1 code implementation • ACL 2022 • Mu-Chun Wang, Zixuan Liu, Sheng Wang
We further illustrate how Textomics can be used to advance other applications, including evaluating scientific paper embeddings and generating masked templates for scientific paper understanding.
1 code implementation • Findings (NAACL) 2022 • Junwei Yang, Zequn Liu, Ming Zhang, Sheng Wang
Collectively, we envision our method will become an important benchmark for evaluating Graph2Text methods and advance biomedical research for complex diseases.
no code implementations • 14 Jun 2025 • Yin Luo, Sheng Wang, Javed Jussa
By capturing outliers, volatility clustering, and tail dependence in the asset return distribution, we build a sophisticated model to predict the downside risk of the global financial market.
1 code implementation • 5 Jun 2025 • Shengkun Zhu, Feiteng Nie, Jinshan Zeng, Sheng Wang, Yuan Sun, Yuan YAO, Shangfeng Chen, Quanqing Xu, Chuanhui Yang
In federated learning (FL), the assumption that datasets from different devices are independent and identically distributed (i. i. d.)
no code implementations • 21 May 2025 • Xiaodong Mei, Sheng Wang, Jie Cheng, Yingbing Chen, Dan Xu
Motion forecasting represents a critical challenge in autonomous driving systems, requiring accurate prediction of surrounding agents' future trajectories.
1 code implementation • 20 May 2025 • Jiaming Li, Sheng Wang, Xin Wang, Yitao Zhu, Honglin Xiong, Zixu Zhuang, Qian Wang
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions.
no code implementations • 14 May 2025 • Yitao Zhu, Yuan Yin, Zhenrong Shen, Zihao Zhao, Haiyu Song, Sheng Wang, Dinggang Shen, Qian Wang
The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive.
1 code implementation • 27 Apr 2025 • Pengchao Feng, Ziyang Ma, Wenxi Chen, Yao Li, Sheng Wang, Kai Yu, Xie Chen
In recent years, end-to-end speech-to-speech (S2S) dialogue systems have garnered increasing research attention due to their advantages over traditional cascaded systems, including achieving lower latency and more natural integration of nonverbal cues such as emotion and speaker identity.
no code implementations • 25 Mar 2025 • Sheng Wang
Our research achieves a nuanced fusion of RGB and depth information by integrating a pre-trained Vision Transformer (ViT) with a resampling technique, closely aligning this combined data with linguistic cues for superior multimodal understanding.
no code implementations • 21 Mar 2025 • Sheng Wang, Pengan Chen, Jingqi Zhou, Qintong Li, Jingwei Dong, Jiahui Gao, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu
Model customization requires high-quality and diverse datasets, but acquiring such data remains challenging and costly.
no code implementations • 12 Mar 2025 • Boyang Xue, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Hongling Xu, Fei Mi, Yasheng Wang, Lifeng Shang, Qun Liu, Kam-Fai Wong
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability.
no code implementations • 8 Mar 2025 • Zixuan Liu, Aaron Honjaya, Yuekai Xu, Yi Zhang, Hefu Pan, Xin Wang, Linda G Shapiro, Sheng Wang, Ruikang K Wang
Retinal vessel segmentation is critical for diagnosing ocular conditions, yet current deep learning methods are limited by modality-specific challenges and significant distribution shifts across imaging devices, resolutions, and anatomical regions.
no code implementations • 5 Mar 2025 • Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen, Qinghang Bao, Sheng Wang, Pengan Chen, Jiuming Wang, Lingpeng Kong, Yu Li, Chuan Wu
After training on our dataset, the model also exhibits improved performance on other mainstream language tasks.
no code implementations • 3 Mar 2025 • Yitao Zhu, Yuan Yin, Jiaming Li, Mengjie Xu, Zihao Zhao, Honglin Xiong, Sheng Wang, Qian Wang
The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD).
no code implementations • CVPR 2025 • Mengjie Xu, Yitao Zhu, Haotian Jiang, Jiaming Li, Zhenrong Shen, Sheng Wang, Haolin Huang, Xinyu Wang, Qing Yang, Han Zhang, Qian Wang
Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking.
no code implementations • 25 Jan 2025 • Jiaqi Guan, Jiahan Li, Xiangxin Zhou, Xingang Peng, Sheng Wang, Yunan Luo, Jian Peng, Jianzhu Ma
Molecular docking is a key task in computational biology that has attracted increasing interest from the machine learning community.
1 code implementation • 16 Dec 2024 • Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, Kam-Fai Wong
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous.
1 code implementation • 9 Dec 2024 • Kangyu Zhu, Peng Xia, Yun Li, Hongtu Zhu, Sheng Wang, Huaxiu Yao
Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness.
