arXiv subjects

Kun Lu

Publications and source records attributed to Kun Lu.

At least 19 recordsLinked to original sources

arXiv2026

UniPolymer: A Unified Framework for Property Prediction, Structure Recommendation, and Evaluation in Polyimide Design

Designing polyimide structures with specific glass transition temperatures (Tg) is highly challenging. Existing methods primarily focus on target-conditioned generation, lacking an assessment of the consistency between the generated structure and the target properties. This leads to low-quality candidates deviating from the design objective entering subsequent processes, increasing invalid experiments and prolonging the development cycle. To address this issue, we propose UniPolymer, a unified framework for property prediction, target-conditioned generation, candidate evaluation, and structure recommendation in polyimide design and a dataset containing 10066 deduplicated polyimide repeating units with Tg tags (PITg-Curated) was constructed. To improve the consistency between generated candidate structures and the target Tg, UniPolymer first establishes a reliable structure-property relationship mapping through self-supervised chemical semantic learning, structural consistency enhancement, and multi-scale information fusion. Subsequently, the model employs a continuous-discrete joint Tg representation to guide the autoregressive generation of SELFIES. The generated candidate structures are further evaluated using a frozen property predictor and polyimide-specific structural constraints, and ranked according to their deviation from the target Tg, thereby preventing structures deviating from the target from entering the subsequent validation stage. Experimental results show that UniPolymer achieved a property prediction accuracy of R^2=0.93 and a candidate structure evaluation pass rate of 73.79%, which are 2% and 1.21% higher than the best baseline, respectively. Meanwhile, the predicted Tg values of the recommended candidates are in high agreement with the results of molecular dynamics simulations, thereby reducing the number of candidates that enter the high-cost experimental stage.

cs.LG↗

arXiv2025

Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition

Fine-grained action recognition (FGAR) aims to identify subtle and distinctive differences among fine-grained action categories. However, current recognition methods often capture coarse-grained motion patterns but struggle to identify subtle details in local regions evolving over time. In this work, we introduce the Action-Region Tracking (ART) framework, a novel solution leveraging a query-response mechanism to discover and track the dynamics of distinctive local details, enabling effective distinction of similar actions. Specifically, we propose a region-specific semantic activation module that employs discriminative and text-constrained semantics as queries to capture the most action-related region responses in each video frame, facilitating interaction among spatial and temporal dimensions with corresponding video features. The captured region responses are organized into action tracklets, which characterize region-based action dynamics by linking related responses across video frames in a coherent sequence. The text-constrained queries encode nuanced semantic representations derived from textual descriptions of action labels extracted by language branches within Visual Language Models (VLMs). To optimize the action tracklets, we design a multi-level tracklet contrastive constraint among region responses at spatial and temporal levels, enabling effective discrimination within each frame and correlation between adjacent frames. Additionally, a task-specific fine-tuning mechanism refines textual semantics such that semantic representations encoded by VLMs are preserved while optimized for task preferences. Comprehensive experiments on widely used action recognition benchmarks demonstrate the superiority to previous state-of-the-art baselines.

cs.CV↗

arXiv2025

Reliable End-to-End Material Information Extraction from the Literature with Source-Tracked Multi-Stage Large Language Models

Data-driven materials discovery requires large-scale experimental datasets, yet most of the information remains trapped in unstructured literature. Existing extraction efforts often focus on a limited set of features and have not addressed the integrated composition-processing-microstructure-property relationships essential for understanding materials behavior, thereby posing challenges for building comprehensive databases. To address this gap, we propose a multi-stage information extraction pipeline powered by large language models, which captures 47 features spanning composition, processing, microstructure, and properties exclusively from experimentally reported materials. The pipeline integrates iterative extraction with source tracking to enhance both accuracy and reliability. Evaluations at the feature level (independent attributes) and tuple level (interdependent features) yielded F1 scores around 0.96. Compared with single-pass extraction without source tracking, our approach improved F1 scores of microstructure category by 10.0% (feature level) and 13.7% (tuple level), and reduced missed materials from 49 to 13 out of 396 materials in 100 articles on precipitate-containing multi-principal element alloys (miss rate reduced from 12.4% to 3.3%). The pipeline enables scalable and efficient literature mining, producing databases with high precision, minimal omissions, and zero false positives. These datasets provide trustworthy inputs for machine learning and materials informatics, while the modular design generalizes to diverse material classes, enabling comprehensive materials information extraction.

