arXiv subjects

Xiangping Wu

Publications and source records attributed to Xiangping Wu.

At least 19 recordsLinked to original sources

arXiv2026

FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts

Continual Learning for Named Entity Recognition (CLNER) enable models to incrementally learn new entity types without forgetting previously acquired ones. However, existing methods suffer from catastrophic forgetting and insufficient exploitation of shared information across tasks. This paper proposes FSE, a Fast-Slow Experts enhanced span-based NER model for CLNER. The shared fast expert learns token-level links to efficiently filter out unlikely spans, while the task-specific slow expert performs span classification only on the remaining candidates. It stabilizes learning by promoting knowledge sharing across tasks and maintains plasticity by reducing learning burden at each task. A length-decay negative sampling strategy to mitigate span imbalance is also introduced. Extensive experiments on OntoNotes and FewNERD synthestic datasets demonstrate that FSE achieves state-of-the-art performance in CLNER scenarios, with effectiveness of each component, empirical evidence of faster convergence and expected functionality of both experts.

cs.CL↗

arXiv2025

WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Existing approaches typically embed signals by manipulating token generation probabilities. Despite their effectiveness, these methods inherently face a trade-off between detectability and text quality: the signal strength and randomness required for robust watermarking tend to degrade the performance of downstream tasks. In this paper, we design a novel embedding scheme that controls seed pools to facilitate diverse parallel generation of watermarked text. Based on that scheme, we propose WaterSearch, a sentence-level, search-based watermarking framework adaptable to a wide range of existing methods. WaterSearch enhances text quality by jointly optimizing two key aspects: 1) distribution fidelity and 2) watermark signal characteristics. Furthermore, WaterSearch is complemented by a sentence-level detection method with strong attack robustness. We evaluate our method on three popular LLMs across ten diverse tasks. Extensive experiments demonstrate that our method achieves an average performance improvement of 51.01\% over state-of-the-art baselines at a watermark detectability strength of 95\%. In challenging scenarios such as short text generation and low-entropy output generation, our method yields performance gains of 47.78\% and 36.47\%, respectively. Moreover, under different attack senarios including insertion, synonym substitution and paraphrase attasks, WaterSearch maintains high detectability, further validating its robust anti-attack capabilities. Our code is available at \href{https://github.com/Yukang-Lin/WaterSearch}{https://github.com/Yukang-Lin/WaterSearch}.

cs.CL↗

arXiv2025

Scientific Objectives of the Xue-shan-mu-chang 15-meter Submillimeter Telescope

Submillimeter astronomy is poised to revolutionize our understanding of the Universe by revealing cosmic phenomena hidden from optical and near-infrared observations, particularly those associated with interstellar dust, molecular gas, and star formation. The Xue-shan-mu-chang 15-meter submillimeter telescope (XSMT-15m), to be constructed at a premier high-altitude site (4813 m) in Qinghai, China, marks a major milestone for Chinese astronomy, establishing the China mainland's first independently developed, world-class submillimeter facility. Equipped with state-of-the-art instruments, XSMT-15m will address a diverse range of frontier scientific questions spanning extragalactic astronomy, Galactic structure, time-domain astrophysics, and astrochemistry. In synergy with current and forthcoming observatories, XSMT-15m will illuminate the formation and evolution of galaxies, unravel the physical and chemical processes shaping the interstellar medium, and explore transient phenomena in the submillimeter regime. These capabilities will advance our understanding across extragalactic astronomy, Galactic ecology, astrochemistry, and time-domain astrophysics, inaugurating a new era for submillimeter research in China and the northern hemisphere.

