Publications (56)
GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
Tianhao Chen, Xin Xu, Zijing Liu +12
Modern Large Language Models, such as the LLaMA, Qwen and DeepSeek series, predominantly adopt the Pre-LayerNorm (Pre-LN) Transformer architecture. While being stable during pretra…
UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models
Xin Xu, Jiaxin Zhang, Tianhao Chen +3
Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However,…
LSMM: A statistical approach to integrating functional annotations with genome-wide association studies
Jingsi Ming, Mingwei Dai, Mingxuan Cai +3
Thousands of risk variants underlying complex phenotypes (quantitative traits and diseases) have been identified in genome-wide association studies (GWAS). However, there are still…
Prediction analysis for microbiome sequencing data
Tao Wang, Can Yang, Hongyu Zhao
One primary goal of human microbiome studies is to predict host traits based on human microbiota. However, microbial community sequencing data present significant challenges to the…
Tensor Completion Leveraging Graph Information: A Dynamic Regularization Approach with Statistical Guarantees
Kaidong Wang, Qianxin Yi, Yao Wang +3
We consider the problem of tensor completion with graphs serving as side information to represent interrelationships among variables. Existing approaches suffer from several limita…
MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Information
Zhiwei Wang, Fa Zhang, Cong Zheng +3
In various practical situations, matrix factorization methods suffer from poor data quality, such as high data sparsity and low signal-to-noise ratio (SNR). Here, we consider a mat…
Reconstructing Close Human Interactions from Multiple Views
Qing Shuai, Zhiyuan Yu, Zhize Zhou +4
This paper addresses the challenging task of reconstructing the poses of multiple individuals engaged in close interactions, captured by multiple calibrated cameras. The difficulty…
Option Dynamic Hedging Using Reinforcement Learning
Cong Zheng, Jiafa He, Can Yang
This work focuses on the dynamic hedging of financial derivatives, where a reinforcement learning algorithm is designed to minimize the variance of the delta hedging process. In co…
Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
Jiafa He, Chengwei Pan, Can Yang +4
Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods based on convolutional neural networks (CNNs) may suffer from d…
Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model
Fengtao Zhou, Yingxue Xu, Zhengyu Zhang +20
Comprehensive molecular profiling is essential for modern precision oncology but remains hindered by prohibitive costs, specimen exhaustion, and protracted turnaround times. While…
Low-Rank Modeling and Its Applications in Image Analysis
Xiaowei Zhou, Can Yang, Hongyu Zhao +1
Low-rank modeling generally refers to a class of methods that solve problems by representing variables of interest as low-rank matrices. It has achieved great success in various fi…
Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation
Xiaowei Zhou, Can Yang, Weichuan Yu
Object detection is a fundamental step for automated video analysis in many vision applications. Object detection in a video is usually performed by object detectors or background…
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Xin Xu, Clive Bai, Kai Yang +7
Large-scale verifiable prompts underpin the success of Reinforcement Learning with Verifiable Rewards (RLVR), but they contain many uninformative examples and are costly to expand…
Can LLMs Solve longer Math Word Problems Better?
Xin Xu, Tong Xiao, Zitong Chao +3
Math Word Problems (MWPs) play a vital role in assessing the capabilities of Large Language Models (LLMs), yet current research primarily focuses on questions with concise contexts…
On the Convergence of the EM Algorithm: A Data-Adaptive Analysis
Chong Wu, Can Yang, Hongyu Zhao +1
The Expectation-Maximization (EM) algorithm is an iterative method to maximize the log-likelihood function for parameter estimation. Previous works on the convergence analysis of t…
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Xin Xu, Cliveb AI, Kai Yang +4
Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computation…
A Deployment-Friendly Foundational Framework for Efficient Computational Pathology
Yu Cai, Cheng Jin, Jiabo Ma +25
Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image analysis. Here, we present LitePath, a dep…
BOOST: A fast approach to detecting gene-gene interactions in genome-wide case-control studies
Xiang Wan, Can Yang, Qiang Yang +4
Gene-gene interactions have long been recognized to be fundamentally important to understand genetic causes of complex disease traits. At present, identifying gene-gene interaction…
PEGNet: A Physics-Embedded Graph Network for Long-Term Stable Multiphysics Simulation
Can Yang, Zhenzhong Wang, Junyuan Liu +2
Accurate and efficient simulations of physical phenomena governed by partial differential equations (PDEs) are important for scientific and engineering progress. While traditional…
Optimal Execution Using Reinforcement Learning
Cong Zheng, Jiafa He, Can Yang
This work is about optimal order execution, where a large order is split into several small orders to maximize the implementation shortfall. Based on the diversity of cryptocurrenc…
A Penalized Multi-trait Mixed Model for Association Mapping in Pedigree-based GWAS
Jin Liu, Can Yang, Xingjie Shi +4
In genome-wide association studies (GWAS), penalization is an important approach for identifying genetic markers associated with trait while mixed model is successful in accounting…
Can We Verify Step by Step for Incorrect Answer Detection?