cs.CL↗

arXiv2025

Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting

Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data. With the surge of Large Language Models (LLMs), recent studies have begun exploring their integration into TKG forecasting and achieved some success. However, they still face limitations such as limited input length, inefficient output generation, and resource-intensive refinement, which undermine their performance and practical applicability. To address these limitations, we introduce SPARK, a Sequence-level Proxy-Adapting framework for Refining LLMs in TKG forecasting. Inspired by inference-time algorithms adopted in controlling generation, SPARK offers a cost-effective, plug-and-play solution through two key innovations: (1) Beam Sequence-Level Generation, which reframes TKG forecasting as a top-K sequence-level generation task, using beam search for efficiently generating next-entity distribution in a single forward pass. (2) TKG Adapter for Refinement, which employs traditional TKG models as trainable proxy adapters to leverage global graph information and refine LLM outputs, overcoming both the input length and the resource-intensive fine-tuning problems. Experiments across diverse datasets validate SPARK's forecasting performance, robust generalization capabilities, and high efficiency. We release source codes at https://github.com/yin-gz/SPARK.

cs.LG↗

arXiv2025

On-device Computation of Single-lead ECG Parameters for Real-time Remote Cardiac Health Assessment: A Real-world Validation Study

Accurate, continuous out-of-hospital electrocardiogram (ECG) parameter measurement is vital for real-time cardiac health monitoring and telemedicine. On-device computation of single-lead ECG parameters enables timely assessment without reliance on centralized data processing, advancing personalized, ubiquitous cardiac care-yet comprehensive validation across heterogeneous real-world populations remains limited. This study validated the on-device algorithm FeatureDB (https://github.com/PKUDigitalHealth/FeatureDB) using two datasets: HeartVoice-ECG-lite (369 participants with single-lead ECGs annotated by two physicians) and PTB-XL/PTB-XL+ (21,354 patients with 12-lead ECGs and physicians' diagnostic annotations). FeatureDB computed PR, QT, and QTc intervals, with accuracy evaluated against physician annotations via mean absolute error (MAE), correlation analysis, and Bland-Altman analysis. Diagnostic performance for first-degree atrioventricular block (AVBI, PR-based) and long QT syndrome (LQT, QTc-based) was benchmarked against commercial 12-lead systems (12SL, Uni-G) and open-source algorithm Deli, using AUC, accuracy, sensitivity, and specificity. Results showed high concordance with expert annotations (Pearson correlations: 0.836-0.960), MAEs matching inter-observer variability, and minimal bias. AVBI AUC reached 0.787 (12SL: 0.859; Uni-G: 0.812; Deli: 0.501); LQT AUC was 0.684 (12SL: 0.716; Uni-G: 0.605; Deli: 0.569)-comparable to commercial tools and superior to open-source alternatives. FeatureDB delivers physician-level parameter accuracy and commercial-grade abnormality detection via single-lead devices, supporting scalable telemedicine, decentralized cardiac screening, and continuous monitoring in community and outpatient settings.

eess.SP↗

arXiv2025

Predictions on observing hot holographic quark star with gravitational waves

We extract the equation of state of hot quark matter from a holographic 2+1 flavor QCD model, which could form the core of a stable compact star. By adding a thin hadron shell, a new type of hybrid star is constructed. With the temperature serving as a parameter, the EoS varies and we obtain stable stars with mass ranging from about 5 to 30 solar masses, and the maximum compactness around 0.2. The I-Love-Q-C relations are further discussed, and compared with the neutron star cases. These compact stars are candidates for black hole mimickers, which could be observed by gravitational waves and distinguished by properties like nonzero tidal Love number and electromagnetic signals.

hep-ph↗

arXiv2023

Alternate Learning based Sparse Semantic Communications for Visual Transmission

Semantic communication (SemCom) demonstrates strong superiority over conventional bit-level accurate transmission, by only attempting to recover the essential semantic information of data. In this paper, in order to tackle the non-differentiability of channels, we propose an alternate learning based SemCom system for visual transmission, named SparseSBC. Specially, SparseSBC leverages two separate Deep Neural Network (DNN)-based models at the transmitter and receiver, respectively, and learns the encoding and decoding in an alternate manner, rather than the joint optimization in existing literature, so as to solving the non-differentiability in the channel. In particular, a ``self-critic" training scheme is leveraged for stable training. Moreover, the DNN-based transmitter generates a sparse set of bits in deduced ``semantic bases", by further incorporating a binary quantization module on the basis of minimal detrimental effect to the semantic accuracy. Extensive simulation results validate that SparseSBC shows efficient and effective transmission performance under various channel conditions, and outperforms typical SemCom solutions.