1 code implementation • 3 Dec 2024 • Yushuai Ji, Zepeng Liu, Sheng Wang, Yuan Sun, Zhiyong Peng
Experiments show that when simplifying datasets with scale such as $10^6$, Dask-means uses less than $30$MB of memory, achieves over $168$ times speedup compared to the widely-used Lloyd's algorithm.
no code implementations • 3 Dec 2024 • Zongxia Liang, Sheng Wang, Jianming Xia
This paper discusses a nonlinear integral equation arising from portfolio selection with a class of time-inconsistent preferences.
no code implementations • 26 Nov 2024 • Sheng Wang, Yao Tian, Xiaodong Mei, Ge Sun, Jie Cheng, Fulong Ma, Pedro V. Sander, Junwei Liang
However, these algorithms typically assess the current and historical plans independently, leading to discontinuities in driving intentions and an accumulation of errors with each step in a discontinuous plan.
1 code implementation • 26 Nov 2024 • Jiahan Li, Tong Chen, Shitong Luo, Chaoran Cheng, Jiaqi Guan, Ruihan Guo, Sheng Wang, Ge Liu, Jian Peng, Jianzhu Ma
To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins.
no code implementations • 14 Nov 2024 • Albert J. Zhai, Xinlei Wang, Kaiyuan Li, Zhao Jiang, Junxiong Zhou, Sheng Wang, Zhenong Jin, Kaiyu Guan, Shenlong Wang
The ability to automatically build 3D digital twins of plants from images has countless applications in agriculture, environmental science, robotics, and other fields.
1 code implementation • 12 Nov 2024 • Yang Hu, Xiao Wang, Lirong Wu, Huatian Zhang, Stan Z. Li, Sheng Wang, Tianlong Chen
FM-TS is more efficient in terms of training and inference.
no code implementations • 22 Oct 2024 • Qintong Li, Jiahui Gao, Sheng Wang, Renjie Pi, Xueliang Zhao, Chuan Wu, Xin Jiang, Zhenguo Li, Lingpeng Kong
In this paper, we present a novel approach, ReverseGen, designed to automatically generate effective training samples that expose the weaknesses of LLMs.
no code implementations • 18 Oct 2024 • Jingqi Zhou, Sheng Wang, Jingwei Dong, Lei LI, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu
Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs.
1 code implementation • 16 Oct 2024 • Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, Huaxiu Yao
Artificial Intelligence (AI) has demonstrated significant potential in healthcare, particularly in disease diagnosis and treatment planning.
1 code implementation • 16 Oct 2024 • Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Kam-Fai Wong
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
no code implementations • 15 Oct 2024 • Jiacheng Lin, Kun Qian, Haoyu Han, Nurendra Choudhary, Tianxin Wei, Zhongruo Wang, Sahika Genc, Edward W Huang, Sheng Wang, Karthik Subbian, Danai Koutra, Jimeng Sun
Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval, question answering, and classification.
no code implementations • 15 Oct 2024 • Juntao Zhao, Wenhao Lu, Sheng Wang, Lingpeng Kong, Chuan Wu
Compared to high-precision quantization methods, QSPEC empirically boosts token generation throughput by up to 1. 64x without any quality compromise, distinguishing it from other low-precision quantization approaches.
no code implementations • 1 Oct 2024 • Sheng Wang, Liheng Chen, Pengan Chen, Jingwei Dong, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu
The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served simultaneously.
1 code implementation • 29 Aug 2024 • Jiyue Jiang, Pengan Chen, Liheng Chen, Sheng Wang, Qinghang Bao, Lingpeng Kong, Yu Li, Chuan Wu
The rapid evolution of large language models (LLMs) has transformed the competitive landscape in natural language processing (NLP), particularly for English and other data-rich languages.
no code implementations • 20 Aug 2024 • Zixuan Liu, Hanwen Xu, Addie Woicik, Linda G. Shapiro, Marian Blazes, Yue Wu, Verena Steffen, Catherine Cukras, Cecilia S. Lee, Miao Zhang, Aaron Y. Lee, Sheng Wang
It then exploits a novel multi-modal contrastive learning framework COEP to integrate other retinal imaging modalities, such as fundus autofluorescence and infrared retinal imaging, into OCTCube, efficiently extending it into multi-modal foundation models.
no code implementations • 29 Jul 2024 • YuHan Liu, Sheng Wang, Yixuan Liu, Feifei Li, Hong Chen
To provide a rigorous DP guarantee for SVT, prior works in the literature adopt a conservative privacy analysis by assuming the direct disclosure of noisy query results as in typical private query releases.
1 code implementation • 23 Jul 2024 • Shengkun Zhu, Jinshan Zeng, Sheng Wang, Yuan Sun, XiaoDong Li, Yuan YAO, Zhiyong Peng
Personalized FL (PFL) is an approach that aims to reduce the impact of statistical heterogeneity by developing personalized models for individual users, while also inherently providing benefits in terms of fairness and robustness.
