Searcharxiv⌕ Search

arXiv subjects

Xue Li

Publications and source records attributed to Xue Li.

At least 109 records · Page 6Linked to original sources
arXiv2024

Ultraviolet and Chromospheric activity and Habitability of M stars

M-type stars are crucial for stellar activity studies since they cover two types of magnetic dynamos and particularly intriguing for habitability studies due to their abundance and long lifespans during the main-sequence stage. In this paper, we used the LAMOST DR9 catalog and the GALEX UV archive data to investigate the chromospheric and UV activities of M-type stars. All the chromospheric and UV activity indices clearly show the saturated and unsaturated regimes and the well-known activity-rotation relation, consistent with previous studies. Both the FUV and NUV activity indices exhibit a single-peaked distribution, while the {\rm H$α$} and \rm {Ca \scriptsize{\uppercase\expandafter{\romannumeral2}} \normalsize H$\&$K} indices show a distinct double-peaked distribution. The gap between these peaks suggests a rapid transition from a saturated population to an unsaturated one. The smoothly varying distributions of different subtypes suggest a rotation-dependent dynamo for both early-type (partly convective) to late-type (fully convective) M stars. We identified a group of stars with high UV activity above the saturation regime (log$R^{\prime}_{\rm NUV} > -2.5$) but low chromospheric activity, and the underlying reason is unknown. By calculating the continuously habitable zone and the UV habitable zone for each star, we found about 70\% stars in the total sample and 40\% stars within 100 pc are located in the overlapping region of these two habitable zones, indicating a number of M stars are potentially habitable. Finally, we examined the possibility of UV activity studies of M stars using the China Space Station Telescope.

astro-ph.SR↗
arXiv2024

Large Anomalous Hall Effect at Room Temperature in a Fermi-Level-Tuned Kagome Antiferromagnet

The recent discoveries of surperisingly large anomalous Hall effect in chiral antiderromagnets have triggered extensive research efforts in various fields, ranging from topological condensed-matter physics to antiferromagnetic spintronics, and energy harvesting technology. However, such AHE-hosting antiferromagnetic materials are rare in nature. Herein, we demonstrate that Mn2.4Ga, a Fermi-level-tuned kagome antiferromagnet, has a large anomalous Hall conductivity of about 150 Ω-1cm-1 at room temperature that surpasses the usual high values (i.e.,20-50 Ω-1cm-1) observed so far in two outstanding kagome antiferromagnets, Mn3Sn and Mn3Ge. The spin triangular structure of Mn2.4Ga guarantees a nonzero Berry curvature while generates only a weak net moment in the kagome plane.Moreover, the anomalous Hall conductivity exhibits a sign reversal with the rotation of a small magnetic field, which can be ascribed to the field-controlled chirality of the spin triangular structure. Our theoretical calculation indicate that the large AHE in Mn2.4Ga originates from a significantly enhanced Berry curvature associated wiht the tuning of the Fermi level close to the Weyl points. These properties, together with the ability to manipulate moment orientations using a moderate external magnetic field, make Mn2.4Ga extremely exciting for future antiferromagnetic spintronics.

cond-mat.mtrl-sci↗
arXiv2024

Stellar cycle and evolution of polar spots in an M+WD binary

Stellar activity cycles reveal continuous relaxation and induction of magnetic fields. The activity cycle is typically traced through the observation of cyclic variations in total brightness or Ca H&K emission flux of stars, as well as cyclic variations of orbital periods of binary systems. In this work, we report the identification of a semi-detached binary system (TIC 16320250) consisting of a white dwarf (0.67 $M_{\odot}$) and an active M dwarf (0.56 $M_{\odot}$). The long-term multi-band optical light curves spanning twenty years revealed three repeated patterns, suggestive of a possible activity cycle of about ten years of the M dwarf. Light curve fitting indicates the repeated variation is caused by the evolution, particularly the motion, of polar spots. The significant Ca H&K, H$α$, ultra-violet, and X-ray emissions imply that the M dwarf is one of the most magnetically active stars. We propose that in the era of large time-domain photometric sky surveys (e.g., ASAS-SN, ZTF, LSST, Sitian), long-term light curve modeling can be a valuable tool for tracing and revealing stellar activity cycle, especially for stars in binary systems.

