Author name cluster

Li Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

1 author row

EAAI Journal 2026 Journal Article

ScholarLens: Tracking the growing penetration of Large Language Models in scholarly writing and peer review

Li Zhou
Ruijie Zhang
Xunlian Dai
Daniel Hershcovich
Haizhou Li

Although the widespread use of Large Language Models (LLMs) brings convenience, it also raises concerns about the credibility of academic research and scholarly processes. To better understand the extent and characteristics of LLM use in scholarly writing and peer review, the penetration of LLMs across academic workflows is evaluated from multiple perspectives and dimensions, providing compelling evidence of their growing influence. A framework consisting of two components is proposed: ScholarLens, a curated dataset of human-written and LLM-generated content across scholarly writing and peer review for multi-perspective evaluation, and LLMetrica, a tool for assessing LLM penetration using rule-based metrics and model-based detectors for multi-dimensional evaluation. The effectiveness of LLMetrica is demonstrated through experiments, revealing the increasing role of LLMs in scholarly processes. These findings emphasize the need for transparency, accountability, and ethical practices in the use of LLMs to maintain academic credibility.

Details DOI

EAAI Journal 2025 Journal Article

A swarm intelligence framework in complex environments: Optimizing area coverage guidance and control

Jiahao Sun
Sen Han
Shifeng Ding
Lingxiao Yan
Fang Li
Li Zhou

With the development of artificial intelligence technology, deploying multiple Unmanned Surface Vehicles (multi-USVs) enhances efficiency and safety but introduces challenges including environmental disturbances, regulatory compliance (COLREGs), and collision avoidance. This study proposes an integrated framework addressing these through the Theta-Integrated Divide Areas Trajectory Planning (TDAP) algorithm for dynamic-constrained coverage planning, Nonlinear Model Predictive Control (NMPC) for robust trajectory tracking under wind/current variations, and a Dynamic Theta* (D-Theta*) algorithm with virtual obstacle-lines for COLREGs-compliant collision avoidance—including emergency evasion when target ships fail to act. Simulations demonstrate high coverage efficiency, precise trajectory tracking, and consistently safe navigation across diverse scenarios. The framework significantly improves multi-USV coordination and safety in complex environments, enabling reliable autonomous operations without direct human intervention.

Details DOI

EAAI Journal 2025 Journal Article

Efficient real-time instance segmentation of garment for intelligent robot tie-dye based on you only look once version 11 network

Difei Feng
Qihong Zhou
Lei Xiao
Kunfeng Ge
Hangzhou Ma
Li Zhou

Tie-dye, as an intangible cultural heritage with a long history, has gained global popularity due to its unique artistic value and versatile craftsmanship. However, its reliance on manual operation leads to low production efficiency and inconsistent quality. To address this, we propose an improved You Only Look Once version-11 (YOLOv11) instance segmentation model, Garment-YOLO, to efficiently segment the garment regions of robotic tie-dye by artificial intelligence technology. First, the C3k2_DynamicMixFormer (C3k2_DMF) module introduces dynamic kernel weight selection mechanism and multi-scale fusion to effectively balance local details and global information. Meanwhile, the Dual-Cross Recalibration Feature Pyramid Network (DCR-FPN) is proposed to enhance the detail preservation of edge region by selectively aggregating semantic and boundary information. Furthermore, the Superior-Head replaces depthwise convolution (DWConv) with part convolution (PConv), significantly reducing model complexity while maintaining performance. Experimental results demonstrate that Garment-YOLO achieves 167. 4 frames per second (FPS) and maintains an optimal trade-off between inference speed and segmentation accuracy, reaching 91. 9 % mean average precision (mAP)50–95 (Box), 91. 5 % mAP50-95 (Mask). To further validate its practical performance, we conducted a 72-h production-line comparison, showing that compared to the baseline, we increase the product qualification rate by 24. 6 %, reduce dye waste by 19. 4 %, and increase the total production by 52. 5 % compared to manual tie-dye. This study not only provides a feasible solution for the intelligent transformation of traditional tie-dye but also contributes to the preservation and development of this intangible cultural heritage. The code will be released on GitHub (https: //github. com/fudifu123/GARMENT-YOLO). A video that intuitively introduces our research (https: //www. bilibili. com/video/BV13MgczAEkB).