Xin Xu, Shizhe Diao, Can Yang +1
Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed vario…
Modx: Binary Level Partial Imported Third-Party Library Detection through Program Modularization and Semantic Matching
Can Yang, Zhengzi Xu, Hongxu Chen +3
With the rapid growth of software, using third-party libraries (TPLs) has become increasingly popular. The prosperity of the library usage has provided the software engineers with…
BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data
Min Zhou, Mingwei Dai, Yuan Yao +3
Detecting interaction effects among predictors on the response variable is a crucial step in various applications. In this paper, we first propose a simple method for sure screenin…
VIMCO: Variational Inference for Multiple Correlated Outcomes in Genome-wide Association Studies
Xingjie Shi, Yuling Jiao, Yi Yang +4
In Genome-Wide Association Studies (GWAS) where multiple correlated traits have been measured on participants, a joint analysis strategy, whereby the traits are analyzed jointly, c…
The Exploration of Error Bounds in Classification with Noisy Labels
Haixia Liu, Boxiao Li, Can Yang +1
Numerous studies have shown that label noise can lead to poor generalization performance, negatively affecting classification accuracy. Therefore, understanding the effectiveness o…
Distilled Prompt Learning for Incomplete Multimodal Survival Prediction
Yingxue Xu, Fengtao Zhou, Chenyu Zhao +3
The integration of multimodal data including pathology images and gene profiles is widely applied in precise survival prediction. Despite recent advances in multimodal survival mod…
Progressive Residual Warmup for Language Model Pretraining
Tianhao Chen, Xin Xu, Lu Yin +4
Transformer architectures serve as the backbone for most modern Large Language Models, therefore their pretraining stability and convergence speed are of central concern. Motivated…
LPG: a four-groups probabilistic approach to leveraging pleiotropy in genome-wide association studies
Yi Yang, Mingwei Dai, Jian Huang +4
To date, genome-wide association studies (GWAS) have successfully identified tens of thousands of genetic variants among a variety of traits/diseases, shedding a light on the genet…
Mathematical design of a novel gesture-based instruction/input device using wave detection
Hongyu Liu, Yuliang Wang, Can Yang
In this paper, we present a conceptual design of a novel gesture-based instruction/input device using wave detection. The device recogonizes/detects gestures from a person and base…
On the Bound of Cumulative Return in Trading Series and the Verification Using Technical Trading Rules
Can Yang, Junjie Zhai, Helong Li
Although there is a wide use of technical trading rules in stock markets, the profitability of them still remains controversial. This paper first presents and proves the upper boun…
HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers
Zhiyuan Yu, Zhe Li, Hujun Bao +2
3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or…
REMI: Regression with marginal information and its application in genome-wide association studies
Jian Huang, Yuling Jiao, Jin Liu +1
In this study, we consider the problem of variable selection and estimation in high-dimensional linear regression models when the complete data are not accessible, but only certain…
GPA: A statistical approach to prioritizing GWAS results by integrating pleiotropy information and annotation data
Dongjun Chung, Can Yang, Cong Li +2
Genome-wide association studies (GWAS) suggests that a complex disease is typically affected by many genetic variants with small or moderate effects. Identification of these risk v…
Wasserstein-Wasserstein Auto-Encoders
Shunkang Zhang, Yuan Gao, Yuling Jiao +3
To address the challenges in learning deep generative models (e.g.,the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we pr…
A Coding-free Software Framework of Developing Web Data Management Systems
Can Yang, Shiying Pan, Runmin Li +2
More and more enterprises recently intend to deploy data management systems in the cloud. Due to the professionalism of software development, it has still been difficult for non-pr…
Integrating Tick-level Data and Periodical Signal for High-frequency Market Making
Jiafa He, Cong Zheng, Can Yang
We focus on the problem of market making in high-frequency trading. Market making is a critical function in financial markets that involves providing liquidity by buying and sellin…
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
Xin Xu, Qiyun Xu, Tong Xiao +6
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks, particularly in mathematics. However, the domain of physics reasoning pre…
The Research and Optimization of Parallel Finite Element Algorithm based on MiniFE