astro-ph.GA↗

arXiv2025

GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay

The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence. However, continual fine-tuning LLMs across various domains often suffers from catastrophic forgetting, characterized by: 1) significant forgetting of their general capabilities, and 2) sharp performance declines in previously learned tasks. To simultaneously address both issues in a simple yet stable manner, we propose General Sample Replay (GeRe), a framework that use usual pretraining texts for efficient anti-forgetting. Beyond revisiting the most prevalent replay-based practices under GeRe, we further leverage neural states to introduce a enhanced activation states constrained optimization method using threshold-based margin (TM) loss, which maintains activation state consistency during replay learning. We are the first to validate that a small, fixed set of pre-collected general replay samples is sufficient to resolve both concerns--retaining general capabilities while promoting overall performance across sequential tasks. Indeed, the former can inherently facilitate the latter. Through controlled experiments, we systematically compare TM with different replay strategies under the GeRe framework, including vanilla label fitting, logit imitation via KL divergence and feature imitation via L1/L2 losses. Results demonstrate that TM consistently improves performance and exhibits better robustness. Our work paves the way for efficient replay of LLMs for the future. Our code and data are available at https://github.com/Qznan/GeRe.

cs.CL↗

arXiv2025

D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping

Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a fine-grained deformation perception model that focuses on Dual Dimensions of document horizontal-vertical-lines to improve document Dewarping called D2Dewarp. It can perceive distortion trends in different directions across document details. To combine the horizontal and vertical granularity features, an effective fusion module based on X and Y coordinate is designed to facilitate interaction and constraint between the two dimensions for feature complementarity. Due to the lack of annotated line features in current public dewarping datasets, we also propose an automatic fine-grained annotation method using public document texture images and automatic rendering engine to build a new large-scale distortion training dataset named DocDewarpHV. On three public Chinese and English benchmarks, both quantitative and qualitative results show that our method achieves better rectification results compared with the state-of-the-art methods. The code and dataset are available at https://github.com/xiaomore/D2Dewarp.

cs.CV↗

arXiv2025

The Chinese Pulsar Timing Array data release I. Single pulsar noise analysis

The Chinese Pulsar Timing Array (CPTA) has collected observations from 57 millisecond pulsars using the Five-hundred-meter Aperture Spherical Radio Telescope (FAST) for close to three years, for the purpose of searching for gravitational waves (GWs). To robustly search for ultra-low-frequency GWs, pulsar timing arrays (PTAs) need to use models to describe the noise from the individual pulsars. We report on the results from the single pulsar noise analysis of the CPTA data release I (DR1). Conventionally, power laws in the frequency domain are used to describe pulsar red noise and dispersion measurement (DM) variations over time. Employing Bayesian methods, we found the choice of number and range of frequency bins with the highest evidence for each pulsar individually. A comparison between a dataset using DM piecewise measured (DMX) values and a power-law Gaussian process to describe the DM variations shows strong Bayesian evidence in favour of the power-law model. Furthermore, we demonstrate that the constraints obtained from four independent software packages are very consistent with each other. The short time span of the CPTA DR1, paired with the large sensitivity of FAST, has proved to be a challenge for the conventional noise model using a power law. This mainly shows in the difficulty to separate different noise terms due to their covariances with each other. Nineteen pulsars are found to display covariances between the short-term white noise and long-term red and DM noise. With future CPTA datasets, we expect that the degeneracy can be broken. Finally, we compared the CPTA DR1 results against the noise properties found by other PTA collaborations. While we can see broad agreement, there is some tension between different PTA datasets for some of the overlapping pulsars. This could be due to the differences in the methods and frequency range compared to the other PTAs.

astro-ph.HE↗

arXiv2025

Document Image Rectification Bases on Self-Adaptive Multitask Fusion

Deformed document image rectification is essential for real-world document understanding tasks, such as layout analysis and text recognition. However, current multi-task methods -- such as background removal, 3D coordinate prediction, and text line segmentation -- often overlook the complementary features between tasks and their interactions. To address this gap, we propose a self-adaptive learnable multi-task fusion rectification network named SalmRec. This network incorporates an inter-task feature aggregation module that adaptively improves the perception of geometric distortions, enhances feature complementarity, and reduces negative interference. We also introduce a gating mechanism to balance features both within global tasks and between local tasks effectively. Experimental results on two English benchmarks (DIR300 and DocUNet) and one Chinese benchmark (DocReal) demonstrate that our method significantly improves rectification performance. Ablation studies further highlight the positive impact of different tasks on dewarping and the effectiveness of our proposed module.

