training and fine-tuning.
no code implementations • 8 Jun 2024 • Zhijun Liu, Shuai Wang, Sho Inoue, Qibing Bai, Haizhou Li
Our experiments reveal that employing Integral Kullback-Leibler (IKL) divergence for distillation at each autoregressive step significantly boosts the perceived quality of the samples.
no code implementations • 8 Jun 2024 • Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, Juergen Rahmel
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks.
no code implementations • 22 May 2024 • Shuai Wang, David W. Zhang, Jia-Hong Huang, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks.
1 code implementation • 15 May 2024 • Chengyu Wu, Chengkai Wang, Yaqi Wang, Huiyu Zhou, Yatao Zhang, Qifeng Wang, Shuai Wang
In addition, efficient and effective interactions between multi-modal representations need to be further explored, lacking insightful exploration of prognostic correlation in multi-modality features.
no code implementations • 30 Apr 2024 • Hankun Wang, Chenpeng Du, Yiwei Guo, Shuai Wang, Xie Chen, Kai Yu
We call the attention maps of those heads Alignment-Emerged Attention Maps (AEAMs).
2 code implementations • 28 Apr 2024 • Ju Huang, Shiao Wang, Shuai Wang, Zhe Wu, Xiao Wang, Bo Jiang
Specifically, our Mamba-based tracker achieves 43. 5/55. 6 on the SR/PR metric, while the ViT-S based tracker (OSTrack) obtains 40. 0/50. 9.
no code implementations • 27 Apr 2024 • Zhenlan Ji, Daoyuan Wu, Pingchuan Ma, Zongjie Li, Shuai Wang
These synthesized inputs are natural language paragraphs that specify the requirements for completing a series of tasks.
no code implementations • 16 Apr 2024 • Xibin Jin, Guoliang Li, Shuai Wang, Miaowen Wen, Chengzhong Xu, H. Vincent Poor
Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals.
no code implementations • 9 Apr 2024 • Yiwei Guo, Chenrun Wang, Yifan Yang, Hankun Wang, Ziyang Ma, Chenpeng Du, Shuai Wang, Hanzheng Li, Shuai Fan, HUI ZHANG, Xie Chen, Kai Yu
Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice synthesis (SVS).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
2 code implementations • 29 Mar 2024 • Chao Pang, Xingxing Weng, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Shuai Wang, Litong Feng, Gui-Song Xia, Conghui He
VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD).
no code implementations • 28 Mar 2024 • Qi Zhang, Guang Wang, Li Lin, Kaiwen Xia, Shuai Wang
With the advent of the era of big data, massive information, expert experience, and high-accuracy models bring great opportunities to the information cascade prediction of public emergencies.
1 code implementation • 23 Mar 2024 • Zhongsen Li, Wenxuan Chen, Shuai Wang, Chuyu Liu, Qing Zou, Rui Li
A graph convolutional network is utilized for feature fusion and dynamic image generation.
no code implementations • 21 Mar 2024 • Xun Lin, Yi Yu, Song Xia, Jue Jiang, Haoran Wang, Zitong Yu, Yizhong Liu, Ying Fu, Shuai Wang, Wenzhong Tang, Alex Kot
This is particularly true for medical image segmentation (MIS) datasets, where the processes of collection and fine-grained annotation are time-intensive and laborious.
1 code implementation • 14 Mar 2024 • Jiazhao Wang, Wenchao Jiang, Ruofeng Liu, Bin Hu, Demin Gao, Shuai Wang
A physical-layer modulator is a vital component for an IoT gateway to map the symbols to signals.
1 code implementation • 11 Mar 2024 • Ruihua Han, Shuai Wang, Shuaijun Wang, Zeqing Zhang, Jianjun Chen, ShiJie Lin, Chengyang Li, Chengzhong Xu, Yonina C. Eldar, Qi Hao, Jia Pan
This paper presents NeuPAN: a real-time, highly accurate, map-free, easy-to-deploy, and environment-invariant robot motion planner.
no code implementations • 10 Mar 2024 • Fei Wang, Chao Shang, Sarthak Jain, Shuai Wang, Qiang Ning, Bonan Min, Vittorio Castelli, Yassine Benajiba, Dan Roth
We investigate common constraints in NLP tasks, categorize them into three classes based on the types of their arguments, and propose a unified framework, ACT (Aligning to ConsTraints), to automatically produce supervision signals for user alignment with constraints.
