Search Results for author: Sheng Wang

Found 140 papers, 68 papers with code

Textomics: A Dataset for Genomics Data Summary Generation

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.

Pathway2Text: Dataset and Method for Biomedical Pathway Description Generation

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.

named-entity-recognition Named Entity Recognition +2

Dynamic allocation: extremes, tail dependence, and regime Shifts

no code implementations14 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.

FedAPM: Federated Learning via ADMM with Partial Model Personalization

1 code implementation5 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.)

Federated Learning

HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning

no code implementations21 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.

Mamba Motion Forecasting +2

ReactDiff: Latent Diffusion for Facial Reaction Generation

1 code implementation20 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.

Decoder Diversity

UniCAD: Efficient and Extendable Architecture for Multi-Task Computer-Aided Diagnosis System

no code implementations14 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.

Diagnostic

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation

1 code implementation27 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.

RAG Retrieval +2

RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation

no code implementations25 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.

DAST: Difficulty-Aware Self-Training on Large Language Models

no code implementations12 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.

Data Augmentation

GrInAdapt: Scaling Retinal Vessel Structural Map Segmentation Through Grounding, Integrating and Adapting Multi-device, Multi-site, and Multi-modal Fundus Domains

no code implementations8 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.

Decision Making Domain Adaptation +3

Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis

no code implementations3 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).

Diagnostic

MITracker: Multi-View Integration for Visual Object Tracking

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.

Object Visual Object Tracking

Group Ligands Docking to Protein Pockets

no code implementations25 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.

Blind Docking

UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models

1 code implementation16 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.

Question Answering

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

1 code implementation9 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.

Visual Question Answering (VQA)

On Simplifying Large-Scale Spatial Vectors: Fast, Memory-Efficient, and Cost-Predictable k-means

1 code implementation3 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.

An Integral Equation in Portfolio Selection with Time-Inconsistent Preferences

no code implementations3 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.

LHPF: Look back the History and Plan for the Future in Autonomous Driving

no code implementations26 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.

Autonomous Driving Imitation Learning

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

1 code implementation26 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.

CropCraft: Inverse Procedural Modeling for 3D Reconstruction of Crop Plants

no code implementations14 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.

3D Reconstruction Bayesian Optimization

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration

no code implementations22 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.

Math

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom

no code implementations18 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.

Visual Reasoning

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

1 code implementation16 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.

Diagnostic Hallucination +4

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

1 code implementation16 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.

Unleashing the Power of LLMs as Multi-Modal Encoders for Text and Graph-Structured Data

no code implementations15 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.

Contrastive Learning Data Ablation +3

QSpec: Speculative Decoding with Complementary Quantization Schemes

no code implementations15 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.

Quantization

MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards

no code implementations1 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.

Mixture-of-Experts

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models

1 code implementation29 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.

Benchmarking General Knowledge

OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation

no code implementations20 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.

Contrastive Learning Diagnostic +1

Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise

no code implementations29 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.

Privacy Preserving

On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness

1 code implementation23 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.

Fairness Federated Learning +1

Panacea: A foundation model for clinical trial search, summarization, design, and recruitment

1 code implementation25 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.

Clinical Knowledge

Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting

no code implementations24 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.

Data Augmentation Dialogue Generation

Efficient k-means with Individual Fairness via Exponential Tilting

no code implementations24 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.

Clustering Fairness

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

1 code implementation16 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.

scientific discovery Survey

BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once

no code implementations21 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).

All Image Segmentation +6

Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening

1 code implementation15 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.

DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving

no code implementations19 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.

Autonomous Driving Diversity +2

MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction

1 code implementation8 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.

Camera Calibration

LoRA Meets Dropout under a Unified Framework

no code implementations25 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.

PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA

1 code implementation24 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.

Two-stage Cytopathological Image Synthesis for Augmenting Cervical Abnormality Screening

no code implementations22 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.

Cell Detection Data Augmentation +2

A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

1 code implementation21 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.

T-Rex: Text-assisted Retrosynthesis Prediction

1 code implementation26 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.

Computational chemistry Prediction +2

Dynamic portfolio selection under generalized disappointment aversion

no code implementations16 Jan 2024 Zongxia Liang, Sheng Wang, Jianming Xia, Fengyi Yuan

This paper addresses the continuous-time portfolio selection problem under generalized disappointment aversion (GDA).

CLIP in Medical Imaging: A Survey

1 code implementation12 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.

Medical Image Analysis Survey

Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis

1 code implementation11 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.

Contrastive Learning Semantic Similarity +1

GDTS: Goal-Guided Diffusion Model with Tree Sampling for Multi-Modal Pedestrian Trajectory Prediction

no code implementations25 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.

Autonomous Driving Denoising +3

Dependency Relationships-Enhanced Attentive Group Recommendation in HINs

no code implementations19 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.

MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis

1 code implementation14 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.

Personalized Federated Learning via ADMM with Moreau Envelope

no code implementations12 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.

Personalized Federated Learning

ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding

no code implementations7 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.

Graph Embedding Link Prediction

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

2 code implementations14 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.

Hallucination In-Context Learning +4

AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentation

1 code implementation2 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.

Anatomy Data Augmentation +5

CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification

1 code implementation12 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.

image-classification Image Classification +2

ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs

1 code implementation25 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.

Diagnostic In-Context Learning +1

Learning Better Contrastive View from Radiologist's Gaze

1 code implementation15 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.