cs.CV↗

arXiv2025

CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation

Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on preprocessing documents into segments to address input length constraints, resulting in the loss of critical semantic information across segments. To address this, we present CrossFormer, a transformer-based model featuring a novel cross-segment fusion module that dynamically models latent semantic dependencies across document segments, substantially elevating segmentation accuracy. Additionally, CrossFormer can replace rule-based chunk methods within the Retrieval-Augmented Generation (RAG) system, producing more semantically coherent chunks that enhance its efficacy. Comprehensive evaluations confirm CrossFormer's state-of-the-art performance on public text semantic segmentation datasets, alongside considerable gains on RAG benchmarks.

cs.CL↗

arXiv2025

The Chinese pulsar timing array data release I. Polarimetry for 56 millisecond pulsars

We present polarization pulse profiles for 56 millisecond pulsars (MSPs) monitored by the Chinese Pulsar Timing Array (CPTA) collaboration using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The observations centered at 1.25 GHz with a raw bandwidth of 500 MHz. Due to the high sensitivity ($\sim$16 K/Jy) of the FAST telescope and our long integration time, the high signal-to-noise ratio polarization profiles show features hardly detected before. Among 56 pulsars, the polarization profiles of PSRs J0406$+$3039, J1327$+$3423, and J2022$+$2534 were not previously reported. 80\% of MSPs in the sample show weak components below 3\% of peak flux, 25\% of pulsars show interpulse-like structures, and most pulsars show linear polarization position angle jumps. Six pulsars seem to be emitting for full rotation phase, with another thirteen pulsars being good candidates for such a 360$^\circ$ radiator. We find that the distribution of the polarization percentage in our sample is compatible with the normal pulsar distribution. Our detailed evaluation of the MSP polarization properties suggests that the wave propagation effects in the pulsar magnetosphere are important in shaping the MSP polarization pulse profiles.

astro-ph.HE↗

arXiv2024

The warm-hot intergalactic medium in inter-cluster filaments -- A forecast for HUBS observations based on eRASS1 superclusters

Cosmological simulations indicate that nearly half of the baryons in the nearby Universe are in the warm-hot intergalactic medium (WHIM) phase, and about a half them reside in cosmic filaments connecting galaxy clusters. Recent observational studies using stacked survey data and deep exposures of galaxy cluster outskirts have detected soft X-ray excesses associated with optically identified filaments. However, the physical characteristics of WHIM in filaments remain largely undetermined due to a lack of direct spectral diagnostics of individual targets, which are limited by the spectral resolution of current instruments in the soft X-ray band. We aim to select appropriate targets for WHIM characterization through pointing observations with the future Hot Universe Baryon Surveyor (HUBS) mission, which is designed with eV-level energy resolution in the 0.1-2.0 keV band and a one-square-degree field of view, thus complementing other planned microcalorimetry missions such as Athena. We built a sample of 1577 inter-cluster filaments based on the eRASS1 supercluster catalog and estimated their soft X-ray emission. Their modeled emission and geometrical properties were used to select candidate targets for HUBS observations. Four inter-cluster filaments were selected as the most appropriate candidates. By simulating and analyzing their mock observations, we demonstrated that with 200 ks HUBS exposure for each candidate, the gas properties of individual filaments can be accurately determined, with the temperature constrained to $\pm0.01$ keV, metallicity constrained to $\leq\pm0.03$ solar, and density constrained to $<\pm10\%$. Elemental abundances of O, Ne, Mg, and Fe can be measured separately, providing unprecedented insights into the chemical history of the filament gas. We also show that direct mapping of the WHIM distribution is promising with narrowband imaging of the Oviii line.

astro-ph.GA↗

arXiv2024

An evaluation of source-blending impact on the calibration of SKA EoR experiments