Details DOI

AAAI Conference 2025 Conference Paper

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model

Xu Yuan
Li Zhou
Zenghui Sun
Zikun Zhou
Jinsong Lan

Large Multimodal Models (LMMs) have significantly progressed by extending large language models. Building on this progress, the latest developments in LMMs demonstrate the ability to generate dense pixel-wise segmentation by integrating segmentation models. Despite the innovations, existing works’ textual responses and segmentation masks remain at the instance level, showing limited ability to perform fine-grained understanding and segmentation even provided with detailed textual cues. To overcome this limitation, we introduce a Multi-Granularity Large Multimodal Model (MGLMM), which is capable of seamlessly adjusting the granularity of Segmentation and Captioning (SegCap) following user instructions, from panoptic SegCap to fine-grained SegCap. We name such a new task Multi-Granularity Segmentation and Captioning (MGSC). Observing the lack of a benchmark for model training and evaluation over the MGSC task, we establish a benchmark with aligned masks and captions in multi-granularity using our customized automated annotation pipeline. This benchmark comprises 10K images and more than 30K image-question pairs. We will release our dataset along with the implementation of our automated dataset annotation pipeline for further research. Besides, we propose a novel unified SegCap data format to unify heterogeneous segmentation datasets; it effectively facilitates learning to associate object concepts with visual features during multi-task training. Extensive experiments demonstrate that our MGLMM excels at tackling more than eight downstream tasks and achieves state-of-the-art performance in MGSC, GCG, image captioning, referring segmentation, multiple/empty segmentation, and reasoning segmentation. The great properties and versatility of MGLMM underscore its potential impact on advancing multimodal research.

PDF Details DOI

JBHI Journal 2025 Journal Article

M-NET: Transforming Single Nucleotide Variations Into Patient Feature Images for the Prediction of Prostate Cancer Metastasis and Identification of Significant Pathways

Li Zhou
Jie Li
Weilong Tan

High-performance prediction of prostate cancer metastasis based on single nucleotide variations remains a challenge. Therefore, we developed a novel biologically informed deep learning framework, named M-NET, for the prediction of prostate cancer metastasis. Within the framework, we transformed single nucleotide variations into patient feature images that are optimal for fitting convolutional neural networks. Moreover, we identified significant pathways associated with the metastatic status. The experimental results showed that M-NET significantly outperformed other comparison methods based on single nucleotide variations, achieving improvements in accuracy, precision, recall, F1-score, area under the receiver operating characteristics curve, and area under the precision-recall curve by 6. 3%, 8. 4%, 5. 1%, 0. 070, 0. 041, and 0. 026, respectively. Furthermore, M-NET identified some important pathways associated with the metastatic status, such as signaling by the hedgehog pathway. In summary, compared with other comparative methods, M-NET exhibited a better performance in the prediction of prostate cancer metastasis.

Details DOI

JBHI Journal 2024 Journal Article

LoMAE: Simple Streamlined Low-Level Masked Autoencoders for Robust, Generalized, and Interpretable Low-Dose CT Denoising

Dayang Wang
Shuo Han
Yongshun Xu
Zhan Wu
Li Zhou
Bahareh Morovati
Hengyong Yu

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In computer vision and natural language processing, masked autoencoders (MAE) have been recognized as a powerful self-pretraining method for transformers, due to their exceptional capability to extract representative features. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective streamlined low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experimental findings show that the proposed LoMAE enhances the denoising capabilities of the transformer and substantially reduce their dependency on high-quality, ground-truth data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. In summary, the proposed LoMAE provides promising solutions to the major issues in LDCT including interpretability, ground truth data dependency, and model robustness/generalizability.