2 code implementations • CVPR 2024 • Xun Lin, Shuai Wang, Rizhao Cai, Yizhong Liu, Ying Fu, Zitong Yu, Wenzhong Tang, Alex Kot
Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks.
no code implementations • 24 Feb 2024 • Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu
Our key insight is that regardless of the kind of jailbreak strategies employed, they eventually need to include a harmful prompt (e. g., "how to make a bomb") in the prompt sent to LLMs, and we found that existing LLMs can effectively recognize such harmful prompts that violate their safety policies.
no code implementations • 19 Feb 2024 • Shuai Wang, Shengyao Zhuang, Guido Zuccon
With this respect, we identify three avenues, each characterised by different trade-offs in terms of computational cost, effectiveness and robustness : (1) use LLMs to stem the vocabulary for a collection, i. e., the set of unique words that appear in the collection (vocabulary stemming), (2) use LLMs to stem each document separately (contextual stemming), and (3) use LLMs to extract from each document entities that should not be stemmed, then use vocabulary stemming to stem the rest of the terms (entity-based contextual stemming).
no code implementations • 19 Feb 2024 • Shuai Wang, Ekaterina Khramtsova, Shengyao Zhuang, Guido Zuccon
Federated search systems aggregate results from multiple search engines, selecting appropriate sources to enhance result quality and align with user intent.
no code implementations • 3 Feb 2024 • Ao Sun, Yuanyuan Yuan, Pingchuan Ma, Shuai Wang
This paper alleviates the information leakage issue by introducing label supervision in concept predication and constructing a hierarchical concept set.
no code implementations • 31 Jan 2024 • Shuai Wang, Shengyao Zhuang, Bevan Koopman, Guido Zuccon
Our ReSLLM method exploits LLMs to drive the selection of resources in federated search in a zero-shot setting.
no code implementations • 30 Jan 2024 • Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han Xiao, Zixin Chen, Danjun Xiang, Yunxia Wang, Yuanyuan Zhu, Yi Xiao, Jing Wang, Yiru Wang, Siran Ding, Jiayang Huang, Jiayi Xu, Yilihamu Tayier, Zhenyu Hu, Yuan Gao, Chengfeng Zheng, Yueshu Ye, Yihang Li, Lei Wan, Xinyue Jiang, Yujie Wang, Siyu Cheng, Zhule Song, Xiangru Tang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang, Wangchunshu Zhou
Weaver is pre-trained on a carefully selected corpus that focuses on improving the writing capabilities of large language models.
no code implementations • 27 Jan 2024 • Zongjie Li, Wenying Qiu, Pingchuan Ma, Yichen Li, You Li, Sijia He, Baozheng Jiang, Shuai Wang, Weixi Gu
In this paper, we present a comprehensive empirical study on the accuracy and robustness of LLMs in the context of the Chinese industrial production area.
no code implementations • 25 Jan 2024 • Chenpeng Du, Yiwei Guo, Hankun Wang, Yifan Yang, Zhikang Niu, Shuai Wang, HUI ZHANG, Xie Chen, Kai Yu
Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt.
no code implementations • 12 Jan 2024 • Shuai Wang, Harrisen Scells, Shengyao Zhuang, Martin Potthast, Bevan Koopman, Guido Zuccon
Systematic reviews are crucial for evidence-based medicine as they comprehensively analyse published research findings on specific questions.
1 code implementation • 12 Jan 2024 • Shuai Wang, Liang Ding, Li Shen, Yong Luo, Bo Du, DaCheng Tao
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
no code implementations • 26 Dec 2023 • Meng Ge, Yizhou Peng, Yidi Jiang, Jingru Lin, Junyi Ao, Mehmet Sinan Yildirim, Shuai Wang, Haizhou Li, Mengling Feng
This paper summarizes our team's efforts in both tracks of the ICMC-ASR Challenge for in-car multi-channel automatic speech recognition.
no code implementations • 7 Dec 2023 • Zongjie Li, Chaozheng Wang, Chaowei Liu, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao
With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within multimodal systems.
1 code implementation • 4 Dec 2023 • Xunguang Wang, Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai Wang
This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text.