Contrastive Learning Data Augmentation

A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment

no code implementations14 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.

Decoder

Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion

no code implementations16 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.

Super-Resolution

DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task

1 code implementation3 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.

BLIAM: Literature-based Data Synthesis for Synergistic Drug Combination Prediction

no code implementations14 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.

Data Augmentation Language Modeling +2

ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models

1 code implementation14 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.

Decision Making Lesion Segmentation +1

RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

1 code implementation13 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.

Contrastive Learning Image Segmentation +3

Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation

1 code implementation26 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.

One-Shot Segmentation Segmentation

Retrieval augmentation of large language models for lay language generation

1 code implementation7 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.

Explanation Generation Retrieval +1

Modern Tontine with Transaction Costs

no code implementations20 Sep 2022 Lin He, Zongxia Liang, Sheng Wang

The wealth of the retiree is divided into a bequest account and a tontine account.

POPDx: An Automated Framework for Patient Phenotyping across 392,246 Individuals in the UK Biobank Study

1 code implementation23 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.

Patient Phenotyping

Brain-Aware Replacements for Supervised Contrastive Learning in Detection of Alzheimer's Disease

1 code implementation11 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.

Contrastive Learning Data Augmentation

A fully differentiable ligand pose optimization framework guided by deep learning and traditional scoring functions

1 code implementation27 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.

Drug Design

Graph-in-Graph Network for Automatic Gene Ontology Description Generation

no code implementations10 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.

Sentence

Hedging option books using neural-SDE market models

1 code implementation31 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.

Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning

no code implementations25 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.

Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing

no code implementations23 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.

Computational Efficiency Super-Resolution

ProTranslator: zero-shot protein function prediction using textual description

no code implementations20 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.

Machine Translation Multi-Label Classification +3

Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis

1 code implementation6 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.

Medical Image Analysis

Estimating risks of option books using neural-SDE market models

1 code implementation15 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.

Adaptive Transfer Learning for Plant Phenotyping

no code implementations14 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.

BIG-bench Machine Learning GPR +3

SurvODE: Extrapolating Gene Expression Distribution for Early Cancer Identification

no code implementations30 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.

Irregular Time Series Time Series +1

Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning

1 code implementation21 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.

Contrastive Learning Diversity +3

GraphPrompt: Graph-Based Prompt Templates for Biomedical Synonym Prediction

1 code implementation13 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.

Prediction

Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion

1 code implementation25 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.

Leveraging the Cell Ontology to classify unseen cell types

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.

Combined Trojan Y Chromosome Strategy and Sterile Insect Technique to Eliminate Mosquitoes: Modelling and Analysis

no code implementations17 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.

UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing

no code implementations12 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.

3D Reconstruction Face Reenactment +3

Shallow Feature Matters for Weakly Supervised Object Localization

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.

Object Pseudo Label +1

DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

1 code implementation21 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.

Collaborative Filtering Graph Attention +1

Arbitrage-free neural-SDE market models

1 code implementation24 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.

Time Series Time Series Analysis

EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models

no code implementations11 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.

Denoising Protein Folding +1

Towards Accurate Active Camera Localization

1 code implementation8 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.

Camera Localization Camera Pose Estimation +2

On the Efficiency of K-Means Clustering: Evaluation, Optimization, and Algorithm Selection

no code implementations13 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.

Clustering

High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies

1 code implementation12 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.

Vocal Bursts Intensity Prediction

Detecting and repairing arbitrage in traded option prices

1 code implementation21 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.

Density Estimation

Boosting Ant Colony Optimization via Solution Prediction and Machine Learning

no code implementations29 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.

BIG-bench Machine Learning Combinatorial Optimization

STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification

1 code implementation7 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.

Person Re-Identification

Task-agnostic Temporally Consistent Facial Video Editing

no code implementations3 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.

3D Reconstruction Video Editing

mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography

no code implementations25 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.

Deep Learning Lesion Detection +1

Analysis of Indexing Structures for Immutable Data

2 code implementations4 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

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling

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.

3D Point Cloud Classification Semantic Segmentation

Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation

1 code implementation1 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.

valid

PANDA: Facilitating Usable AI Development

no code implementations26 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.

Autonomous Driving

Rafiki: Machine Learning as an Analytics Service System

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.

BIG-bench Machine Learning Hyperparameter Optimization +3

ForkBase: An Efficient Storage Engine for Blockchain and Forkable Applications

no code implementations14 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

Adaptive Graph Convolutional Neural Networks

2 code implementations10 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.

Metric Learning

Folding membrane proteins by deep transfer learning

no code implementations28 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.

Transfer Learning

Robust Contextual Bandit via the Capped-$\ell_{2}$ norm

no code implementations17 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.

Decision Making

Predicting membrane protein contacts from non-membrane proteins by deep transfer learning

no code implementations24 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).

Prediction Transfer Learning

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

1 code implementation2 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.

Prediction Protein Folding

Deep Learning At Scale and At Ease

no code implementations25 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.

Deep Learning image-classification +1

AUC-maximized Deep Convolutional Neural Fields for Sequence Labeling

no code implementations17 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.

Prediction

Feature Learning based Deep Supervised Hashing with Pairwise Labels

1 code implementation12 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.

Deep Hashing Image Retrieval +1

MRFalign: Protein Homology Detection through Alignment of Markov Random Fields

no code implementations12 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.

Multiple Sequence Alignment

Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learning

no code implementations10 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.

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