Details DOI

AAAI Conference 2023 Conference Paper

Substructure Aware Graph Neural Networks

DingYi Zeng
Wanlong Liu
Wenyu Chen
Li Zhou
Malu Zhang
Hong Qu

Despite the great achievements of Graph Neural Networks (GNNs) in graph learning, conventional GNNs struggle to break through the upper limit of the expressiveness of first-order Weisfeiler-Leman graph isomorphism test algorithm (1-WL) due to the consistency of the propagation paradigm of GNNs with the 1-WL.Based on the fact that it is easier to distinguish the original graph through subgraphs, we propose a novel framework neural network framework called Substructure Aware Graph Neural Networks (SAGNN) to address these issues. We first propose a Cut subgraph which can be obtained from the original graph by continuously and selectively removing edges. Then we extend the random walk encoding paradigm to the return probability of the rooted node on the subgraph to capture the structural information and use it as a node feature to improve the expressiveness of GNNs. We theoretically prove that our framework is more powerful than 1-WL, and is superior in structure perception. Our extensive experiments demonstrate the effectiveness of our framework, achieving state-of-the-art performance on a variety of well-proven graph tasks, and GNNs equipped with our framework perform flawlessly even in 3-WL failed graphs. Specifically, our framework achieves a maximum performance improvement of 83% compared to the base models and 32% compared to the previous state-of-the-art methods.

PDF Details DOI

TCS Journal 2022 Journal Article

A proof system for disjoint parallel quantum programs

Mingsheng Ying
Li Zhou
Yangjia Li
Yuan Feng

In this paper, we define the operational and denotational semantics of a special class of parallel quantum programs, namely disjoint parallel quantum programs. Based on them, a proof system for reasoning about disjoint parallel quantum programs is developed, which is (relatively) complete even when entanglement between different processes appears in the preconditions and postconditions.

Details DOI

JBHI Journal 2021 Journal Article

Estimating Time to Progression of Chronic Obstructive Pulmonary Disease With Tolerance

Chunlei Tang
Joseph M. Plasek
Xiao Shi
Meihan Wan
Haohan Zhang
Min-Jeoung Kang
Liqin Wang
Sevan M. Dulgarian

We defined tolerance range as the distance of observing similar disease conditions or functional status from the upper to the lower boundaries of a specified time interval. A tolerance range was identified for linear regression and support vector machines to optimize the improvement rate (defined as IR) on accuracy in predicting mortality risk in patients with chronic obstructive pulmonary disease using clinical notes. The corpus includes pulmonary, cardiology, and radiology reports of 15, 500 patients who died between 2011 and 2017. Their performance was compared against a long short-term memory recurrent neural network. The results demonstrate an overall improvement by those basic machine learning approaches after considering an optimal tolerance range: the average IR of linear regression was 90. 1% and the maximum IR of support vector machines was 66. 2%. There was a similitude between the time segments produced by our tolerance algorithms and those produced by the long short-term memory.

Details DOI

AAAI Conference 2021 Conference Paper

Inverse Reinforcement Learning with Natural Language Goals

Li Zhou
Kevin Small

Humans generally use natural language (NL) to communicate task requirements to each other. Ideally, NL should also be usable for communicating goals to autonomous machines (e. g. , robots) to minimize friction in task specification. However, understanding and mapping NL goals to sequences of states and actions is challenging. Specifically, existing work along these lines has encountered difficulty in generalizing learned policies to new NL goals and environments. In this paper, we propose a novel adversarial inverse reinforcement learning algorithm to learn a language-conditioned policy and reward function. To improve generalization of the learned policy and reward function, we use a variational goal generator to relabel trajectories and sample diverse goals during training. Our algorithm outperforms multiple baselines by a large margin on a vision-based NL instruction following dataset (Room-2- Room), demonstrating a promising advance in enabling the use of NL instructions in specifying agent goals.