1 code implementation • 30 Nov 2023 • Tengjin Weng, Yang shen, Zhidong Zhao, Zhiming Cheng, Shuai Wang
Optic disc and cup segmentation plays a crucial role in automating the screening and diagnosis of optic glaucoma.
no code implementations • 20 Nov 2023 • Zhihan Yang, Zhiming Cheng, Tengjin Weng, Shucheng He, Yaqi Wang, Xin Ye, Shuai Wang
Specifically, we design a Patch Message Passing (PMP) module based on the Message Passing mechanism to establish global interaction for pathological semantic features and to exploit the subtle differences further between different diseases.
no code implementations • 17 Nov 2023 • Shuai Wang, Tengjin Weng, Jingyi Wang, Yang shen, Zhidong Zhao, Yixiu Liu, Pengfei Jiao, Zhiming Cheng, Yaqi Wang
Medical image segmentation annotations exhibit variations among experts due to the ambiguous boundaries of segmented objects and backgrounds in medical images.
no code implementations • 14 Nov 2023 • Xinwei Li, Li Lin, Shuai Wang, Chen Qian
The first stage pre-trains the student model on a large number of filtered multi-modal datasets.
1 code implementation • 13 Nov 2023 • Zhenyu Ren, Guoliang Li, Chenqing Ji, Chao Yu, Shuai Wang, Rui Wang
In the proposed CASTER simulator, however, the training dataset can be simulated via existing videos.
no code implementations • 11 Nov 2023 • Xiang Feng, Chengkai Wang, Chengyu Wu, Yunxiang Li, Yongbo He, Shuai Wang, Yaiqi Wang
Precise Tooth Cone Beam Computed Tomography (CBCT) image segmentation is crucial for orthodontic treatment planning.
no code implementations • 8 Nov 2023 • Lukas Gienapp, Harrisen Scells, Niklas Deckers, Janek Bevendorff, Shuai Wang, Johannes Kiesel, Shahbaz Syed, Maik Fröbe, Guido Zuccon, Benno Stein, Matthias Hagen, Martin Potthast
To lay a foundation for developing new evaluation methods for generative retrieval systems, we survey the relevant literature from the fields of information retrieval and natural language processing, identify search tasks and system architectures in generative retrieval, develop a new user model, and study its operationalization.
no code implementations • 30 Oct 2023 • Yiwei Li, Chien-Wei Huang, Shuai Wang, Chong-Yung Chi, Tony Q. S. Quek
Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients' data.
no code implementations • 30 Oct 2023 • Haitao Xu, Songwei Liu, Yuyang Xu, Shuai Wang, Jiashi Li, Chenqian Yan, Liangqiang Li, Lean Fu, Xin Pan, Fangmin Chen
Our framework consists of two parts: (a) A fine-grained kernel sparsity schema with a sparsity granularity between structured pruning and unstructured pruning.
no code implementations • 14 Oct 2023 • Changqing Su, Zihan Lin, You Zhou, Shuai Wang, Yuhan Gao, Chenggang Yan, Bo Xiong
Moreover, by introducing the temporal continuity, our method shows the superior compression ratio on time series data of zebrafish blood vessels.
1 code implementation • 10 Oct 2023 • Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai Wang
We illustrate the insights that our framework can provide by studying over 3 popular LLMs with over 12 prompt adjustment strategies.
1 code implementation • 2 Oct 2023 • Pritthijit Nath, Pancham Shukla, Shuai Wang, César Quilodrán-Casas
As tropical cyclones become more intense due to climate change, the rise of Al-based modelling provides a more affordable and accessible approach compared to traditional methods based on mathematical models.
no code implementations • 29 Sep 2023 • Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, Yang Liu
Specifically, PORTIA splits the answers into multiple segments, aligns similar content across candidate answers, and then merges them back into a single prompt for evaluation by LLMs.