1 code implementation • 25 Jun 2024 • Jiacheng Lin, Hanwen Xu, Zifeng Wang, Sheng Wang, Jimeng Sun
To address this challenge, we propose a clinical trial foundation model named Panacea, designed to handle multiple tasks, including trial search, trial summarization, trial design, and patient-trial matching.
no code implementations • 24 Jun 2024 • Jiyue Jiang, Liheng Chen, Sheng Wang, Lingpeng Kong, Yu Li, Chuan Wu
The thought generated by the progressive thought generator serves as a prompt to prevent the generated dialogue from having significant semantic deviations, while the psychology knowledge generator produces psychological knowledge to serve as the dialogue history for the LLM, guiding the dialogue generator to create multi-turn psychological dialogue.
no code implementations • 24 Jun 2024 • Shengkun Zhu, Jinshan Zeng, Yuan Sun, Sheng Wang, XiaoDong Li, Zhiyong Peng
Our experiments demonstrate that TKM outperforms state-of-the-art methods in effectiveness, fairness, and efficiency.
1 code implementation • 16 Jun 2024 • Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han
In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e. g., molecules and proteins) are handled, achieving superior performance in various applications and augmenting the scientific discovery process.
no code implementations • 10 Jun 2024 • Xin Wang, Zhiyun Song, Yitao Zhu, Sheng Wang, Lichi Zhang, Dinggang Shen, Qian Wang
To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated.
no code implementations • 25 May 2024 • Si Xu, Zixiao Huang, Yan Zeng, Shengen Yan, Xuefei Ning, Quanlu Zhang, Haolin Ye, Sipei Gu, Chunsheng Shui, Zhezheng Lin, Hao Zhang, Sheng Wang, Guohao Dai, Yu Wang
We train the Llama-140B model on a heterogeneous cluster with 768 GPU-accelerators(128 AMD and 640 GPU-accelerator A).
no code implementations • 21 May 2024 • Theodore Zhao, Yu Gu, Jianwei Yang, Naoto Usuyama, Ho Hin Lee, Tristan Naumann, Jianfeng Gao, Angela Crabtree, Jacob Abel, Christine Moung-Wen, Brian Piening, Carlo Bifulco, Mu Wei, Hoifung Poon, Sheng Wang
On object recognition, which aims to identify all objects in a given image along with their semantic types, we showed that BiomedParse can simultaneously segment and label all biomedical objects in an image (all at once).
1 code implementation • 15 May 2024 • Yan Kong, Sheng Wang, Jiangdong Cai, Zihao Zhao, Zhenrong Shen, Yonghao Li, Manman Fei, Qian Wang
Accurate detection of vulvovaginal candidiasis is critical for women's health, yet its sparse distribution and visually ambiguous characteristics pose significant challenges for accurate identification by pathologists and neural networks alike.
no code implementations • 19 Apr 2024 • Sheng Wang, Ge Sun, Fulong Ma, Tianshuai Hu, Qiang Qin, Yongkang Song, Lei Zhu, Junwei Liang
Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion.
no code implementations • 11 Apr 2024 • Sheng Wang, Tianming Du, Katherine Fischer, Gregory E Tasian, Justin Ziemba, Joanie M Garratt, Hersh Sagreiya, Yong Fan
Computer-aided diagnosis systems hold great promise to aid radiologists and clinicians in radiological clinical practice and enhance diagnostic accuracy and efficiency.
no code implementations • 10 Apr 2024 • Fulong Ma, Weiqing Qi, Guoyang Zhao, Linwei Zheng, Sheng Wang, Yuxuan Liu, Ming Liu, Jun Ma
This review looks back and analyzes the current state of achievements in the field of 3D lane detection research.
no code implementations • CVPR 2024 • Albert J. Zhai, Yuan Shen, Emily Y. Chen, Gloria X. Wang, Xinlei Wang, Sheng Wang, Kaiyu Guan, Shenlong Wang
Can computers perceive the physical properties of objects solely through vision?
1 code implementation • 12 Mar 2024 • Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu, Hanwen Xu, Naoto Usuyama, Sheng Zhang, Fei Wang, Yujia Xie, Mahmoud Khademi, ZiYi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang, Chunyuan Li, Jianfeng Gao, Yu Gu, Cliff Wong, Mu Wei, Tristan Naumann, Muhao Chen, Matthew P. Lungren, Akshay Chaudhari, Serena Yeung-Levy, Curtis P. Langlotz, Sheng Wang, Hoifung Poon
Frontier general-domain models such as GPT-4V still have significant performance gaps in multimodal biomedical applications.
1 code implementation • 8 Mar 2024 • Yitao Zhu, Sheng Wang, Mengjie Xu, Zixu Zhuang, Zhixin Wang, Kaidong Wang, Han Zhang, Qian Wang
Rather than merely averaging the models across views, we develop a neural network trained to assign weights to individual views for all human body joints, based on the estimated distribution of joint distances from each camera.
no code implementations • 25 Feb 2024 • Sheng Wang, Liheng Chen, Jiyue Jiang, Boyang Xue, Lingpeng Kong, Chuan Wu
Hence, a possible contradiction arises from negligible trainable parameters of LoRA and the effectiveness of previous dropout methods, which has been largely overlooked.