cs.IT↗

arXiv2023

A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN

Deep convolutional neural network has made great achievements in sea-land clutter classification for over-the-horizon-radar (OTHR). The premise is that a large number of labeled training samples must be provided for a sea-land clutter classifier. In practical engineering applications, it is relatively easy to obtain label-free sea-land clutter samples. However, the labeling process is extremely cumbersome and requires expertise in the field of OTHR. To solve this problem, we propose an improved generative adversarial network, namely weighted loss semi-supervised generative adversarial network (WL-SSGAN). Specifically, we propose a joint feature matching loss by weighting the middle layer features of the discriminator of semi-supervised generative adversarial network. Furthermore, we propose the weighted loss of WL-SSGAN by linearly weighting standard adversarial loss and joint feature matching loss. The semi-supervised classification performance of WL-SSGAN is evaluated on a sea-land clutter dataset. The experimental results show that WL-SSGAN can improve the performance of the fully supervised classifier with only a small number of labeled samples by utilizing a large number of unlabeled sea-land clutter samples. Further, the proposed weighted loss is superior to both the adversarial loss and the feature matching loss. Additionally, we compare WL-SSGAN with conventional semi-supervised classification methods and demonstrate that WL-SSGAN achieves the highest classification accuracy.

cs.CV↗

arXiv2023

Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN

In the sea-land clutter classification of sky-wave over-the-horizon-radar (OTHR), the imbalanced and scarce data leads to a poor performance of the deep learning-based classification model. To solve this problem, this paper proposes an improved auxiliary classifier generative adversarial network~(AC-GAN) architecture, namely auxiliary classifier variational autoencoder generative adversarial network (AC-VAEGAN). AC-VAEGAN can synthesize higher quality sea-land clutter samples than AC-GAN and serve as an effective tool for data augmentation. Specifically, a 1-dimensional convolutional AC-VAEGAN architecture is designed to synthesize sea-land clutter samples. Additionally, an evaluation method combining both traditional evaluation of GAN domain and statistical evaluation of signal domain is proposed to evaluate the quality of synthetic samples. Using a dataset of OTHR sea-land clutter, both the quality of the synthetic samples and the performance of data augmentation of AC-VAEGAN are verified. Further, the effect of AC-VAEGAN as a data augmentation method on the classification performance of imbalanced and scarce sea-land clutter samples is validated. The experiment results show that the quality of samples synthesized by AC-VAEGAN is better than that of AC-GAN, and the data augmentation method with AC-VAEGAN is able to improve the classification performance in the case of imbalanced and scarce sea-land clutter samples.

eess.SY↗

arXiv2022

Semantics-Empowered Communication: A Tutorial-cum-Survey

Along with the springing up of the semantics-empowered communication (SemCom) research, it is now witnessing an unprecedentedly growing interest towards a wide range of aspects (e.g., theories, applications, metrics and implementations) in both academia and industry. In this work, we primarily aim to provide a comprehensive survey on both the background and research taxonomy, as well as a detailed technical tutorial. Specifically, we start by reviewing the literature and answering the "what" and "why" questions in semantic transmissions. Afterwards, we present the ecosystems of SemCom, including history, theories, metrics, datasets and toolkits, on top of which the taxonomy for research directions is presented. Furthermore, we propose to categorize the critical enabling techniques by explicit and implicit reasoning-based methods, and elaborate on how they evolve and contribute to modern content & channel semantics-empowered communications. Besides reviewing and summarizing the latest efforts in SemCom, we discuss the relations with other communication levels (e.g., conventional communications) from a holistic and unified viewpoint. Subsequently, in order to facilitate future developments and industrial applications, we also highlight advanced practical techniques for boosting semantic accuracy, robustness, and large-scale scalability, just to mention a few. Finally, we discuss the technical challenges that shed light on future research opportunities.