1 code implementation • 28 Sep 2023 • Xun Lin, Wenzhong Tang, Haoran Wang, Yizhong Liu, Yakun Ju, Shuai Wang, Zitong Yu
Compared to image duplication and synthesis, image splicing detection is more challenging due to the lack of reference images and the typically small tampered areas.
no code implementations • 27 Sep 2023 • Ziqian Ning, Yuepeng Jiang, Pengcheng Zhu, Shuai Wang, Jixun Yao, Lei Xie, Mengxiao Bi
Third, the model is unable to effectively address the noise in the unvoiced segments, lowering the sound quality.
no code implementations • 25 Sep 2023 • Jianwei Yu, Hangting Chen, Yanyao Bian, Xiang Li, Yi Luo, Jinchuan Tian, Mengyang Liu, Jiayi Jiang, Shuai Wang
To address this issue, we introduce an automatic in-the-wild speech data preprocessing framework (AutoPrep) in this paper, which is designed to enhance speech quality, generate speaker labels, and produce transcriptions automatically.
no code implementations • 22 Sep 2023 • Shuai Wang, Jiayi Shen, Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs).
no code implementations • 22 Sep 2023 • Pingyue Yue, Yixuan Li, Yue Li, Rui Zhang, Shuai Wang, Jianping An
Low Earth Orbit (LEO) satellites are being extensively researched in the development of secure Internet of Remote Things (IoRT).
no code implementations • 21 Sep 2023 • Shuai Wang, Eric Nalisnick
We apply active learning to help with data scarcity problems in sign languages.
1 code implementation • 21 Sep 2023 • Shuai Wang, Qibing Bai, Qi Liu, Jianwei Yu, Zhengyang Chen, Bing Han, Yanmin Qian, Haizhou Li
Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets.
1 code implementation • 14 Sep 2023 • Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li, Jialong Wu, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Chen, Wentao Zhang, Xiangru Tang, Ningyu Zhang, Huajun Chen, Peng Cui, Mrinmaya Sachan
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces.
no code implementations • 12 Sep 2023 • Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan, Sihang Hu, Tianxiang Li, Shuai Wang
Defenses have also been proposed to guard model weights.
no code implementations • 11 Sep 2023 • Pingchuan Ma, Zhenlan Ji, Peisen Yao, Shuai Wang, Kui Ren
Based on the decision procedure to CIR, CICheck includes two variants: ED-CICheck and ED-CICheck, which detect erroneous CI tests (to enhance reliability) and prune excessive CI tests (to enhance privacy), respectively.
1 code implementation • 11 Sep 2023 • Shuai Wang, Harrisen Scells, Martin Potthast, Bevan Koopman, Guido Zuccon
Our best approach is not only viable based on the information available at the time of screening, but also has similar effectiveness to the final title.
no code implementations • 9 Sep 2023 • Menghao Hu, Tong Zhang, Shuai Wang, Guoliang Li, Yingyang Chen, Qiang Li, Gaojie Chen
Terrestrial robots, i. e., unmanned ground vehicles (UGVs), and aerial robots, i. e., unmanned aerial vehicles (UAVs), operate in separate spaces.
1 code implementation • 31 Aug 2023 • Jinkai Zheng, Xinchen Liu, Shuai Wang, Lihao Wang, Chenggang Yan, Wu Liu
Furthermore, due to the lack of suitable datasets, we build the first parsing-based dataset for gait recognition in the wild, named Gait3D-Parsing, by extending the large-scale and challenging Gait3D dataset.
no code implementations • 31 Aug 2023 • Shuai Wang, Zhen Wang, Yuan-Hai Shao
Furthermore, we propose some different memory impact functions for the MIMM and WIMM.
no code implementations • 29 Aug 2023 • Qingyue Wang, Yanhe Fu, Yanan Cao, Shuai Wang, Zhiliang Tian, Liang Ding
We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation.
1 code implementation • ICCV 2023 • Shuai Wang, Yao Teng, LiMin Wang
To be more specific to object decoding, we use a two-step unrolled equilibrium equation to explicitly capture the query vector refinement.
no code implementations • 5 Jul 2023 • Wenxuan Chen, Sirui Wu, Shuai Wang, Zhongsen Li, Jia Yang, Huifeng Yao, Xiaolei Song
Multi-contrast magnetic resonance imaging (MRI) reflects information about human tissue from different perspectives and has many clinical applications.