Meng Wu, Can Yang, Taoran Xiang +1
Finite element method (FEM) is one of the most important numerical methods in modern engineering design and analysis. Since traditional serial FEM is difficult to solve large FE pr…
Flexible and Accurate Methods for Estimation and Inference of Gaussian Graphical Models with Applications
Yueqi Qian, Xianghong Hu, Can Yang
The Gaussian graphical model (GGM) incorporates an undirected graph to represent the conditional dependence between variables, with the precision matrix encoding partial correlatio…
BIVAS: A scalable Bayesian method for bi-level variable selection with applications
Mingxuan Cai, Mingwei Dai, Jingsi Ming +3
In this paper, we consider a Bayesian bi-level variable selection problem in high-dimensional regressions. In many practical situations, it is natural to assign group membership to…
Improving genetic risk prediction by leveraging pleiotropy
Cong Li, Can Yang, Joel Gelernter +1
An important task of human genetics studies is to accurately predict disease risks in individuals based on genetic markers, which allows for identifying individuals at high disease…
Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
Xin Xu, Tianhao Chen, Fan Zhang +11
While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and re…
Bayesian Weighted Mendelian Randomization for Causal Inference based on Summary Statistics
Jia Zhao, Jingsi Ming, Xianghong Hu +3
The results from Genome-Wide Association Studies (GWAS) on thousands of phenotypes provide an unprecedented opportunity to infer the causal effect of one phenotype (exposure) on an…
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
Wenfei Cao, Yao Wang, Jian Sun +4
Background subtraction has been a fundamental and widely studied task in video analysis, with a wide range of applications in video surveillance, teleconferencing and 3D modeling.…
High-dimensional genome-wide association study and misspecified mixed model analysis
Jiming Jiang, Cong Li, Debashis Paul +2
We study behavior of the restricted maximum likelihood (REML) estimator under a misspecified linear mixed model (LMM) that has received much attention in recent gnome-wide associat…
Joint Analysis of Individual-level and Summary-level GWAS Data by Leveraging Pleiotropy
Mingwei Dai, Xiang Wan, Hao Peng +5
A large number of recent genome-wide association studies (GWASs) for complex phenotypes confirm the early conjecture for polygenicity, suggesting the presence of large number of va…
Deep Generative Learning via Variational Gradient Flow
Yuan Gao, Yuling Jiao, Yang Wang +3
We propose a general framework to learn deep generative models via \textbf{V}ariational \textbf{Gr}adient Fl\textbf{ow} (VGrow) on probability spaces. The evolving distribution tha…
StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance
Yunpeng Gong, Sihan Lan, Can Yang +2
Symbolic regression aims to find interpretable analytical expressions by searching over mathematical formula spaces to capture underlying system behavior, particularly in scientifi…
Deep Generative Learning via Schrödinger Bridge
Gefei Wang, Yuling Jiao, Qian Xu +2
We propose to learn a generative model via entropy interpolation with a Schrödinger Bridge. The generative learning task can be formulated as interpolating between a reference dis…
Exploring the genetic patterns of complex diseases via the integrative genome-wide approach
Ben Teng, Can Yang, Jiming Liu +2
Motivation: Genome-wide association studies (GWASs), which assay more than a million single nucleotide polymorphisms (SNPs) in thousands of individuals, have been widely used to id…
SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation
Hongrui Wang, Fan Zhang, Zhiyuan Yu +4
Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attri…
A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations
Andong Tan, Shuyu Dai, Jinglu Wang +7
Clinical practice guidelines (CPGs) play a pivotal role in ensuring evidence-based decision-making and improving patient outcomes. While Large Language Models (LLMs) are increasing…
A Unified Primal Dual Active Set Algorithm for Nonconvex Sparse Recovery
Jian Huang, Yuling Jiao, Bangti Jin +3
In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations. We develop a novel algorithm of primal-dual active set type for…
Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns
Jianming Lv, Weihang Chen, Qing Li +1
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained mod…
On Joint Estimation of Gaussian Graphical Models for Spatial and Temporal Data
Zhixiang Lin, Tao Wang, Can Yang +1
In this paper, we first propose a Bayesian neighborhood selection method to estimate Gaussian Graphical Models (GGMs). We show the graph selection consistency of this method in the…