1 code implementation • 24 Feb 2024 • Sheng Wang, Boyang Xue, Jiacheng Ye, Jiyue Jiang, Liheng Chen, Lingpeng Kong, Chuan Wu
Hopefully, the conspicuously higher parameter efficiency can establish PRoLoRA as a resource-friendly alternative to LoRA.
no code implementations • 22 Feb 2024 • Zhenrong Shen, Manman Fei, Xin Wang, Jiangdong Cai, Sheng Wang, Lichi Zhang, Qian Wang
In the first Global Image Generation stage, a Normal Image Generator is designed to generate cytopathological images full of normal cervical cells.
1 code implementation • 21 Feb 2024 • Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Kam-Fai Wong
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
1 code implementation • 26 Jan 2024 • Yifeng Liu, Hanwen Xu, Tangqi Fang, Haocheng Xi, Zixuan Liu, Sheng Zhang, Hoifung Poon, Sheng Wang
As a fundamental task in computational chemistry, retrosynthesis prediction aims to identify a set of reactants to synthesize a target molecule.
no code implementations • 16 Jan 2024 • Zongxia Liang, Sheng Wang, Jianming Xia, Fengyi Yuan
This paper addresses the continuous-time portfolio selection problem under generalized disappointment aversion (GDA).
1 code implementation • 12 Dec 2023 • Zihao Zhao, Yuxiao Liu, Han Wu, Mei Wang, Yonghao Li, Sheng Wang, Lin Teng, Disheng Liu, Zhiming Cui, Qian Wang, Dinggang Shen
With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications.
1 code implementation • 11 Dec 2023 • Zihao Zhao, Sheng Wang, Qian Wang, Dinggang Shen
Accordingly, we introduce the Medical contrastive Gaze Image Pre-training (McGIP) as a plug-and-play module for contrastive learning frameworks.
no code implementations • 25 Nov 2023 • Ge Sun, Sheng Wang, Lei Zhu, Ming Liu, Jun Ma
To address these challenges and facilitate the use of diffusion models in multi-modal trajectory prediction, we propose GDTS, a novel Goal-Guided Diffusion Model with Tree Sampling for multi-modal trajectory prediction.
no code implementations • 19 Nov 2023 • Juntao Zhang, Sheng Wang, Zhiyu Chen, Xiandi Yang, Zhiyong Peng
Finally, we develop an attention aggregator that aggregates users' preferences as the group's preferences for the group recommendation task.
1 code implementation • 14 Nov 2023 • Yitao Zhu, Zhenrong Shen, Zihao Zhao, Sheng Wang, Xin Wang, Xiangyu Zhao, Dinggang Shen, Qian Wang
By fixing the weight of ViT models and only adding small low-rank plug-ins, we achieve competitive results on various diagnosis tasks across different imaging modalities using only a few trainable parameters.
1 code implementation • 14 Nov 2023 • Zhiyun Song, Zengxin Qi, Xin Wang, Xiangyu Zhao, Zhenrong Shen, Sheng Wang, Manman Fei, Zhe Wang, Di Zang, Dongdong Chen, Linlin Yao, Qian Wang, Xuehai Wu, Lichi Zhang
Cross-modality synthesis (CMS), super-resolution (SR), and their combination (CMSR) have been extensively studied for magnetic resonance imaging (MRI).
no code implementations • 12 Nov 2023 • Shengkun Zhu, Jinshan Zeng, Sheng Wang, Yuan Sun, Zhiyong Peng
Our experiments validate that FLAME, when trained on heterogeneous data, outperforms state-of-the-art methods in terms of model performance.
no code implementations • 7 Oct 2023 • Zixuan Liu, Gaurush Hiranandani, Kun Qian, Eddie W. Huang, Yi Xu, Belinda Zeng, Karthik Subbian, Sheng Wang
ForeSeer transfers reviews from similar products on a large product graph and exploits these reviews to predict aspects that might emerge in future reviews.
2 code implementations • 14 Sep 2023 • Haozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang
In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts.
Ranked #17 on
Visual Reasoning
on Winoground
1 code implementation • 2 Sep 2023 • Xiangyu Zhao, Sheng Wang, Zhiyun Song, Zhenrong Shen, Linlin Yao, Haolei Yuan, Qian Wang, Lichi Zhang
To address these issues, we propose a novel one-shot medical image segmentation method with adversarial training and label error rectification (AdLER), with the aim of improving the diversity of generated data and correcting label errors to enhance segmentation performance.