1 code implementation • 28 Jun 2023 • Wei-Bin Kou, Shuai Wang, Guangxu Zhu, Bin Luo, Yingxian Chen, Derrick Wing Kwan Ng, Yik-Chung Wu
While federated learning (FL) improves the generalization of end-to-end autonomous driving by model aggregation, the conventional single-hop FL (SFL) suffers from slow convergence rate due to long-range communications among vehicles and cloud server.
no code implementations • 27 Jun 2023 • Shuai Wang, Chengdong Liang, Xu Xiang, Bing Han, Zhengyang Chen, Hongji Wang, Wen Ding
This report showcases the results achieved using the wespeaker toolkit for the VoxSRC2023 Challenge.
no code implementations • 21 Jun 2023 • Hao Xu, Jia Liu, Yang shen, Kenan Lou, Yanxia Bao, Ruihua Zhang, Shuyue Zhou, Hongsen Zhao, Shuai Wang
However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of units dropped by sorting pooling are negative-value units that contain useful information and can contribute considerably to the final decision.
1 code implementation • 15 Jun 2023 • Zhaoyu Wang, Pingchuan Ma, Shuai Wang
Federated learning can solve this problem, but existing solutions for federated causal structure learning make unrealistic assumptions about data and lack convergence guarantees.
1 code implementation • 11 Jun 2023 • Yuanyuan Yuan, Shuai Wang, Zhendong Su
We identify two key properties, independence and continuity, that convert the latent space into a precise and analysis-friendly input space representation for certification.
no code implementations • 5 Jun 2023 • Tengjin Weng, Yang shen, Kai Jin, Zhiming Cheng, Yunxiang Li, Gewen Zhang, Shuai Wang, Yaqi Wang
Specifically, we use points to annotate fluid regions in unlabeled OCT images and the Superpixel-Guided Pseudo-Label Generation (SGPLG) module generates pseudo-labels and pixel-level label trust maps from the point annotations.
no code implementations • 22 May 2023 • Karthikeyan K, Yogarshi Vyas, Jie Ma, Giovanni Paolini, Neha Anna John, Shuai Wang, Yassine Benajiba, Vittorio Castelli, Dan Roth, Miguel Ballesteros
We experiment with 6 diverse datasets and show that PLM consistently performs better than most other approaches (0. 5 - 2. 5 F1), including in novel settings for taxonomy expansion not considered in prior work.
no code implementations • 22 May 2023 • Zhenlan Ji, Pingchuan Ma, Shuai Wang, Yanhui Li
This paper uses causality analysis as a principled method for analyzing trade-offs between fairness parameters and other crucial metrics in ML pipelines.
no code implementations • 21 May 2023 • Ziqian Ning, Yuepeng Jiang, Pengcheng Zhu, Jixun Yao, Shuai Wang, Lei Xie, Mengxiao Bi
Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities.
no code implementations • 19 May 2023 • Robert Vacareanu, Siddharth Varia, Kishaloy Halder, Shuai Wang, Giovanni Paolini, Neha Anna John, Miguel Ballesteros, Smaranda Muresan
We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks.
1 code implementation • NeurIPS 2023 • Ao Sun, Pingchuan Ma, Yuanyuan Yuan, Shuai Wang
For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying important pixels, and emerging concept-based XAI explore forming explanations with concepts (e. g., a head in an image).
no code implementations • 16 May 2023 • Xintao Zhao, Shuai Wang, Yang Chao, Zhiyong Wu, Helen Meng
Experimental results show that our proposed method achieves comparable similarity and higher naturalness than the supervised method, which needs a huge amount of annotated corpora for training and is applicable to improve similarity for VC methods with other SSL representations as input.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
no code implementations • 13 May 2023 • Shuai Wang, Zipei Yan, Daoan Zhang, Zhongsen Li, Sirui Wu, Wenxuan Chen, Rui Li
In contrast, the IID hypothesis is not universally guaranteed in numerous real-world applications, especially in medical image analysis.
no code implementations • 13 May 2023 • Shuai Wang, Daoan Zhang, Zipei Yan, Shitong Shao, Rui Li
In Stage \uppercase\expandafter{\romannumeral1}, we train the target model from scratch with soft pseudo-labels generated by the source model in a knowledge distillation manner.
1 code implementation • 4 May 2023 • Pingchuan Ma, Zongjie Li, Ao Sun, Shuai Wang
Moreover, we propose a novel on-the-fly (OTF) repairing scheme that repairs unethical suggestions made by LLMs in real-time.
no code implementations • 29 Apr 2023 • Mingyang Wang, Zhenshan Bing, Xiangtong Yao, Shuai Wang, Hang Su, Chenguang Yang, Kai Huang, Alois Knoll
On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.