PDF Details

TCS Journal 2020 Journal Article

Strassen's theorem for quantum couplings

Li Zhou
Shenggang Ying
Nengkun Yu
Mingsheng Ying

Strassen's theorem for probabilistic couplings is a fundamental theorem in probability theory that can be used to bound the probability of an event in a distribution by the probability of an event in another distribution coupled with the first. It has been widely applied in computer science for analysis of random algorithms, machine learning and verification of security and privacy protocols. We extend the coupling techniques in probability theory to quantum systems. A quantum generalisation of the notion of lifting, a coupling under certain constraints, is introduced. Several interesting examples and basic properties of quantum couplings and liftings are presented. Finally, a quantum extension of Strassen's theorem is established.

Details DOI

AAAI Conference 2019 Conference Paper

Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization

Li Yuan
Francis EH Tay
Ping Li
Li Zhou
Jiashi Feng

In this paper, we present a novel unsupervised video summarization model that requires no manual annotation. The proposed model termed Cycle-SUM adopts a new cycleconsistent adversarial LSTM architecture that can effectively maximize the information preserving and compactness of the summary video. It consists of a frame selector and a cycle-consistent learning based evaluator. The selector is a bi-direction LSTM network that learns video representations that embed the long-range relationships among video frames. The evaluator defines a learnable information preserving metric between original video and summary video and “supervises” the selector to identify the most informative frames to form the summary video. In particular, the evaluator is composed of two generative adversarial networks (GANs), in which the forward GAN is learned to reconstruct original video from summary video while the backward GAN learns to invert the processing. The consistency between the output of such cycle learning is adopted as the information preserving metric for video summarization. We demonstrate the close relation between mutual information maximization and such cycle learning procedure. Experiments on two video summarization benchmark datasets validate the state-of-theart performance and superiority of the Cycle-SUM model over previous baselines.

PDF Details

IJCAI Conference 2018 Conference Paper

3D-Aided Deep Pose-Invariant Face Recognition

Jian Zhao
Lin Xiong
Yu Cheng
Yi Cheng
Jianshu Li
Li Zhou
Yan Xu
Jayashree Karlekar

Learning from synthetic faces, though perhaps appealing for high data efficiency, may not bring satisfactory performance due to the distribution discrepancy of the synthetic and real face images. To mitigate this gap, we propose a 3D-Aided Deep Pose-Invariant Face Recognition Model (3D-PIM), which automatically recovers realistic frontal faces from arbitrary poses through a 3D face model in a novel way. Specifically, 3D-PIM incorporates a simulator with the aid of a 3D Morphable Model (3D MM) to obtain shape and appearance prior for accelerating face normalization learning, requiring less training data. It further leverages a global-local Generative Adversarial Network (GAN) with multiple critical improvements as a refiner to enhance the realism of both global structures and local details of the face simulator’s output using unlabelled real data only, while preserving the identity information. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks clearly demonstrate superiority of the proposed model over state-of-the-arts.

PDF Details

IJCAI Conference 2016 Conference Paper

Latent Contextual Bandits and their Application to Personalized Recommendations for New Users

Li Zhou
Emma Brunskill

Personalized recommendations for new users, also known as the cold-start problem, can be formulated as a contextual bandit problem. Existing contextual bandit algorithms generally rely on features alone to capture user variability. Such methods are inefficient in learning new users' interests. In this paper we propose Latent Contextual Bandits. We consider both the benefit of leveraging a set of learned latent user classes for new users, and how we can learn such latent classes from prior users. We show that our approach achieves a better regret bound than existing algorithms. We also demonstrate the benefit of our approach using a large real world dataset and a preliminary user study.

PDF Details

TCS Journal 2011 Journal Article

Scheduling resumable deteriorating jobs on a single machine with non-availability constraints

Baoqiang Fan
Shisheng Li
Li Zhou
Liqi Zhang

We consider a problem of scheduling resumable deteriorating jobs on a single machine with non-availability constraints. The objective is to minimize the total completion time. We prove that the problem with a single non-availability period is NP-hard in the ordinary sense and possesses a fully polynomial-time approximation scheme. In addition, we show that there does not exist a polynomial-time approximation algorithm with a constant worst-case ratio for the problem with two or more non-availability periods, unless P = N P.

Details DOI