1 code implementation • 25 Jul 2023 • Zhengliang Liu, Tianyang Zhong, Yiwei Li, Yutong Zhang, Yi Pan, Zihao Zhao, Peixin Dong, Chao Cao, Yuxiao Liu, Peng Shu, Yaonai Wei, Zihao Wu, Chong Ma, Jiaqi Wang, Sheng Wang, Mengyue Zhou, Zuowei Jiang, Chunlin Li, Jason Holmes, Shaochen Xu, Lu Zhang, Haixing Dai, Kai Zhang, Lin Zhao, Yuanhao Chen, Xu Liu, Peilong Wang, Pingkun Yan, Jun Liu, Bao Ge, Lichao Sun, Dajiang Zhu, Xiang Li, Wei Liu, Xiaoyan Cai, Xintao Hu, Xi Jiang, Shu Zhang, Xin Zhang, Tuo Zhang, Shijie Zhao, Quanzheng Li, Hongtu Zhu, Dinggang Shen, Tianming Liu
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
1 code implementation • 12 Jul 2023 • Zhenrong Shen, Maosong Cao, Sheng Wang, Lichi Zhang, Qian Wang
In this paper, we propose CellGAN to synthesize cytopathological images of various cervical cell types for augmenting patch-level cell classification.
no code implementations • 5 Jun 2023 • Han Xie, Da Zheng, Jun Ma, Houyu Zhang, Vassilis N. Ioannidis, Xiang Song, Qing Ping, Sheng Wang, Carl Yang, Yi Xu, Belinda Zeng, Trishul Chilimbi
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain.
1 code implementation • 25 May 2023 • Zihao Zhao, Sheng Wang, Jinchen Gu, Yitao Zhu, Lanzhuju Mei, Zixu Zhuang, Zhiming Cui, Qian Wang, Dinggang Shen
The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic processes akin to those performed by radiologists and providing consultations similar to a virtual family doctor.
1 code implementation • 15 May 2023 • Sheng Wang, Zixu Zhuang, Xi Ouyang, Lichi Zhang, Zheren Li, Chong Ma, Tianming Liu, Dinggang Shen, Qian Wang
Then, we propose a novel augmentation method, i. e., FocusContrast, to learn from radiologists' gaze in diagnosis and generate contrastive views for medical images with guidance from radiologists' visual attention.
no code implementations • 14 May 2023 • Jiyue Jiang, Sheng Wang, Qintong Li, Lingpeng Kong, Chuan Wu
In this paper, we propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the CS principle and emotional support strategy.
no code implementations • 20 Apr 2023 • Zheren Li, Zhiming Cui, Lichi Zhang, Sheng Wang, Chenjin Lei, Xi Ouyang, Dongdong Chen, Xiangyu Zhao, Yajia Gu, Zaiyi Liu, Chunling Liu, Dinggang Shen, Jie-Zhi Cheng
The training of an efficacious deep learning model requires large data with diverse styles and qualities.
no code implementations • 16 Apr 2023 • Xin Wang, Zhenrong Shen, Zhiyun Song, Sheng Wang, Mengjun Liu, Lichi Zhang, Kai Xuan, Qian Wang
Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution.
1 code implementation • 3 Apr 2023 • Honglin Xiong, Sheng Wang, Yitao Zhu, Zihao Zhao, Yuxiao Liu, Linlin Huang, Qian Wang, Dinggang Shen
The recent progress of large language models (LLMs), including ChatGPT and GPT-4, in comprehending and responding to human instructions has been remarkable.
5 code implementations • 2 Mar 2023 • Sheng Zhang, Yanbo Xu, Naoto Usuyama, Hanwen Xu, Jaspreet Bagga, Robert Tinn, Sam Preston, Rajesh Rao, Mu Wei, Naveen Valluri, Cliff Wong, Andrea Tupini, Yu Wang, Matt Mazzola, Swadheen Shukla, Lars Liden, Jianfeng Gao, Angela Crabtree, Brian Piening, Carlo Bifulco, Matthew P. Lungren, Tristan Naumann, Sheng Wang, Hoifung Poon
Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs.
Ranked #2 on
Medical Visual Question Answering
on SLAKE-English
no code implementations • 14 Feb 2023 • Cai Yang, Addie Woicik, Hoifung Poon, Sheng Wang
Instead of obtaining features from language models, we propose BLIAM, a literature-based data synthesis approach to directly generate training data points that are interpretable and model-agnostic to downstream applications.
1 code implementation • 14 Feb 2023 • Sheng Wang, Zihao Zhao, Xi Ouyang, Qian Wang, Dinggang Shen
Large language models (LLMs) have recently demonstrated their potential in clinical applications, providing valuable medical knowledge and advice.
1 code implementation • 13 Jan 2023 • Xiangyu Zhao, Zengxin Qi, Sheng Wang, Qian Wang, Xuehai Wu, Ying Mao, Lichi Zhang
However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches.
1 code implementation • 26 Nov 2022 • Jinxin Lv, Xiaoyu Zeng, Sheng Wang, Ran Duan, Zhiwei Wang, Qiang Li
In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues.
1 code implementation • 7 Nov 2022 • Yue Guo, Wei Qiu, Gondy Leroy, Sheng Wang, Trevor Cohen
Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility.
1 code implementation • 14 Oct 2022 • Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu, Ming Zhang, Sheng Wang
Meta-path, a sequence of node types and edge types, is the core technique to embed HINs.
no code implementations • 20 Sep 2022 • Lin He, Zongxia Liang, Sheng Wang
The wealth of the retiree is divided into a bequest account and a tontine account.