1 code implementation • 26 Apr 2023 • Shitong Shao, Xiaohan Yuan, Zhen Huang, Ziming Qiu, Shuai Wang, Kevin Zhou
Based on this insight, we propose an approach called DiffuseExpand for expanding datasets for 2D medical image segmentation using DPM, which first samples a variety of masks from Gaussian noise to ensure the diversity, and then synthesizes images to ensure the alignment of images and masks.
1 code implementation • ICCV 2023 • Haochen Wang, Cilin Yan, Shuai Wang, XiaoLong Jiang, Xu Tang, Yao Hu, Weidi Xie, Efstratios Gavves
Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos.
no code implementations • 2 Apr 2023 • Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, Dongmei Zhang
In brief, an IQuery is an abstraction and automation of data analysis operations, which mimics the approach of data analysts and simplifies the exploration process for users.
no code implementations • 21 Mar 2023 • Ming Shen, Jie Ma, Shuai Wang, Yogarshi Vyas, Kalpit Dixit, Miguel Ballesteros, Yassine Benajiba
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews.
1 code implementation • CVPR 2023 • Shuai Wang, Daoan Zhang, Zipei Yan, JianGuo Zhang, Rui Li
Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples.
1 code implementation • 17 Mar 2023 • Shuai Wang, Zipei Yan, Daoan Zhang, Haining Wei, Zhongsen Li, Rui Li
Specifically, our ProtoKD can not only distillate the pixel-wise knowledge of multi-modality data to single-modality data but also transfer intra-class and inter-class feature variations, such that the student model could learn more robust feature representation from the teacher model and inference with only one single modality data.
no code implementations • 7 Mar 2023 • Shuai Wang, Daoan Zhang, JianGuo Zhang, Weiwei Zhang, Rui Li
In this paper, considering the balance of data/model privacy of model owners and user needs, we propose a new setting called Back-Propagated Black-Box Adaptation (BPBA) for users to better train their private models via the guidance of the back-propagated results of a Black-box foundation/source model.
no code implementations • 23 Feb 2023 • Katerina Margatina, Shuai Wang, Yogarshi Vyas, Neha Anna John, Yassine Benajiba, Miguel Ballesteros
Temporal concept drift refers to the problem of data changing over time.
no code implementations • 3 Feb 2023 • Shuai Wang, Harrisen Scells, Bevan Koopman, Guido Zuccon
The ability of ChatGPT to follow complex instructions and generate queries with high precision makes it a valuable tool for researchers conducting systematic reviews, particularly for rapid reviews where time is a constraint and often trading-off higher precision for lower recall is acceptable.
no code implementations • 8 Jan 2023 • Shuai Wang, ChiYung Yam, Shuguang Chen, Lihong Hu, Liping Li, Faan-Fung Hung, Jiaqi Fan, Chi-Ming Che, Guanhua Chen
Here, we develop a general protocol for accurate predictions of emission wavelength, radiative decay rate constant, and PL quantum yield for phosphorescent Pt(II) emitters based on the combination of first-principles quantum mechanical method, machine learning (ML) and experimental calibration.
no code implementations • 19 Dec 2022 • Yuxiang Zhang, Zhenbo Liu, Shuai Wang
The execution efficiency of the one-stage scene graph generation approaches are quite high, which infer the effective relation between entity pairs using sparse proposal sets and a few queries.
no code implementations • 18 Dec 2022 • Shuai Wang, Harrisen Scells, Bevan Koopman, Guido Zuccon
An empirical analysis compares how effective neural methods compare to traditional methods for this task.
1 code implementation • 18 Dec 2022 • Shuai Wang, Hang Li, Guido Zuccon
One challenge to creating an effective systematic review Boolean query is the selection of effective MeSH Terms to include in the query.
no code implementations • 11 Dec 2022 • Shitong Shao, Huanran Chen, Zhen Huang, Linrui Gong, Shuai Wang, Xinxiao wu
To be specific, we design a neural network-based data augmentation module with priori bias, which assists in finding what meets the teacher's strengths but the student's weaknesses, by learning magnitudes and probabilities to generate suitable data samples.