Twenty-one-centimetre signals from the Epoch of Reionization (EoR) are expected to be detected in the low-frequency radio window by the next-generation interferometers, particularly the Square Kilometre Array (SKA). However, precision data analysis pipelines are required to minimize the systematics within an infinitesimal error budget. Consequently, there is a growing need to characterize the sources of errors in EoR analysis. In this study, we identify one such error origin, namely source blending, which is introduced by the overlap of objects in the densely populated observing sky under SKA1-Low's unprecedented sensitivity and resolution, and evaluate its two-fold impact in both the spatial and frequency domains using a novel hybrid evaluation (HEVAL) pipeline combining end-to-end simulation with an analytic method to mimic EoR analysis pipelines. Sky models corrupted by source blending induce small but severe frequency-dependent calibration errors when coupled with astronomical foregrounds, impeding EoR parameter inference with strong additive residuals in the two-dimensional power spectrum space. We report that additive residuals from poor calibration against sky models with blending ratios of 5 and 0.5 per cent significantly contaminate the EoR window. In contrast, the sky model with a 0.05 per cent blending ratio leaves little residual imprint within the EoR window, therefore identifying a blending tolerance at approximately 0.05 per cent. Given that the SKA observing sky is estimated to suffer from an extended level of blending, strategies involving de-blending, frequency-dependent error mitigation, or a combination of both, are required to effectively attenuate the calibration impact of source-blending defects.

astro-ph.IM↗

arXiv2024

The Giant Radio Array for Neutrino Detection (GRAND) Collaboration -- Contributions to the 10th International Workshop on Acoustic and Radio EeV Neutrino Detection Activities (ARENA 2024)

This is an index of the contributions by the Giant Radio Array for Neutrino Detection (GRAND) Collaboration to the 10th International Workshop on Acoustic and Radio EeV Neutrino Detection Activities (ARENA 2024, University of Chicago, June 11-14, 2024). The contributions include an overview of GRAND in its present and future incarnations, methods of radio-detection that are being developed for them, and ongoing joint work between the GRAND and BEACON experiments.

astro-ph.IM↗

arXiv2024

GRANDlib: A simulation pipeline for the Giant Radio Array for Neutrino Detection (GRAND)

The operation of upcoming ultra-high-energy cosmic-ray, gamma-ray, and neutrino radio-detection experiments, like the Giant Radio Array for Neutrino Detection (GRAND), poses significant computational challenges involving the production of numerous simulations of particle showers and their detection, and a high data throughput. GRANDlib is an open-source software tool designed to meet these challenges. Its primary goal is to perform end-to-end simulations of the detector operation, from the interaction of ultra-high-energy particles, through -- by interfacing with external air-shower simulations -- the ensuing particle shower development and its radio emission, to its detection by antenna arrays and its processing by data-acquisition systems. Additionally, GRANDlib manages the visualization, storage, and retrieval of experimental and simulated data. We present an overview of GRANDlib to serve as the basis of future GRAND analyses.

astro-ph.IM↗

arXiv2023

ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization

Lowering the memory requirement in full-parameter training on large models has become a hot research area. MeZO fine-tunes the large language models (LLMs) by just forward passes in a zeroth-order SGD optimizer (ZO-SGD), demonstrating excellent performance with the same GPU memory usage as inference. However, the simulated perturbation stochastic approximation for gradient estimate in MeZO leads to severe oscillations and incurs a substantial time overhead. Moreover, without momentum regularization, MeZO shows severe over-fitting problems. Lastly, the perturbation-irrelevant momentum on ZO-SGD does not improve the convergence rate. This study proposes ZO-AdaMU to resolve the above problems by adapting the simulated perturbation with momentum in its stochastic approximation. Unlike existing adaptive momentum methods, we relocate momentum on simulated perturbation in stochastic gradient approximation. Our convergence analysis and experiments prove this is a better way to improve convergence stability and rate in ZO-SGD. Extensive experiments demonstrate that ZO-AdaMU yields better generalization for LLMs fine-tuning across various NLP tasks than MeZO and its momentum variants.