1 code implementation • 23 Aug 2022 • Lu Yang, Sheng Wang, Russ B. Altman
We describe a method for phenotype recognition that imputes phenotype codes for all UK Biobank participants.
no code implementations • 12 Aug 2022 • Xiangyu Zhao, Di Zang, Sheng Wang, Zhenrong Shen, Kai Xuan, Zeyu Wei, Zhe Wang, Ruizhe Zheng, Xuehai Wu, Zheren Li, Qian Wang, Zengxin Qi, Lichi Zhang
To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps.
1 code implementation • 11 Jul 2022 • Mehmet Saygın Seyfioğlu, Zixuan Liu, Pranav Kamath, Sadjyot Gangolli, Sheng Wang, Thomas Grabowski, Linda Shapiro
On top of BAR, we propose using a soft-label-capable supervised contrastive loss, aiming to learn the relative similarity of representations that reflect how mixed are the synthetic MRIs using our soft labels.
3 code implementations • 4 Jul 2022 • Tao Shen, Zhihang Hu, Siqi Sun, Di Liu, Felix Wong, Jiuming Wang, Jiayang Chen, YiXuan Wang, Liang Hong, Jin Xiao, Liangzhen Zheng, Tejas Krishnamoorthi, Irwin King, Sheng Wang, Peng Yin, James J. Collins, Yu Li
Accurate prediction of RNA three-dimensional (3D) structure remains an unsolved challenge.
1 code implementation • 27 Jun 2022 • Zechen Wang, Liangzhen Zheng, Sheng Wang, Mingzhi Lin, Zhihao Wang, Adams Wai-Kin Kong, Yuguang Mu, Yanjie Wei, Weifeng Li
In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF.
no code implementations • 10 Jun 2022 • Fenglin Liu, Bang Yang, Chenyu You, Xian Wu, Shen Ge, Adelaide Woicik, Sheng Wang
This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i. e., molecular function, biological process, and cellular component.
1 code implementation • 31 May 2022 • Samuel N. Cohen, Christoph Reisinger, Sheng Wang
We study the capability of arbitrage-free neural-SDE market models to yield effective strategies for hedging options.
no code implementations • 25 May 2022 • Chong Ma, Lin Zhao, Yuzhong Chen, Lu Zhang, Zhenxiang Xiao, Haixing Dai, David Liu, Zihao Wu, Zhengliang Liu, Sheng Wang, Jiaxing Gao, Changhe Li, Xi Jiang, Tuo Zhang, Qian Wang, Dinggang Shen, Dajiang Zhu, Tianming Liu
To address this problem, we propose to infuse human experts' intelligence and domain knowledge into the training of deep neural networks.
no code implementations • 23 May 2022 • Xin Wang, Sheng Wang, Honglin Xiong, Kai Xuan, Zixu Zhuang, Mengjun Liu, Zhenrong Shen, Xiangyu Zhao, Lichi Zhang, Qian Wang
Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution.
1 code implementation • NAACL 2022 • Yu Zhang, Yu Meng, Xuan Wang, Sheng Wang, Jiawei Han
Discovering latent topics from text corpora has been studied for decades.
no code implementations • 20 Apr 2022 • Hanwen Xu, Sheng Wang
Here, we tackle this problem by annotating proteins to a function only based on its textual description so that we do not need to know any associated proteins for this function.
1 code implementation • 6 Apr 2022 • Sheng Wang, Xi Ouyang, Tianming Liu, Qian Wang, Dinggang Shen
In this paper, we demonstrate that the eye movement of radiologists reading medical images can be a new form of supervision to train the DNN-based computer-aided diagnosis (CAD) system.
1 code implementation • 15 Feb 2022 • Samuel N. Cohen, Christoph Reisinger, Sheng Wang
In this paper, we examine the capacity of an arbitrage-free neural-SDE market model to produce realistic scenarios for the joint dynamics of multiple European options on a single underlying.
no code implementations • 14 Jan 2022 • Jun Wu, Elizabeth A. Ainsworth, Sheng Wang, Kaiyu Guan, Jingrui He
Plant phenotyping (Guo et al. 2021; Pieruschka et al. 2019) focuses on studying the diverse traits of plants related to the plants' growth.
no code implementations • 12 Jan 2022 • Zixu Zhuang, Liping Si, Sheng Wang, Kai Xuan, Xi Ouyang, Yiqiang Zhan, Zhong Xue, Lichi Zhang, Dinggang Shen, Weiwu Yao, Qian Wang
Knee osteoarthritis (OA) is the most common osteoarthritis and a leading cause of disability.
no code implementations • 30 Nov 2021 • Tong Chen, Sheng Wang
With the increasingly available large-scale cancer genomics datasets, machine learning approaches have played an important role in revealing novel insights into cancer development.
1 code implementation • 21 Nov 2021 • Zheren Li, Zhiming Cui, Sheng Wang, Yuji Qi, Xi Ouyang, Qitian Chen, Yuezhi Yang, Zhong Xue, Dinggang Shen, Jie-Zhi Cheng
Specifically, the backbone network is firstly trained with a multi-style and multi-view unsupervised self-learning scheme for the embedding of invariant features to various vendor-styles.
