Author name cluster

Long Li

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.

8 papers

2 author rows

EAAI Journal 2026 Journal Article

Anomaly localization of industrial images based on coordinate dual memory banks and difference subsection evolution

Long Li
Zhiyan Han
Jian Wang

Unsupervised image anomaly detection has been widely used in the industrial field, yet data imbalance and overfitting limit its performance. Therefore, this study proposes an industrial image anomaly localization network based on coordinate dual memory banks and difference subsection evolution (DmseNet). Firstly, to enable diversified generation of anomaly masks, the foreground coordinate dual memory banks strategy is proposed, and the corrosion factor is introduced for generating more realistic anomalies. Secondly, to effectively guide the learning process, a group channel migrated attention module was designed as a projector. It directly propagates and refines multi-scale teacher features through joint channel-spatial optimization, providing precise reconstruction guidance for the student network. In addition, a regularization repair module is proposed, which enhances the generalization ability and feature repair ability of the model. Finally, the entire system is refined under the optimization of the proposed difference subsection evolution loss. It dynamically assigns weights and loss levels according to the degree of feature deviation and enables the model to focus on the key information areas more accurately and improves the model’s discrimination ability. Comprehensive experiments on four challenging datasets, a self-built printed circuit board (PCB) anomaly detection platform and multi-view inspection application verify the portability and practicability of DmseNet in different scenarios, although its capability for image-level logical anomaly detection remains relatively limited. The research results not only promote the application of unsupervised learning in industrial image analysis, but also provide a new solution for the landing of artificial intelligence.

Details DOI

NeurIPS Conference 2025 Conference Paper

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?

Yuqian Yuan
Ronghao Dang
Long Li
Wentong Li
Dian Jiao
Xin Li
Deli Zhao
Fan Wang

The emergence of multimodal large language models (MLLMs) has driven breakthroughs in egocentric vision applications. These applications necessitate persistent, context-aware understanding of objects, as users interact with tools in dynamic and cluttered environments. However, existing embodied benchmarks primarily focus on static scene exploration, emphasizing object's appearance and spatial attributes while neglecting the assessment of dynamic changes arising from users' interactions. capabilities in object-level spatiotemporal reasoning required for real-world interactions. To address this gap, we introduce EOC-Bench, an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios. Specially, EOC-Bench features 3, 277 meticulously annotated QA pairs categorized into three temporal categories: Past, Present, and Future, covering 11 fine-grained evaluation dimensions and 3 visual object referencing types. To ensure thorough assessment, we develop a mixed-format human-in-the-loop annotation frameworkBased on EOC-Bench, we conduct comprehensive evaluations of various proprietary, open-source, and object-level MLLMs. EOC-Bench serves as a crucial tool for advancing the embodied object cognitive capabilities of MLLMs, establishing a robust foundation for developing reliable core models for embodied systems.

PDF Details

NeurIPS Conference 2025 Conference Paper

PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection

Long Li
Wencheng Zhang
Shi Yuan
Hongle Guo
Wanghu Chen

Unsupervised anomaly detection of multivariate time series remains challenging in complex nonstationary dynamics, due to the high false-positive rates and limited interpretability. We propose PhysDiff, combining physics-guided decomposition with diffusion-based reconstruction, to address these issues. The physics-guided signal decomposition is introduced to disentangle overlapping dynamics by isolating high frequency oscillations and low frequency trends, which can reduce interference and provide meaningful physical priors. The reconstruction through conditional diffusion modeling captures deviations from learned normal behavior, making anomalies more distinguishable. Notably, PhysDiff introduces an amplitude-sensitive permutation entropy criterion to adaptively determine the optimal decomposition depth, and automatically extract adaptive frequency components used as explicit physics-based constraints for the diffusion process. Furthermore, the proposed conditional diffusion network employs a dual-path conditioning mechanism that integrates high-frequency and low-frequency physical priors, dynamically regulating the denoising process via a novel time frequency energy routing mechanism. By weighting reconstruction errors across frequency bands, our method improves anomaly localization and enhances interpretability. Extensive experiments on five benchmark datasets and two NeurIPS-TS scenarios demonstrate that PhysDiff outperforms 18 state-of-the-art baselines, with average F1-score improvements on both standard and challenging datasets. Experimental results validate the advantages of combining principled signal decomposition with diffusion-based reconstruction for robust, interpretable anomaly detection in complex dynamic systems.