astro-ph.SR↗
arXiv2024

A spectral data release for 104 Type II Supernovae from the Tsinghua Supernova Group

We present 206 unpublished optical spectra of 104 type II supernovae obtained by the Xinglong 2.16m telescope and Lijiang 2.4m telescope during the period from 2011 to 2018, spanning the phases from about 1 to 200 days after the SN explosion. The spectral line identifications, evolution of line velocities and pseudo equivalent widths, as well as correlations between some important spectral parameters are presented. Our sample displays a large range in expansion velocities. For instance, the Fe~{\sc ii} $5169$ velocities measured from spectra at $t\sim 50$ days after the explosion vary from ${\rm 2000\ km\ s^{-1}}$ to ${\rm 5500\ km\ s^{-1}}$, with an average value of ${\rm 3872 \pm 949\ km\ s^{-1}}$. Power-law functions can be used to fit the velocity evolution, with the power-law exponent quantifying the velocity decline rate. We found an anticorrelation existing between H$β$ velocity at mid-plateau phase and its velocity decay exponent, SNe II with higher velocities tending to have smaller velocity decay rate. Moreover, we noticed that the velocity decay rate inferred from the Balmer lines (i.e., H$α$ and H$β$) have moderate correlations with the ratio of absorption to emission for H$α$ (a/e). In our sample, two objects show possibly flash-ionized features at early phases. Besides, we noticed that multiple high-velocity components may exist on the blue side of hydrogen lines of SN 2013ab, possibly suggesting that these features arise from complex line forming region. All our spectra can be found in WISeREP and Zenodo.

astro-ph.HE↗
arXiv2023

Unicron: Economizing Self-Healing LLM Training at Scale

Training large-scale language models is increasingly critical in various domains, but it is hindered by frequent failures, leading to significant time and economic costs. Current failure recovery methods in cloud-based settings inadequately address the diverse and complex scenarios that arise, focusing narrowly on erasing downtime for individual tasks without considering the overall cost impact on a cluster. We introduce Unicron, a workload manager designed for efficient self-healing in large-scale language model training. Unicron optimizes the training process by minimizing failure-related costs across multiple concurrent tasks within a cluster. Its key features include in-band error detection for real-time error identification without extra overhead, a dynamic cost-aware plan generation mechanism for optimal reconfiguration, and an efficient transition strategy to reduce downtime during state changes. Deployed on a 128-GPU distributed cluster, Unicron demonstrates up to a 1.9x improvement in training efficiency over state-of-the-art methods, significantly reducing failure recovery costs and enhancing the reliability of large-scale language model training.

cs.DC↗
arXiv2023

CaseGNN: Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphs

Legal case retrieval is an information retrieval task in the legal domain, which aims to retrieve relevant cases with a given query case. Recent research of legal case retrieval mainly relies on traditional bag-of-words models and language models. Although these methods have achieved significant improvement in retrieval accuracy, there are still two challenges: (1) Legal structural information neglect. Previous neural legal case retrieval models mostly encode the unstructured raw text of case into a case representation, which causes the lack of important legal structural information in a case and leads to poor case representation; (2) Lengthy legal text limitation. When using the powerful BERT-based models, there is a limit of input text lengths, which inevitably requires to shorten the input via truncation or division with a loss of legal context information. In this paper, a graph neural networks-based legal case retrieval model, CaseGNN, is developed to tackle these challenges. To effectively utilise the legal structural information during encoding, a case is firstly converted into a Text-Attributed Case Graph (TACG), followed by a designed Edge Graph Attention Layer and a readout function to obtain the case graph representation. The CaseGNN model is optimised with a carefully designed contrastive loss with easy and hard negative sampling. Since the text attributes in the case graph come from individual sentences, the restriction of using language models is further avoided without losing the legal context. Extensive experiments have been conducted on two benchmarks from COLIEE 2022 and COLIEE 2023, which demonstrate that CaseGNN outperforms other state-of-the-art legal case retrieval methods. The code has been released on https://github.com/yanran-tang/CaseGNN.

