Publications (45)
The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems
Weinan E, Bing Yu
We propose a deep learning based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations. T…
On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
Bing Yu, Ke Sun, He Wang +2
The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it…
No dialgebra has Gelfand-Kirillov dimension strictly between 1 and 2
Zerui Zhang, Yuqun Chen, Bing Yu
The Gelfand-Kirillov dimension measures the asymptotic growth rate of algebras. For every associative dialgebra , the quotient $\mathcal{A}_\mathcal{D}:=\mathcal{D}/\m…
Polygamy relation of quantum correlations with equality
Zhi-Xiang Jin, Bing Yu, Xue-Na Zhu +2
We provide a generalized definition of polygamy relations for any quantum correlation measures. Instead of the usual polygamy inequality, a polygamy relation with equality is given…
Near-Optimal Variance-Based Uncertainty Relations
Yunlong Xiao, Naihuan Jing, Bing Yu +2
Learning physical properties of a quantum system is essential for the developments of quantum technologies. However, Heisenberg's uncertainty principle constrains the potential kno…
Anatomy Aware Cascade Network: Bridging Epistemic Uncertainty and Geometric Manifold for 3D Tooth Segmentation
Bing Yu, Liu Shi, Haitao Wang +4
Accurate three-dimensional (3D) tooth segmentation from Cone-Beam Computed Tomography (CBCT) is a prerequisite for digital dental workflows. However, achieving high-fidelity segmen…
Reusability of Quantum Catalysts
Haitao Ma, Yantong Li, Yingchun Kang +4
Quantum catalysts enable transformations that otherwise would be forbidden, offering a pathway to surpass conventional limits in quantum information processing. Among them, embezzl…
Zeolitic Imidazolate Framework-8 offers an anti-inflammatory and antifungal method in the treatment of Aspergillus fungus keratitis in vitro and in vivo
Xueyun Fu, Xue Tian, Jing Lin +10
Background: Fungal keratitis is a serious blinding eye disease. Traditional drugs used to treat fungal keratitis commonly have the disadvantages of low bioavailability, poor disper…
Nonlocal advantage of quantum imaginarity in Schwarzchild spacetime
Bing Yu, Xiao-Yong Yang, Xiaoli Hu +2
Black hole spacetimes provide a natural setting for quantum systems in curved spacetime, where effects such as Hawking radiation arise from event horizons. In this work, we investi…
Physics-informed DeepCT: Sinogram Wavelet Decomposition Meets Masked Diffusion
Zekun Zhou, Tan Liu, Bing Yu +3
Diffusion model shows remarkable potential on sparse-view computed tomography (SVCT) reconstruction. However, when a network is trained on a limited sample space, its generalizatio…
Deep learning for automated detection of breast cancer in deep ultraviolet fluorescence images with diffusion probabilistic model
Sepehr Salem Ghahfarokhi, Tyrell To, Julie Jorns +3
Data limitation is a significant challenge in applying deep learning to medical images. Recently, the diffusion probabilistic model (DPM) has shown the potential to generate high-q…
A two-step backward compatible fullband speech enhancement system
Xu Zhang, Lianwu Chen, Xiguang Zheng +4
Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fu…
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
Bing Yu, Haoteng Yin, Zhanxing Zhu
Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy…
Load Balanced GANs for Multi-view Face Image Synthesis
Jie Cao, Yibo Hu, Bing Yu +2
Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion. Producing photo-realistic and identity preserving multi-…
Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
Pouya Afshin, David Helminiak, Tianling Niu +4
Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rap…
Smartphone microendoscopy for high resolution fluorescence imaging
Xiangqian Hong, Vivek K. Nagarajan, Dale H. Mugler +1
High resolution optical endoscopes are increasingly used in diagnosis of various medical conditions of internal organs, such as the gastrointestinal tracts, but they are too expens…
SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM
Xiaojiang Zhang, Jinghui Wang, Zifei Cheng +14
Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capab…
Computing solution landscape of nonlinear space-fractional problems via fast approximation algorithm
Bing Yu, Lei Zhang, Pingwen Zhang +1
The nonlinear space-fractional problems often allow multiple stationary solutions, which can be much more complicated than the corresponding integer-order problems. In this paper,…
KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
Guochen Yu, Runqiang Han, Chenglin Xu +7
This paper presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a…
DeepRepair: Style-Guided Repairing for DNNs in the Real-world Operational Environment
Bing Yu, Hua Qi, Qing Guo +4
Deep neural networks (DNNs) are being widely applied for various real-world applications across domains due to their high performance (e.g., high accuracy on image classification).…
3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
Bing Yu, Mengzhang Li, Jiyong Zhang +1
Spatio-temporal prediction plays an important role in many application areas especially in traffic domain. However, due to complicated spatio-temporal dependency and high non-linea…
Tangent-Normal Adversarial Regularization for Semi-supervised Learning
Bing Yu, Jingfeng Wu, Jinwen Ma +1
Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual advers…
Genuinely nonlocal sets with smallest cardinality
Zong-Xing Xiong, Mao-Sheng Li, Bing Yu +2
Recently, there is growing interest in the study of genuine nonlocality, which serves to explore the local accessability of global information encoded in orthogonal multipartite qu…
SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling
Jinghui Wang, Shaojie Wang, Yinghan Cui +24
We introduce SeamlessFlow, a server based reinforcement learning (RL) framework that addresses two core challenges in industrial scale RL: (1) decoupling RL training from the compl…
KAT-V1: Kwai-AutoThink Technical Report
Zizheng Zhan, Ken Deng, Huaixi Tang +27
We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks, where an automatic thinkin…
Multi-scale temporal-frequency attention for music source separation
Lianwu Chen, Xiguang Zheng, Chen Zhang +2
In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS). Although previous methods have addre…
Deep-learning based numerical BSDE method for barrier options
Bing Yu, Xiaojing Xing, Agus Sudjianto
As is known, an option price is a solution to a certain partial differential equation (PDE) with terminal conditions (payoff functions). There is a close association between the so…
Solution landscapes of the diblock copolymer-homopolymer model under two-dimensional confinement
Zhen Xu, Yucen Han, Jianyuan Yin +3
We investigate the solution landscapes of the confined diblock copolymer and homopolymer in two-dimensional domain by using the extended Ohta--Kawasaki model. The projected saddle…
Quantum discord of X-states as optimization of one variable function
Naihuan Jing, Bing Yu
We solve the quantum discord completely as an optimization of certain one variable function for arbitrary two qubit X state. Exact solutions of the quantum discord are obtained for…
ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
Bing Yu, Haoteng Yin, Zhanxing Zhu
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is…
On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks
Bing Yu, Junzhao Zhang, Zhanxing Zhu
Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works wel…
Super quantum discord for general two qubit X states
Naihuan Jing, Bing Yu
The exact solutions of the super quantum discord are derived for general two qubit X states in terms of a one-variable function. Several exact solutions of the super quantum discor…
Enhanced quantum channel uncertainty relations by skew information
Xiaoli Hu, Naihong Hu, Bing Yu +1
By revisiting the mathematical foundation of the uncertainty relation, skew information-based uncertainty sequences are developed for any two quantum channels. A reinforced version…
Solution landscape of reaction-diffusion systems reveals a nonlinear mechanism and spatial robustness of pattern formation
Shuonan Wu, Bing Yu, Yuhai Tu +1
Spontaneous pattern formation in homogeneous systems is ubiquitous in nature. Although Turing demonstrated that spatial patterns can emerge in reaction-diffusion (RD) systems when…
MLPerf Inference Benchmark
Vijay Janapa Reddi, Christine Cheng, David Kanter +44
Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organization…
BAE-Net: A Low complexity and high fidelity Bandwidth-Adaptive neural network for speech super-resolution
Guochen Yu, Xiguang Zheng, Nan Li +6
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches prima…
Searching the solution landscape by generalized high-index saddle dynamics
Jianyuan Yin, Bing Yu, Lei Zhang
We introduce a generalized numerical algorithm to construct the solution landscape, which is a pathway map consisting of all stationary points and their connections. Based on the h…
Strong unitary uncertainty relations
Bing Yu, Naihuan Jing, Xianqing Li-Jost
In this paper we provide a new set of uncertainty principles for unitary operators using a sequence of inequalities with the help of the geometric-arithmetic mean inequality. As th…
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Qing Guo, Felix Juefei-Xu, Xiaofei Xie +5
The state-of-the-art deep neural networks (DNNs) are vulnerable against adversarial examples with additive random-like noise perturbations. While such examples are hardly found in…
Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
Ke Sun, Bing Yu, Zhouchen Lin +1
Regularization plays a crucial role in machine learning models, especially for deep neural networks. The existing regularization techniques mainly rely on the i.i.d. assumption and…
Breast Cancer Classification in Deep Ultraviolet Fluorescence Images Using a Patch-Level Vision Transformer Framework
Pouya Afshin, David Helminiak, Tongtong Lu +5
Breast-conserving surgery (BCS) aims to completely remove malignant lesions while maximizing healthy tissue preservation. Intraoperative margin assessment is essential to achieve a…
Distribution of spin correlation strengths in multipartite systems
Bing Yu, Naihuan Jing, Xianqing Li-Jost
For a two-qubit state the isotropic strength measures the degree of isotropic spin correlation. The concept of isotropic strength is generalized to multipartite qudit systems, and…
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
Zhanxing Zhu, Jingfeng Wu, Bing Yu +2
Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general for…
Clinical Feasibility of Low-Magnification Fluorescence Imaging for Breast Cancer Margin Detection Using Texture Analysis and Deep Learning
Pouya Afshin, Tianling Niu, Tongtong Lu +6
High-resolution images of unprocessed surgical breast tissue can be obtained using microscopy with ultraviolet surface excitation (MUSE). This technique is considered a promising m…
Basis-independent Coherence and its Applications
Zhi-Xiang Jin, Yuan-Hong Tao, Bing Yu +1
In the quantitative theory of quantum coherence, the amount of coherence for given states can be meaningfully discussed only when referring to a preferred basis. One of the objecti…