arXiv subjects

Zhihao Yang

Publications and source records attributed to Zhihao Yang.

27 records · Page 2Linked to original sources

arXiv2025

Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation

Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods typically employ spatio-temporal modeling to establish dependencies among joints as well as frames, and utilize one-hot encoding with cross-entropy loss for frame-wise classification supervision. However, these methods overlook the intrinsic correlations among joints and actions within skeletal features, leading to a limited understanding of human movements. To address this, we propose a Text-Derived Relational Graph-Enhanced Network (TRG-Net) that leverages prior graphs generated by Large Language Models (LLM) to enhance both modeling and supervision. For modeling, the Dynamic Spatio-Temporal Fusion Modeling (DSFM) method incorporates Text-Derived Joint Graphs (TJG) with channel- and frame-level dynamic adaptation to effectively model spatial relations, while integrating spatio-temporal core features during temporal modeling. For supervision, the Absolute-Relative Inter-Class Supervision (ARIS) method employs contrastive learning between action features and text embeddings to regularize the absolute class distributions, and utilizes Text-Derived Action Graphs (TAG) to capture the relative inter-class relationships among action features. Additionally, we propose a Spatial-Aware Enhancement Processing (SAEP) method, which incorporates random joint occlusion and axial rotation to enhance spatial generalization. Performance evaluations on four public datasets demonstrate that TRG-Net achieves state-of-the-art results.

cs.CV↗

arXiv2024

Anisotropic pressure effect on central EOS of PSR J0740+6620 in the light of dimensionless TOV equation

It is generally agreed upon that the pressure inside a neutron star is isotropic. However, a strong magnetic field or superfluidity suggests that the pressure anisotropy may be a more realistic model. We derived the dimensionless TOV equation for anisotropic neutron stars based on two popular models, namely the BL model and the H model, to investigate the effect of anisotropy. Similar to the isotropic case, the maximum mass $M_{max}$ and its corresponding radius $R_{Mmax}$ can also be expressed linearly by a combination of radial central pressure $p_{rc}$ and central energy density $\varepsilon_{c}$, which is insensitive to the equation of state (EOS). We also found that the obtained central EOS would change with different values of $λ_{BL}$ ($λ_{H}$), which controls the magnitude of the difference between the transverse pressure and the radial pressure. Combining with observational data of PSR J0740+6620 and comparing to the extracted EOS based on isotropic neutron star, it is shown that in the BL model, for $λ_{BL}$ = 0.4, the extracted central energy density $\varepsilon_{c}$ changed from 546 -- 1056 MeV/fm$^{3}$ to 510 -- 1005 MeV/fm$^{3}$, and the extracted radial central pressure $p_{rc}$ changed from 87 -- 310 MeV/fm$^{3}$ to 76 -- 271 MeV/fm$^{3}$. For $λ_{BL}$ = 2, the extracted $\varepsilon_{c}$ and $p_{rc}$ changed to 412 -- 822 MeV/fm$^{3}$ and 50 -- 165 MeV/fm$^{3}$, respectively. In the H model, for $λ_{H}$ = 0.4, the extracted $\varepsilon_{c}$ changed to 626 -- 1164 MeV/fm$^{3}$, and the extracted $p_{rc}$ changed to 104 -- 409 MeV/fm$^{3}$. For $λ_{H}$ = 2, the extracted $\varepsilon_{c}$ decreased to 894 -- 995 MeV/fm$^{3}$, and the extracted $p_{rc}$ changed to 220 -- 301 MeV/fm$^{3}$.

astro-ph.HE↗

arXiv2023

Xpert: Empowering Incident Management with Query Recommendations via Large Language Models

Large-scale cloud systems play a pivotal role in modern IT infrastructure. However, incidents occurring within these systems can lead to service disruptions and adversely affect user experience. To swiftly resolve such incidents, on-call engineers depend on crafting domain-specific language (DSL) queries to analyze telemetry data. However, writing these queries can be challenging and time-consuming. This paper presents a thorough empirical study on the utilization of queries of KQL, a DSL employed for incident management in a large-scale cloud management system at Microsoft. The findings obtained underscore the importance and viability of KQL queries recommendation to enhance incident management. Building upon these valuable insights, we introduce Xpert, an end-to-end machine learning framework that automates KQL recommendation process. By leveraging historical incident data and large language models, Xpert generates customized KQL queries tailored to new incidents. Furthermore, Xpert incorporates a novel performance metric called Xcore, enabling a thorough evaluation of query quality from three comprehensive perspectives. We conduct extensive evaluations of Xpert, demonstrating its effectiveness in offline settings. Notably, we deploy Xpert in the real production environment of a large-scale incident management system in Microsoft, validating its efficiency in supporting incident management. To the best of our knowledge, this paper represents the first empirical study of its kind, and Xpert stands as a pioneering DSL query recommendation framework designed for incident management.

cs.SE↗

arXiv2023

Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks

Objective: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical NLP tasks in different languages, We present Taiyi, a bilingual fine-tuned LLM for diverse biomedical tasks. Materials and Methods: We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, a two-stage strategy is proposed for supervised fine-tuning to optimize the model performance across varied tasks. Results: Experimental results on 13 test sets covering named entity recognition, relation extraction, text classification, question answering tasks demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multi-tasking. Conclusion: Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multi-tasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches of smaller language models.