no code implementations • 3 Dec 2022 • Shuai Wang, Yanqing Xu, Zhiguo Wang, Tsung-Hui Chang, Tony Q. S. Quek, Defeng Sun
In this paper, we firstly reveal the fact that the federated ADMM is essentially a client-variance-reduced algorithm.
no code implementations • 26 Oct 2022 • Sahisnu Mazumder, Bing Liu, Shuai Wang, Yingxuan Zhu, Xiaotian Yin, Lifeng Liu, Jian Li
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP).
no code implementations • 18 Oct 2022 • Xinrao Li, Tong Zhang, Shuai Wang, Guangxu Zhu, Rui Wang, Tsung-Hui Chang
However, wireless channels between the edge server and the autonomous vehicles are time-varying due to the high-mobility of vehicles.
1 code implementation • 12 Oct 2022 • Siddharth Varia, Shuai Wang, Kishaloy Halder, Robert Vacareanu, Miguel Ballesteros, Yassine Benajiba, Neha Anna John, Rishita Anubhai, Smaranda Muresan, Dan Roth
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts: aspect term, aspect category, opinion term, and sentiment polarity.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
no code implementations • 11 Oct 2022 • Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros
The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge.
no code implementations • 3 Oct 2022 • Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma
BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models.
no code implementations • 2 Oct 2022 • Zhongsen Li, Aiqi Sun, Chuyu Liu, Haining Wei, Shuai Wang, Mingzhu Fu, Rui Li
The main objective of this study is to accelerate the PS model, shorten the time required for acquisition and reconstruction, and maintain good image quality simultaneously.
1 code implementation • 19 Sep 2022 • Shuai Wang, Harrisen Scells, Bevan Koopman, Guido Zuccon
However, identifying the correct MeSH terms to include in a query is difficult: information experts are often unfamiliar with the MeSH database and unsure about the appropriateness of MeSH terms for a query.
no code implementations • 6 Sep 2022 • Yuxiang Zhang, Mengmeng Zhang, Wei Li, Shuai Wang, Ran Tao
Text information including extensive prior knowledge about land cover classes has been ignored in hyperspectral image classification (HSI) tasks.
no code implementations • 16 Aug 2022 • Guoliang Li, Shuai Wang, Kejiang Ye, Miaowen Wen, Derrick Wing Kwan Ng, Marco Di Renzo
Integrated sensing and communication (ISAC) represents a paradigm shift, where previously competing wireless transmissions are jointly designed to operate in harmony via the shared use of the hardware platform for improving the spectral and energy efficiencies.
no code implementations • 9 Aug 2022 • Yunzhi Huang, Sahar Ahmad, Luyi Han, Shuai Wang, Zhengwang Wu, Weili Lin, Gang Li, Li Wang, Pew-Thian Yap
In this paper, we propose a deep learning framework to predict missing scans from acquired scans, catering to longitudinal infant studies.
no code implementations • 26 Jul 2022 • Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, Dongmei Zhang
XInsight is a three-module, end-to-end pipeline designed to extract causal graphs, translate causal primitives into XDA semantics, and quantify the quantitative contribution of each explanation to a data fact.
no code implementations • 16 Jul 2022 • Dongjiang Cao, Ruofeng Liu, Hao Li, Shuai Wang, Wenchao Jiang, Chris Xiaoxuan Lu
Human identification is a key requirement for many applications in everyday life, such as personalized services, automatic surveillance, continuous authentication, and contact tracing during pandemics, etc.
no code implementations • 6 Jul 2022 • Qingya Li, Xiangzhi Liu, Fuqiang Wang, Shuai Wang, Peng Zhang, Xiaoming Wu
In this paper, a novel framework based on generational and environmental response strategies (FGERS) is proposed, in which response strategies are run both in the environmental change stage and the environmental static stage to obtain population evolution information of those both stages.
no code implementations • 4 Jul 2022 • Danpeng Chen, Shuai Wang, Weijian Xie, Shangjin Zhai, Nan Wang, Hujun Bao, Guofeng Zhang
Even if the plane parameters are involved in the optimization, we effectively simplify the back-end map by using planar structures.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2022 • Yuxiang Zhang, Wei Li, Mengmeng Zhang, Shuai Wang, Ran Tao, Qian Du
The IDE-block is used to characterize and aggregate the intradomain nonlocal relationships and the interdomain feature and distribution similarities are captured in the CSA-block.