cs.IR↗
arXiv2023

GraphScope Flex: LEGO-like Graph Computing Stack

Graph computing has become increasingly crucial in processing large-scale graph data, with numerous systems developed for this purpose. Two years ago, we introduced GraphScope as a system addressing a wide array of graph computing needs, including graph traversal, analytics, and learning in one system. Since its inception, GraphScope has achieved significant technological advancements and gained widespread adoption across various industries. However, one key lesson from this journey has been understanding the limitations of a "one-size-fits-all" approach, especially when dealing with the diversity of programming interfaces, applications, and data storage formats in graph computing. In response to these challenges, we present GraphScope Flex, the next iteration of GraphScope. GraphScope Flex is designed to be both resource-efficient and cost-effective, while also providing flexibility and user-friendliness through its LEGO-like modularity. This paper explores the architectural innovations and fundamental design principles of GraphScope Flex, all of which are direct outcomes of the lessons learned during our ongoing development process. We validate the adaptability and efficiency of GraphScope Flex with extensive evaluations on synthetic and real-world datasets. The results show that GraphScope Flex achieves 2.4X throughput and up to 55.7X speedup over other systems on the LDBC Social Network and Graphalytics benchmarks, respectively. Furthermore, GraphScope Flex accomplishes up to a 2,400X performance gain in real-world applications, demonstrating its proficiency across a wide range of graph computing scenarios with increased effectiveness.

cs.DC↗
arXiv2023

Gene-MOE: A sparsely gated prognosis and classification framework exploiting pan-cancer genomic information

Benefiting from the advancements in deep learning, various genomic analytical techniques, such as survival analysis, classification of tumors and their subtypes, and exploration of specific pathways, have significantly enhanced our understanding of the biological mechanisms driving cancer. However, the overfitting issue, arising from the limited number of patient samples, poses a challenge in improving the accuracy of genome analysis by deepening the neural network. Furthermore, it remains uncertain whether novel approaches such as the sparsely gated mixture of expert (MOE) and self-attention mechanisms can improve the accuracy of genomic analysis. In this paper, we introduce a novel sparsely gated RNA-seq analysis framework called Gene-MOE. This framework exploits the potential of the MOE layers and the proposed mixture of attention expert (MOAE) layers to enhance the analysis accuracy. Additionally, it addresses overfitting challenges by integrating pan-cancer information from 33 distinct cancer types through pre-training.We pre-trained Gene-MOE on TCGA pan-cancer RNA-seq dataset with 33 cancer types. Subsequently, we conducted experiments involving cancer classification and survival analysis based on the pre-trained Gene-MOE. According to the survival analysis results on 14 cancer types, Gene-MOE outperformed state-of-the-art models on 12 cancer types. Through detailed feature analysis, we found that the Gene-MOE model could learn rich feature representations of high-dimensional genes. According to the classification results, the total accuracy of the classification model for 33 cancer classifications reached 95.8%, representing the best performance compared to state-of-the-art models. These results indicate that Gene-MOE holds strong potential for use in cancer classification and survival analysis.

cs.LG↗
arXiv2023

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

The integration of a SLAM algorithm with place recognition technology empowers it with the ability to mitigate accumulated errors and to relocalize itself. However, existing methods for point cloud-based place recognition predominantly rely on the matching of descriptors, which are mostly lidar-centric. These methods suffer from two major drawbacks: first, they cannot perform place recognition when the distance between two point clouds is significant, and second, they can only calculate the rotation angle without considering the offset in the X and Y directions. To overcome these limitations, we propose a novel local descriptor that is constructed around the Main Object. By using a geometric method, we can accurately calculate the relative pose. We have provided a theoretical analysis to demonstrate that this method can overcome the aforementioned limitations. Furthermore, we conducted extensive experiments on KITTI Odometry and KITTI360, which indicate that our proposed method has significant advantages over state-of-the-art methods.

cs.CV↗
arXiv2023

Wide binaries with white dwarf or neutron star companions discovered from Gaia DR3 and LAMOST