cs.CL↗

arXiv2023

BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding

Bokeh effect is an optical phenomenon that offers a pleasant visual experience, typically generated by high-end cameras with wide aperture lenses. The task of bokeh effect transformation aims to produce a desired effect in one set of lenses and apertures based on another combination. Current models are limited in their ability to render a specific set of bokeh effects, primarily transformations from sharp to blur. In this paper, we propose a novel universal method for embedding lens metadata into the model and introducing a loss calculation method using alpha masks from the newly released Bokeh Effect Transformation Dataset(BETD) [3]. Based on the above techniques, we propose the BokehOrNot model, which is capable of producing both blur-to-sharp and sharp-to-blur bokeh effect with various combinations of lenses and aperture sizes. Our proposed model outperforms current leading bokeh rendering and image restoration models and renders visually natural bokeh effects. Our code is available at: https://github.com/indicator0/bokehornot.

cs.CV↗

arXiv2021

Biomedical named entity recognition using BERT in the machine reading comprehension framework

Recognition of biomedical entities from literature is a challenging research focus, which is the foundation for extracting a large amount of biomedical knowledge existing in unstructured texts into structured formats. Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method. This method, however, often cannot take full advantage of the semantic information in the dataset, and the performance is not always satisfactory. In this work, instead of treating the BioNER task as a sequence labeling problem, we formulate it as a machine reading comprehension (MRC) problem. This formulation can introduce more prior knowledge utilizing well-designed queries, and no longer need decoding processes such as conditional random fields (CRF). We conduct experiments on six BioNER datasets, and the experimental results demonstrate the effectiveness of our method. Our method achieves state-of-the-art (SOTA) performance on the BC4CHEMD, BC5CDR-Chem, BC5CDR-Disease, NCBI-Disease, BC2GM and JNLPBA datasets, achieving F1-scores of 92.92%, 94.19%, 87.83%, 90.04%, 85.48% and 78.93%, respectively.

cs.CL↗

arXiv2020

EPIHC: Improving Enhancer-Promoter Interaction Prediction by using Hybrid features and Communicative learning

Enhancer-promoter interactions (EPIs) regulate the expression of specific genes in cells, and EPIs are important for understanding gene regulation, cell differentiation and disease mechanisms. EPI identification through the wet experiments is costly and time-consuming, and computational methods are in demand. In this paper, we propose a deep neural network-based method EPIHC based on sequence-derived features and genomic features for the EPI prediction. EPIHC extracts features from enhancer and promoter sequences respectively using convolutional neural networks (CNN), and then design a communicative learning module to captures the communicative information between enhancer and promoter sequences. EPIHC also take the genomic features of enhancers and promoters into account. At last, EPIHC combines sequence-derived features and genomic features to predict EPIs. The computational experiments show that EPIHC outperforms the existing state-of-the-art EPI prediction methods on the benchmark datasets and chromosome-split datasets, and the study reveal that the communicative learning module can bring explicit information about EPIs, which is ignore by CNN. Moreover, we consider two strategies to improve performances of EPIHC in the cross-cell line prediction, and experimental results show that EPIHC constructed on training cell lines exhibit improved performances for the other cell lines.

q-bio.GN↗

arXiv2020

Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge

Motivation: The biomedical literature contains a wealth of chemical-protein interactions (CPIs). Automatically extracting CPIs described in biomedical literature is essential for drug discovery, precision medicine, as well as basic biomedical research. Most existing methods focus only on the sentence sequence to identify these CPIs. However, the local structure of sentences and external biomedical knowledge also contain valuable information. Effective use of such information may improve the performance of CPI extraction. Results: In this paper, we propose a novel neural network-based approach to improve CPI extraction. Specifically, the approach first employs BERT to generate high-quality contextual representations of the title sequence, instance sequence, and knowledge sequence. Then, the Gaussian probability distribution is introduced to capture the local structure of the instance. Meanwhile, the attention mechanism is applied to fuse the title information and biomedical knowledge, respectively. Finally, the related representations are concatenated and fed into the softmax function to extract CPIs. We evaluate our proposed model on the CHEMPROT corpus. Our proposed model is superior in performance as compared with other state-of-the-art models. The experimental results show that the Gaussian probability distribution and external knowledge are complementary to each other. Integrating them can effectively improve the CPI extraction performance. Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks. Availability: Data and code are available at https://github.com/CongSun-dlut/CPI_extraction. Contact: yangzh@dlut.edu.cn, wangleibihami@gmail.com Supplementary information: Supplementary data are available at Bioinformatics online.

cs.CL↗

arXiv2019

Detailed Performance Loss Analysis of Silicon Solar Cells using High-Throughput Metrology Methods

In this work, novel, high-throughput metrology methods are used to perform a detailed performance loss analysis of approximately 400 industrial crystalline silicon solar cells, all coming from the same production line. The characterization sequence includes a non-destructive transfer length method (TLM) measurement technique featuring circular TLM structures hidden within the busbar region of the cells. It also includes a very fast external quantum efficiency and reflectance measurement technique. More traditional measurements, like illuminated current-voltage, Suns-VOC, and photoluminescence imaging are also used to carry out the loss analysis. The variance of the individual loss parameters and their impact on cell performance are investigated and quantified for this large group of industrial solar cells. Some important correlations between the measured loss parameters are found. The nature of these distributions and correlations provide important insights about loss mechanisms in a cell and help prioritize efforts to optimize the performance of the production line.

physics.app-ph↗