cs.HC↗

arXiv2022

Contrastive Monotonic Pixel-Level Modulation

Continuous one-to-many mapping is a less investigated yet important task in both low-level visions and neural image translation. In this paper, we present a new formulation called MonoPix, an unsupervised and contrastive continuous modulation model, and take a step further to enable a pixel-level spatial control which is critical but can not be properly handled previously. The key feature of this work is to model the monotonicity between controlling signals and the domain discriminator with a novel contrastive modulation framework and corresponding monotonicity constraints. We have also introduced a selective inference strategy with logarithmic approximation complexity and support fast domain adaptations. The state-of-the-art performance is validated on a variety of continuous mapping tasks, including AFHQ cat-dog and Yosemite summer-winter translation. The introduced approach also helps to provide a new solution for many low-level tasks like low-light enhancement and natural noise generation, which is beyond the long-established practice of one-to-one training and inference. Code is available at https://github.com/lukun199/MonoPix.

cs.CV↗

arXiv2021

Finding citations for PubMed: A large-scale comparison between five freely available bibliographic data sources

As an important biomedical database, PubMed provides users with free access to abstracts of its documents. However, citations between these documents need to be collected from external data sources. Although previous studies have investigated the coverage of various data sources, the quality of citations is underexplored. In response, this study compares the coverage and citation quality of five freely available data sources on 30 million PubMed documents, including OpenCitations Index of CrossRef open DOI-to-DOI citations (COCI), Dimensions, Microsoft Academic Graph (MAG), National Institutes of Health Open Citation Collection (NIH-OCC), and Semantic Scholar Open Research Corpus (S2ORC). Three gold standards and five metrics are introduced to evaluate the correctness and completeness of citations. Our results indicate that Dimensions is the most comprehensive data source that provides references for 62.4% of PubMed documents, outperforming the official NIH-OCC dataset (56.7%). Over 90% of citation links in other data sources can also be found in Dimensions. The coverage of MAG, COCI, and S2ORC is 59.6%, 34.7%, and 23.5%, respectively. Regarding the citation quality, Dimensions and NIH-OCC achieve the best overall results. Almost all data sources have a precision higher than 90%, but their recall is much lower. All databases have better performances on recent publications than earlier ones. Meanwhile, the gaps between different data sources have diminished for the documents published in recent years. This study provides evidence for researchers to choose suitable PubMed citation sources, which is also helpful for evaluating the citation quality of free bibliographic databases.

cs.DL↗

arXiv2021

Rethinking Modern Communication from Semantic Coding to Semantic Communication

Modern communications are usually designed to pursue a higher bit-level precision and fewer bits while transmitting a message. This article rethinks these two major features and introduces the concept and advantage of semantics that characterizes a new kind of semantics-aware communication framework, incorporating both the semantic encoding and the semantic communication problem. After analyzing the underlying defects of existing semantics-aware techniques, we establish a confidence-based distillation mechanism for the joint semantics-noise coding (JSNC) problem and a reinforcement learning (RL)-powered semantic communication paradigm that endows a system the ability to convey the semantics instead of pursuing the bit level accuracy. On top of these technical contributions, this work provides a new insight to understand how the semantics are processed and represented in a semantics-aware coding and communication system, and verifies the significant benefits of doing so. Targeted on the next generation's semantics-aware communication, some critical concerns and open challenges such as the information overhead, semantic security and implementation cost are also discussed and envisioned.

eess.SP↗

arXiv2021

Topics Emerged in the Biomedical Field and Their Characteristics

This study aims to reveal what kind of topics emerged in the biomedical domain by retrospectively analyzing newly added MeSH (Medical Subject Headings) terms from 2001 to 2010 and how they have been used for indexing since their inclusion in the thesaurus. The goal is to investigate if the future trend of a new topic depends on what kind of topic it is without relying on external indicators such as growth, citation patterns, or word co-occurrences. This topic perspective complements the traditional publication perspective in studying emerging topics. Results show that topic characteristics, including topic category, clinical significance, and if a topic has any narrower terms at the time of inclusion, influence future popularity of a new MeSH. Four emergence trend patterns are identified, including emerged and sustained, emerged not sustained, emerged and fluctuated, and not yet emerged. Predictive models using topic characteristics for emerging topic prediction show promise. This suggests that the characteristics of topics and domain should be considered when predicting future emergence of research topics. This study bridges a gap in emerging topic prediction by offering a topic perspective and advocates for considering topic and domain characteristics as well as economic, medical, and environmental impact when studying emerging topics in the biomedical domain.