Gaia DR3 mission has identified and provided about 440,000 binary systems with orbital solutions, offering a valuable resource for searching binaries including a compact component. By combining the Gaia DR3 data with radial velocities (RVs) from the LAMOST spectroscopic survey, we identify three wide binaries possibly containing a compact object. For two of these sources with a main-sequence companion, no obvious excess is observed in the blue/red band of the Gaia DR3 XP spectra, and the LAMOST medium-resolution spectra exhibit clear single-lined features. The absence of an additional component from spectral disentangling analysis further suggests the presence of compact objects within these systems. On the other hand, the visible star of the third source is a stripped giant star. In contrast to most binaries including stripped stars, no emission line is detected in the optical spectra. The unseen star could potentially be a massive white dwarf or neutron star, but the possibility of an F-type dwarf star scenario cannot be ruled out. An examination of about ten binaries containing white dwarfs or neutron stars using both kinematic and chemical methods suggest most of these systems are located in the thin disk of the Milky Way.

astro-ph.SR↗
arXiv2023

TinyMetaFed: Efficient Federated Meta-Learning for TinyML

The field of Tiny Machine Learning (TinyML) has made substantial advancements in democratizing machine learning on low-footprint devices, such as microcontrollers. The prevalence of these miniature devices raises the question of whether aggregating their knowledge can benefit TinyML applications. Federated meta-learning is a promising answer to this question, as it addresses the scarcity of labeled data and heterogeneous data distribution across devices in the real world. However, deploying TinyML hardware faces unique resource constraints, making existing methods impractical due to energy, privacy, and communication limitations. We introduce TinyMetaFed, a model-agnostic meta-learning framework suitable for TinyML. TinyMetaFed facilitates collaborative training of a neural network initialization that can be quickly fine-tuned on new devices. It offers communication savings and privacy protection through partial local reconstruction and Top-P% selective communication, computational efficiency via online learning, and robustness to client heterogeneity through few-shot learning. The evaluations on three TinyML use cases demonstrate that TinyMetaFed can significantly reduce energy consumption and communication overhead, accelerate convergence, and stabilize the training process.

cs.LG↗
arXiv2023

Prompt-based Effective Input Reformulation for Legal Case Retrieval

Legal case retrieval plays an important role for legal practitioners to effectively retrieve relevant cases given a query case. Most existing neural legal case retrieval models directly encode the whole legal text of a case to generate a case representation, which is then utilised to conduct a nearest neighbour search for retrieval. Although these straightforward methods have achieved improvement over conventional statistical methods in retrieval accuracy, two significant challenges are identified in this paper: (1) Legal feature alignment: the usage of the whole case text as the input will generally incorporate redundant and noisy information because, from the legal perspective, the determining factor of relevant cases is the alignment of key legal features instead of whole text matching; (2) Legal context preservation: furthermore, since the existing text encoding models usually have an input length limit shorter than the case, the whole case text needs to be truncated or divided into paragraphs, which leads to the loss of the global context of legal information. In this paper, a novel legal case retrieval framework, PromptCase, is proposed to tackle these challenges. Firstly, legal facts and legal issues are identified and formally defined as the key features facilitating legal case retrieval based on a thorough study of the definition of relevant cases from a legal perspective. Secondly, with the determining legal features, a prompt-based encoding scheme is designed to conduct an effective encoding with language models. Extensive zero-shot experiments have been conducted on two benchmark datasets in legal case retrieval, which demonstrate the superior retrieval effectiveness of the proposed PromptCase. The code has been released on https://github.com/yanran-tang/PromptCase.

cs.IR↗
arXiv2023

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications.

cs.CV↗
arXiv2023

Smart Data Mapping for Connecting Power System Model and Geospatial Data

Knowing the geospatial locations of power system model elements and linking load models with end users and their communities are the foundation for analyzing system resilience and vulnerability to natural hazards. However, power system models and geospatial data for power grid assets are often developed asynchronously without close coordination. Creating a direct mapping between the two is a challenging task, mainly due to heterogeneous data structures, target uses, historical legacies, and human errors. This work aims to build an automatic data mapping workflow to connect the two, and to support energy grid resilience studies for Puerto Rico. The primary steps in this workflow include constructing graphs using geospatial data, and aligning them to the transmission networks defined in the power system data. The results have been evaluated against existing manual mapping practices for part of the Puerto Rico Power Grid model to illustrate the performance of such auto-mapping solutions.