1 code implementation • 13 Nov 2021 • Hanwen Xu, Jiayou Zhang, Zhirui Wang, Shizhuo Zhang, Megh Manoj Bhalerao, Yucong Liu, Dawei Zhu, Sheng Wang
In the expansion of biomedical dataset, the same category may be labeled with different terms, thus being tedious and onerous to curate these terms.
no code implementations • NeurIPS 2021 • Fenglin Liu, Chenyu You, Xian Wu, Shen Ge, Sheng Wang, Xu sun
KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder.
1 code implementation • 25 Sep 2021 • Jinxin Lv, Zhiwei Wang, Hongkuan Shi, Haobo Zhang, Sheng Wang, Yilang Wang, Qiang Li
Registration of brain MRI images requires to solve a deformation field, which is extremely difficult in aligning intricate brain tissues, e. g., subcortical nuclei, etc.
1 code implementation • Nature Communications 2021 • Sheng Wang, Angela Oliveira Pisco, Aaron McGeever, Maria Brbic, Marinka Zitnik, Spyros Darmanis, Jure Leskovec, Jim Karkanias, Russ B. Altman
Single cell technologies are rapidly generating large amounts of data that enables us to understand biological systems at single-cell resolution.
1 code implementation • EMNLP 2021 • Zequn Liu, Shukai Wang, Yiyang Gu, Ruiyi Zhang, Ming Zhang, Sheng Wang
Unfortunately, the lack of large-scale terminology definition dataset hinders the process toward definition generation.
no code implementations • 17 Aug 2021 • Jingjing Lyu, Musong Gu, Sheng Wang
Sterile insect technique has been successfully applied in the control of agricultural pests, however, it has a limited ability to control mosquitoes.
no code implementations • 12 Aug 2021 • Meng Cao, HaoZhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao, Zhifeng Li, Jiebo Luo
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
no code implementations • 5 Aug 2021 • Qin Wang, Jun Wei, Boyuan Wang, Zhen Li1, Sheng Wang, Shuguang Cu
Protein secondary structure prediction (PSSP) is essential for protein function analysis.
1 code implementation • CVPR 2021 • Jun Wei, Qin Wang, Zhen Li, Sheng Wang, S. Kevin Zhou, Shuguang Cui
In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.
1 code implementation • 21 Jun 2021 • Yifan Wang, Suyao Tang, Yuntong Lei, Weiping Song, Sheng Wang, Ming Zhang
In this paper, we propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation, which learns disentangled user/item representations from different aspects in a heterogeneous information network.
1 code implementation • 24 May 2021 • Samuel N. Cohen, Christoph Reisinger, Sheng Wang
Modelling joint dynamics of liquid vanilla options is crucial for arbitrage-free pricing of illiquid derivatives and managing risks of option trade books.
no code implementations • 11 May 2021 • Jiaxiang Wu, Shitong Luo, Tao Shen, Haidong Lan, Sheng Wang, Junzhou Huang
In this paper, we propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network.
no code implementations • 10 May 2021 • Liangzhen Zheng, Haidong Lan, Tao Shen, Jiaxiang Wu, Sheng Wang, Wei Liu, Junzhou Huang
Protein structure prediction has been a grand challenge for over 50 years, owing to its broad scientific and application interests.
no code implementations • 8 Mar 2021 • Tu Gu, Kaiyu Feng, Gao Cong, Cheng Long, Zheng Wang, Sheng Wang
Learned indices have been proposed to replace classic index structures like B-Tree with machine learning (ML) models.
1 code implementation • ICCV 2021 • Zhihao Yuan, Xu Yan, Yinghong Liao, Ruimao Zhang, Sheng Wang, Zhen Li, Shuguang Cui
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging.
1 code implementation • 8 Dec 2020 • Qihang Fang, Yingda Yin, Qingnan Fan, Fei Xia, Siyan Dong, Sheng Wang, Jue Wang, Leonidas Guibas, Baoquan Chen
These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale.
no code implementations • 13 Oct 2020 • Sheng Wang, Yuan Sun, Zhifeng Bao
This paper presents a thorough evaluation of the existing methods that accelerate Lloyd's algorithm for fast k-means clustering.
1 code implementation • 12 Oct 2020 • Linchao Bao, Xiangkai Lin, Yajing Chen, Haoxian Zhang, Sheng Wang, Xuefei Zhe, Di Kang, HaoZhi Huang, Xinwei Jiang, Jue Wang, Dong Yu, Zhengyou Zhang
We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera.
1 code implementation • 21 Aug 2020 • Samuel N. Cohen, Christoph Reisinger, Sheng Wang
In addition, we show that removing arbitrage from prices data by our repair method can improve model calibration with enhanced robustness and reduced calibration error.
no code implementations • 29 Jul 2020 • Yuan Sun, Sheng Wang, Yunzhuang Shen, Xiao-Dong Li, Andreas T. Ernst, Michael Kirley
In the first phase of our ML-ACO algorithm, an ML model is trained using a set of small problem instances where the optimal solution is known.