PDF Details

EAAI Journal 2025 Journal Article

Store-and-forward with graph attention: Enhanced multi-agent reinforcement learning for emergency-responsive traffic signal control

Kangkang Yang
Zhiwen Wang
Xinyou Meng
Long Li
Yaoke Shi
Yuling Yu
Haoxu Wang
Ziheng Yao

This paper investigates the problem of priority access signal control for emergency vehicles (EMVs) in urban road networks. Based on the characteristics of traffic road network, a cooperative multi-agent reinforcement learning model leveraging the store-and-forward paradigm is proposed, as a way to improve emergency vehicle priority and alleviate urban traffic pressure. Initially, we establish cooperative relationships among agents at the network modeling level, modeling the traffic flow between pairs of adjacent agents as a co-optimization objective, which achieves parameter decoupling among algorithms. Subsequently, through regional partitioning, we design a spatiotemporal information extraction algorithm, termed store-and-forward graph attention mechanism for multi-agent proximal policy optimization (SF-GMPPO), to control information exchange among agents, thereby learning optimal traffic signal control policies. Finally, the proposed algorithm model is tested in both synthetic and real-world network environments. Experimental results demonstrate that the proposed algorithm surpasses similar algorithms in terms of training convergence and control performance. Specifically, in the 5x5 synthetic road network, the average speed of EMVs increased by 2. 463 meters per second (m/s) compared to social vehicles. In the Lanzhou Chengguan road network with 128 intersections, the proposed algorithm achieved high traffic control efficiency, resulting in the speed of social vehicles approaching that of EMVs, with EMVs operating at an average speed of 13. 061 m/s and social vehicles at 13. 032 m/s under efficient traffic flow management. These results highlight the effectiveness of the proposed approach in enhancing EMV priority while maintaining overall traffic efficiency.

Details DOI

IROS Conference 2024 Conference Paper

A Facile one-step injection novel composite sensor for robot tactile assistance

Yuyin Zhang
Yue Wang 0110
Na Liu 0004
Songyi Zhong
Long Li
Xie Xie
Quan Zhang
Tao Yue 0001

Tactile information is the research hotspot of wearable flexible sensors due to its importance and complexity. With the innovation of wearable technology and robotics in healthcare, researchers are increasingly integrating wearable flexible sensors on the front end of robots to reproduce the hand tactile manipulation of human tissues. Therefore, it is hoped to develop a thin-film sensor that can be deployed in a small area to assist robots in surgery and data collection of human tissues. Here we use a one-step injection method to fabricate a novel composite sensor based on liquid metal. By laminating multiple PDMS microfluidic layers, the two parameters of pressure and deformation are measured simultaneously in a decoupled manner. The sensor is small and thin, making it easy to integrate into fingers/robot fingers for assistance. The finger/robot finger exerts pressure on the sensor and the sensor deforms with the material to identify the hardness of the material being touched. Separate performance tests of the two sensors show that the strain and pressure functions are decoupled from each other, and their ratios can identify and classify the hardness of different touched materials (glass, PDMS and silicone). This novel composite sensor we proposed can assist robots in manipulating human tissues during medical surgeries. At the same time, its function in tactile information feedback also has broad applications in medical treatment, rehabilitation and services.