cs.DL↗

arXiv2021

Augmented Abstractive Summarization With Document-LevelSemantic Graph

Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module to assist the system to detect vital mentions and relationships within a document. To address this problem, we utilize semantic graph to boost the generation performance. Firstly, we extract important entities from each document and then establish a graph inspired by the idea of distant supervision \citep{mintz-etal-2009-distant}. Then, we combine a Bi-LSTM with a graph encoder to obtain the representation of each graph node. A novel neural decoder is presented to leverage the information of such entity graphs. Automatic and human evaluations show the effectiveness of our technique.

cs.CL↗

arXiv2021

Reinforcement Learning-powered Semantic Communication via Semantic Similarity

We introduce a new semantic communication mechanism - SemanticRL, whose key idea is to preserve the semantic information instead of strictly securing the bit-level precision. Unlike previous methods that mainly concentrate on the network or structure design, we revisit the learning process and point out the semantic blindness of commonly used objective functions. To address this semantic gap, we introduce a schematic shift that learns from semantic similarity, instead of relying on conventional paired bit-level supervisions like cross entropy and bit error rate. However, developing such a semantic communication system is indeed a nontrivial task considering the non-differentiability of most semantic metrics as well as the instability from noisy channels. To further resolve these issues, we put forward a self-critic reinforcement learning (RL) solution which allows an efficient and stable learning on any user-defined semantic measurement, and take a step further to simultaneously tackle the non-differentiable semantic channel optimization problem via self-critic stochastic iterative updating (SCSIU) training on the decoupled semantic transceiver. We have firstly tested the proposed method in the challenging European-parliament dataset, which confirms the superiority of our method in revealing the semantic meanings, and better handling the semantic noise. Apart from the experimental results, we further provide an in-depth look at how the semantic model behaves, along with its superb generalization ability in real-life examples. An RL-based image transmission extension is also exemplified, so as to prove the generalization ability and motivate future discussion.

cs.LG↗

arXiv2020

OTHR multitarget tracking with a GMRF model of ionospheric parameters

The ionosphere is the propagation medium for radio waves transmitted by an over-the-horizon radar (OTHR). Ionospheric parameters, typically, virtual ionospheric heights (VIHs), are required to perform coordinate registration for OTHR multitarget tracking and localization. The inaccuracy of ionospheric parameters has a significant deleterious effect on the target localization of OTHR. Therefore, to improve the localization accuracy of OTHR, it is important to develop accurate models and estimation methods of ionospheric parameters and the corresponding target tracking algorithms. In this paper, we consider the variation of the ionosphere with location and the spatial correlation of the ionosphere in OTHR target tracking. We use a Gaussian Markov random field (GMRF) to model the VIHs, providing a more accurate representation of the VIHs for OTHR target tracking. Based on expectation-conditional maximization and GMRF modeling of the VIHs, we propose a novel joint optimization solution, called ECM-GMRF, to perform target state estimation, multipath data association and VIHs estimation simultaneously. In ECM-GMRF, the measurements from both ionosondes and OTHR are exploited to estimate the VIHs, leading to a better estimation of the VIHs which improves the accuracy of data association and target state estimation, and vice versa. The simulation indicates the effectiveness of the proposed algorithm.

eess.SY↗

arXiv2020

Measurement-Level Fusion for OTHR Network Using Message Passing

Tracking an unknown number of targets based on multipath measurements provided by an over-the-horizon radar (OTHR) network with a statistical ionospheric model is complicated, which requires solving four subproblems: target detection, target tracking, multipath data association and ionospheric height identification. A joint solution is desired since the four subproblems are highly correlated, but suffering from the intractable inference problem of high-dimensional latent variables. In this paper, a unified message passing approach, combining belief propagation (BP) and mean-field (MF) approximation, is developed for simplifying the intractable inference. Based upon the factor graph corresponding to a factorization of the joint probability distribution function (PDF) of the latent variables and a choice for a separation of this factorization into BP region and MF region, the posterior PDFs of continuous latent variables including target kinematic state, target visibility state, and ionospheric height, are approximated by MF due to its simple MP update rules for conjugate-exponential models. With regard to discrete multipath data association which contains one-to-one frame (hard) constraints, its PDF is approximated by loopy BP. Finally, the approximated posterior PDFs are updated iteratively in a closed-loop manner, which is effective for dealing with the coupling issue among target detection, target tracking, multipath data association, and ionospheric height identification. Meanwhile, the proposed approach has the measurement-level fusion architecture due to the direct processing of the raw multipath measurements from an OTHR network, which is benefit to improving target tracking performance. Its performance is demonstrated on a simulated OTHR network multitarget tracking scenario.

eess.SP↗