1 code implementation • 7 Jul 2020 • Bo Jiang, Sheng Wang, Xiao Wang, Aihua Zheng
Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map.
no code implementations • 3 Jul 2020 • Meng Cao, Hao-Zhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao, Zhifeng Li, Jiebo Luo
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
no code implementations • 25 May 2020 • Sheng Wang, Jiayu Huo, Xi Ouyang, Jifei Che, Xuhua Ren, Zhong Xue, Qian Wang, Jie-Zhi Cheng
However, the image styles of different vendors are very distinctive, and there may exist domain gap among different vendors that could potentially compromise the universal applicability of one deep learning model.
no code implementations • ECCV 2020 • Jinyu Yang, Weizhi An, Sheng Wang, Xinliang Zhu, Chaochao Yan, Junzhou Huang
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation.
Ranked #28 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
2 code implementations • 4 Mar 2020 • Cong Yue, Zhongle Xie, Meihui Zhang, Gang Chen, Beng Chin Ooi, Sheng Wang, Xiaokui Xiao
We establish the worst-case guarantees of each index in terms of these five metrics, and we experimentally evaluate all indexes in a large variety of settings.
Databases
1 code implementation • CVPR 2020 • Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui
Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise.
Ranked #27 on
Semantic Segmentation
on S3DIS
1 code implementation • 1 Oct 2019 • Chaochao Yan, Sheng Wang, Jinyu Yang, Tingyang Xu, Junzhou Huang
We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation.
no code implementations • 26 Apr 2018 • Jinyang Gao, Wei Wang, Meihui Zhang, Gang Chen, H. V. Jagadish, Guoliang Li, Teck Khim Ng, Beng Chin Ooi, Sheng Wang, Jingren Zhou
In many complex applications such as healthcare, subject matter experts (e. g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results.
1 code implementation • PVLDB (The Proceedings of the VLDB Endowment) 2018 • Wei Wang, Sheng Wang, Jinyang Gao, Meihui Zhang, Gang Chen, Teck Khim Ng, Beng Chin Ooi
Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users.
no code implementations • 14 Feb 2018 • Sheng Wang, Tien Tuan Anh Dinh, Qian Lin, Zhongle Xie, Meihui Zhang, Qingchao Cai, Gang Chen, Wanzeng Fu, Beng Chin Ooi, Pingcheng Ruan
By integrating the core application properties into the storage, ForkBase not only delivers high performance but also reduces development effort.
Databases Cryptography and Security Distributed, Parallel, and Cluster Computing
2 code implementations • 10 Jan 2018 • Ruoyu Li, Sheng Wang, Feiyun Zhu, Junzhou Huang
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks.
no code implementations • 28 Aug 2017 • Sheng Wang, Zhen Li, Yizhou Yu, Jinbo Xu
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.
no code implementations • 17 Aug 2017 • Feiyun Zhu, Xinliang Zhu, Sheng Wang, Jiawen Yao, Junzhou Huang
In the critic updating, the capped-$\ell_{2}$ norm is used to measure the approximation error, which prevents outliers from dominating our objective.
no code implementations • 24 Apr 2017 • Zhen Li, Sheng Wang, Yizhou Yu, Jinbo Xu
Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).
1 code implementation • 2 Sep 2016 • Sheng Wang, Siqi Sun, Zhen Li, Renyu Zhang, Jinbo Xu
Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0. 5.
no code implementations • 25 Mar 2016 • Wei Wang, Gang Chen, Haibo Chen, Tien Tuan Anh Dinh, Jinyang Gao, Beng Chin Ooi, Kian-Lee Tan, Sheng Wang
The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets.
1 code implementation • 2 Dec 2015 • Sheng Wang, Jian Peng, Jianzhu Ma, Jinbo Xu
Protein secondary structure (SS) prediction is important for studying protein structure and function.
Ranked #1 on
Protein Secondary Structure Prediction
on CullPDB
no code implementations • 17 Nov 2015 • Sheng Wang, Siqi Sun, Jinbo Xu
Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also have similar performance as the other two training methods on the solvent accessibility prediction problem which has three equally-distributed labels.
1 code implementation • 12 Nov 2015 • Wu-Jun Li, Sheng Wang, Wang-Cheng Kang
For another common application scenario with pairwise labels, there have not existed methods for simultaneous feature learning and hash-code learning.
no code implementations • 12 Jan 2014 • Jianzhu Ma, Sheng Wang, Zhiyong Wang, Jinbo Xu
A sequence profile is usually represented as a position-specific scoring matrix (PSSM) or an HMM (Hidden Markov Model) and accordingly PSSM-PSSM or HMM-HMM comparison is used for homolog detection.
no code implementations • 10 Dec 2013 • Jianzhu Ma, Sheng Wang, Zhiyong Wang, Jinbo Xu
To further improve the accuracy of the estimated precision matrices, we employ a supervised learning method to predict contact probability from a variety of evolutionary and non-evolutionary information and then incorporate the predicted probability as prior into our GGL framework.