Details

AAAI Conference 2024 Conference Paper

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

Hongjie Xia
Huijie Ao
Long Li
Yu Liu
Sen Liu
Guangnan Ye
Hongfeng Chai

Quantitative stock selection is one of the most challenging FinTech tasks due to the non-stationary dynamics and complex market dependencies. Existing studies rely on channel mixing methods, exacerbating the issue of distribution shift in financial time series. Additionally, complex model structures they build make it difficult to handle very long sequences. Furthermore, most of them are based on predefined stock relationships thus making it difficult to capture the dynamic and highly volatile stock markets. To address the above issues, in this paper, we propose Channel-Independent based Spatio-Temporal Hypergraph Pre-trained Attention Networks (CI-STHPAN), a two-stage framework for stock selection, involving Transformer and HGAT based stock time series self-supervised pre-training and stock-ranking based downstream task fine-tuning. We calculate the similarity of stock time series of different channel in dynamic intervals based on Dynamic Time Warping (DTW), and further construct channel-independent stock dynamic hypergraph based on the similarity. Experiments with NASDAQ and NYSE markets data over five years show that our framework outperforms SOTA approaches in terms of investment return ratio (IRR) and Sharpe ratio (SR). Additionally, we find that even without introducing graph information, self-supervised learning based on the vanilla Transformer Encoder also surpasses SOTA results. Notable improvements are gained on the NYSE market. It is mainly attributed to the improvement of fine-tuning approach on Information Coefficient (IC) and Information Ratio based IC (ICIR), indicating that the fine-tuning method enhances the accuracy and stability of the model prediction.

PDF Details DOI

JBHI Journal 2023 Journal Article

sEMG-Based End-to-End Continues Prediction of Human Knee Joint Angles Using the Tightly Coupled Convolutional Transformer Model

Tuanjie Liang
Ning Sun
Qiong Wang
Jingyu Bu
Long Li
Yuhao Chen
Menglin Cao
Jin Ma

Wearable exoskeleton robots can promote the rehabilitation of patients with physical dysfunction. And improving human-computer interaction performance is a significant challenge for exoskeleton robots. The traditional feature extraction process based on surface Electromyography(sEMG) is complex and requires manual intervention, making real-time performance difficult to guarantee. In this study, we propose an end-to-end method to predict human knee joint angles based on sEMG signals using a tightly coupled convolutional transformer (TCCT) model. We first collected sEMG signals from 5 healthy subjects. Then, the envelope was extracted from the noise-removed sEMG signal and used as the input to the model. Finally, we developed the TCCT model to predict the knee joint angle after 100 ms. For the prediction performance, we used the Root Mean Square Error(RMSE), Pearson Correlation Coefficient(CC), and Adjustment R 2 as metrics to evaluate the error between the actual knee angle and the predicted knee angle. The results show that the model can predict the human knee angle quickly and accurately. The mean RMSE, Adjustment R 2, and (CC) values of the model are 3. 79°, 0. 96, and 0. 98, respectively, which are better than traditional deep learning models such as Informer (4. 14, 0. 95, 0. 98), CNN (5. 56, 0. 89, 0. 96) and CNN-BiLSTM (3. 97, 0. 95, 0. 98). In addition, the prediction time of our proposed model is only 11. 67 ± 0. 67 ms, which is less than 100 ms. Therefore, the real-time and accuracy of the model can meet the continuous prediction of human knee joint angle in practice.

Details DOI

TCS Journal 2021 Journal Article

Enumeration of subtrees and BC-subtrees with maximum degree no more than k in trees

Yu Yang
Xiao-xiao Li
Meng-yuan Jin
Long Li
Hua Wang
Xiao-Dong Zhang

The subtrees and BC-subtrees (subtrees where any two leaves are at even distance apart) have been intensively studied in recent years. Such structures, under special constraints on degrees, have a wide range of applications in many fields. By way of an approach based on generating functions, we present novel recursive algorithms for enumerating various subtrees and BC-subtrees of maximum degree ≤k in trees. The algorithms are explained through detailed examples. We also briefly discuss, in trees, the densities of subtrees (resp. BC-subtrees) with maximum degree ≤k among all subtrees (resp. BC-subtrees). For a tree of order n, the novelly proposed algorithms have multiple advantages. (1) Novel ( k + 2 ) (resp. ( 2 k + 3 ) ) variable generating functions were introduced to construct the algorithms. (2) The proposed algorithms solved the fast enumerating problem of subtree (resp. BC-subtrees) with maximum degree constraint, and also make the subtree (resp. BC-subtrees) enumerating algorithms proposed by Yan and Yeh [1] (resp. Yang et al. [2]) a special case of ours with k = n − 1. (3) The time complexity of our algorithm for subtree (resp. BC-subtrees) is O ( k n ) (resp. O ( k n 2 ) ), which is much faster than the O ( n 2 ) (resp. O ( k n 3 ) ) time method based on algorithm proposed in [1] (resp. [2]).

Details DOI