cs.LG↗

arXiv2023

TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement

The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distribution tables in other domains. To tackle this problem, we start from the essence of the table, which is a set of text arranged in rows and columns. Based on this, we propose a novel, light-weighted and robust Table Detection method based on Learning Text Arrangement, namely TDeLTA. TDeLTA takes the text blocks as input, and then models the arrangement of them with a sequential encoder and an attention module. To locate the tables precisely, we design a text-classification task, classifying the text blocks into 4 categories according to their semantic roles in the tables. Experiments are conducted on both the text blocks parsed from PDF and extracted by open-source OCR tools, respectively. Compared to several state-of-the-art methods, TDeLTA achieves competitive results with only 3.1M model parameters on the large-scale public datasets. Moreover, when faced with the cross-domain data under the 0-shot setting, TDeLTA outperforms baselines by a large margin of nearly 7%, which shows the strong robustness and transferability of the proposed model.

cs.CL↗

arXiv2023

Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning

The excellent generalization, contextual learning, and emergence abilities in the pre-trained large models (PLMs) handle specific tasks without direct training data, making them the better foundation models in the adversarial domain adaptation (ADA) methods to transfer knowledge learned from the source domain to target domains. However, existing ADA methods fail to account for the confounder properly, which is the root cause of the source data distribution that differs from the target domains. This study proposes an adversarial domain adaptation with confounder balancing for PLMs fine-tuning (ADA-CBF). The ADA-CBF includes a PLM as the foundation model for a feature extractor, a domain classifier and a confounder classifier, and they are jointly trained with an adversarial loss. This loss is designed to improve the domain-invariant representation learning by diluting the discrimination in the domain classifier. At the same time, the adversarial loss also balances the confounder distribution among source and unmeasured domains in training. Compared to existing ADA methods, ADA-CBF can correctly identify confounders in domain-invariant features, thereby eliminating the confounder biases in the extracted features from PLMs. The confounder classifier in ADA-CBF is designed as a plug-and-play and can be applied in the confounder measurable, unmeasurable, or partially measurable environments. Empirical results on natural language processing and computer vision downstream tasks show that ADA-CBF outperforms the newest GPT-4, LLaMA2, ViT and ADA methods.

cs.LG↗

arXiv2023

The Giant Radio Array for Neutrino Detection (GRAND) Collaboration -- Contributions to the 38th International Cosmic Ray Conference (ICRC 2023)

The Giant Radio Array for Neutrino Detection (GRAND) is an envisioned observatory of ultra-high-energy particles of cosmic origin, with energies in excess of 100 PeV. GRAND uses large surface arrays of autonomous radio-detection units to look for the radio emission from extensive air showers that are triggered by the interaction of ultra-high-energy cosmic rays, gamma rays, and neutrinos in the atmosphere or underground. In particular, for ultra-high-energy neutrinos, the future final phase of GRAND aims to be sensitive enough to discover them in spite of their plausibly tiny flux. Presently, three prototype GRAND radio arrays are in operation: GRANDProto300, in China, GRAND@Auger, in Argentina, and GRAND@Nancay, in France. Their goals are to field-test the design of the radio-detection units, understand the radio background to which they are exposed, and develop tools for diagnostic, data gathering, and data analysis. This list of contributions to the 38th International Cosmic Ray Conference (ICRC 2023) presents an overview of GRAND, in its present and future incarnations, and a look at the first data collected by GRANDProto13, the first phase of GRANDProto300.

hep-ex↗

arXiv2023

Pulsar discovery prospect of FASTA

The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has discovered more than 650 new pulsars, which account for 20% of our known Galactic pulsar population. In this paper, we estimate the prospect of a pulsar survey with a radio telescope array to be planned -- the FAST Array (FASTA), consists of six "FAST-type" telescopes. Such a sensitive radio telescope array would be a powerful instrument in probing the pulsar population deep into our Galaxy as well as in nearby galaxies. We simulate the FASTA pulsar discovery prospects with different Galactic pulsar population models and instrumental parameter combinations. We find that FASTA could detect tens of thousands of canonical pulsars and well-over thousands of millisecond pulsars. We also estimate the potential yield if the FASTA is used to search for pulsars from the nearby spiral galaxy M31, and find that it would probably discover around a hundred new radio pulsars.

astro-ph.HE↗