eess.SY↗
arXiv2023

AutoHint: Automatic Prompt Optimization with Hint Generation

This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the key to applying this ability to specific tasks lies in developing high-quality prompts. Thus we propose a framework to inherit the merits of both in-context learning and zero-shot learning by incorporating enriched instructions derived from input-output demonstrations to optimize original prompt. We refer to the enrichment as the hint and propose a framework to automatically generate the hint from labeled data. More concretely, starting from an initial prompt, our method first instructs a LLM to deduce new hints for selected samples from incorrect predictions, and then summarizes from per-sample hints and adds the results back to the initial prompt to form a new, enriched instruction. The proposed method is evaluated on the BIG-Bench Instruction Induction dataset for both zero-shot and few-short prompts, where experiments demonstrate our method is able to significantly boost accuracy for multiple tasks.

cs.CL↗
arXiv2023

Prokaryotic genome editing based on the subtype I-B-Svi CRISPR-Cas system

Type I CRISPR-Cas systems are the most common among six types of CRISPR-Cas systems, however, non-self-targeting genome editing based on a single Cas3 of type I CRISPR-Cas systems has not been reported. Here, we present the subtype I-B-Svi CRISPR-Cas system (with three confirmed CRISPRs and a cas gene cluster) and genome editing based on this system found in Streptomyces virginiae IBL14. Importantly, like the animal-derived bacterial protein SpCas9 (1368 amino-acids), the single, compact, non-animal-derived bacterial protein SviCas3 (771 amino-acids) can also direct template-based microbial genome editing through the target cell's own homology-directed repair system, which breaks the view that the genome editing based on type I CRISPR-Cas systems requires a full Cascade. Notably, no off-target changes or indel-formation were detected in the analysis of potential off-target sites. This discovery broadens our understanding of the diversity of type I CRISPR-Cas systems and will facilitate new developments in genome editing tools.

q-bio.GN↗
arXiv2023

A Novel Efficient Signcryption Scheme for Resource-Constrained Smart Terminals in Cyber-Physical Power Systems

Most of the existing signcryption schemes generate pseudonym by key generation center (KGC) and usually choose bilinear pairing to construct authentication schemes. The drawback is that these schemes not only consume heavy computation and communication costs during information exchange, but also can not eliminate security risks due to not updating pseudonym, which do not work well for resource-constrained smart terminals in cyber-physical power systems (CPPSs). The main objective of this paper is to propose a novel efficient signcryption scheme for resource-constrained smart terminals. First, a dynamical pseudonym self-generation mechanism (DPSGM) is explored to achieve privacy preservation and avoid the source being linked. Second, combined with DPSGM, an efficient signcryption scheme based on certificateless cryptography (CLC) and elliptic curve cryptography (ECC) is designed, which reduces importantly computation and communication burden. Furthermore, under random oracle model (ROM), the confidentiality and non-repudiation of the proposed signcryption scheme are transformed into elliptic curve discrete logarithm and computational Diffie-Hellman problems that cannot be solved in polynomial time, which guarantees the security. Finally, the effectiveness and feasibility of the proposed signcryption scheme are confirmed by experimental analyses.

cs.CR↗
arXiv2023

Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics

Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the training process towards less frequent classes. However, they usually evaluate the performance on a balanced testing set or multiple independent testing sets having distinct distributions with the training data. Considering the testing data may have arbitrary distributions, existing evaluation strategies are unable to reflect the actual classification performance objectively. We set up novel evaluation benchmarks based on a series of testing sets with evolving distributions. A corpus of metrics are designed for measuring the accuracy, robustness, and bounds of algorithms for learning with long-tailed distribution. Based on our benchmarks, we re-evaluate the performance of existing methods on CIFAR10 and CIFAR100 datasets, which is valuable for guiding the selection of data rebalancing techniques. We also revisit existing methods and categorize them into four types including data balancing, feature balancing, loss balancing, and prediction balancing, according the focused procedure during the training pipeline.

cs.CV↗