arXiv subjects

Xin Zhang

Publications and source records attributed to Xin Zhang.

At least 487 records · Page 27Linked to original sources

arXiv2025

SmartFL: Semantics Based Probabilistic Fault Localization

Testing-based fault localization has been a research focus in software engineering in the past decades. It localizes faulty program elements based on a set of passing and failing test executions. Since whether a fault could be triggered and detected by a test is related to program semantics, it is crucial to model program semantics in fault localization approaches. Existing approaches either consider the full semantics of the program (e.g., mutation-based fault localization and angelic debugging), leading to scalability issues, or ignore the semantics of the program (e.g., spectrum-based fault localization), leading to imprecise localization results. Our key idea is: by modeling only the correctness of program values but not their full semantics, a balance could be reached between effectiveness and scalability. To realize this idea, we introduce a probabilistic model by efficient approximation of program semantics and several techniques to address scalability challenges. Our approach, SmartFL(SeMantics bAsed pRobabilisTic Fault Localization), is evaluated on a real-world dataset, Defects4J 2.0. The top-1 statement-level accuracy of our approach is {14\%}, which improves 130\% over the best SBFL and MBFL methods. The average time cost is {205} seconds per fault, which is half of SBFL methods. After combining our approach with existing approaches using the CombineFL framework, the performance of the combined approach is significantly boosted by an average of 10\% on top-1, top-3, and top-5 accuracy compared to state-of-the-art combination methods.

cs.SE↗

arXiv2025

GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a combination of both. Previous work has attempted to adopt multimodal large language models (MLLMs) to realize UMR using only text data. However, our preliminary experiments demonstrate that more diverse multimodal training data can further unlock the potential of MLLMs. Despite its effectiveness, the existing multimodal training data is highly imbalanced in terms of modality, which motivates us to develop a training data synthesis pipeline and construct a large-scale, high-quality fused-modal training dataset. Based on the synthetic training data, we develop the General Multimodal Embedder (GME), an MLLM-based dense retriever designed for UMR. Furthermore, we construct a comprehensive UMR Benchmark (UMRB) to evaluate the effectiveness of our approach. Experimental results show that our method achieves state-of-the-art performance among existing UMR methods. Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.

cs.CL↗

arXiv2025

MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach

Face editing modifies the appearance of face, which plays a key role in customization and enhancement of personal images. Although much work have achieved remarkable success in text-driven face editing, they still face significant challenges as none of them simultaneously fulfill the characteristics of diversity, controllability and flexibility. To address this challenge, we propose MuseFace, a text-driven face editing framework, which relies solely on text prompt to enable face editing. Specifically, MuseFace integrates a Text-to-Mask diffusion model and a semantic-aware face editing model, capable of directly generating fine-grained semantic masks from text and performing face editing. The Text-to-Mask diffusion model provides \textit{diversity} and \textit{flexibility} to the framework, while the semantic-aware face editing model ensures \textit{controllability} of the framework. Our framework can create fine-grained semantic masks, making precise face editing possible, and significantly enhancing the controllability and flexibility of face editing models. Extensive experiments demonstrate that MuseFace achieves superior high-fidelity performance.

cs.CV↗

arXiv2025

Object Isolated Attention for Consistent Story Visualization

Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline. One of the main difficulties is maintaining character consistency while creating natural and contextually fitting scenes--an area where many existing methods struggle. In this paper, we propose an enhanced Transformer module that uses separate self attention and cross attention mechanisms, leveraging prior knowledge from pre-trained diffusion models to ensure logical scene creation. The isolated self attention mechanism improves character consistency by refining attention maps to reduce focus on irrelevant areas and highlight key features of the same character. Meanwhile, the isolated cross attention mechanism independently processes each character's features, avoiding feature fusion and further strengthening consistency. Notably, our method is training-free, allowing the continuous generation of new characters and storylines without re-tuning. Both qualitative and quantitative evaluations show that our approach outperforms current methods, demonstrating its effectiveness.

cs.CV↗

arXiv2025

Nanohertz gravitational waves from a quasar-based supermassive black hole binary population model as dark sirens

Recently, several pulsar timing array (PTA) projects have detected evidence of the existence of a stochastic gravitational wave background (SGWB) in the nanohertz frequency band, providing confidence in detecting individual supermassive black hole binaries (SMBHBs) in the future. Nanohertz GWs emitted by inspiraling SMBHBs encode the luminosity distances of SMBHBs. They can serve as dark sirens to explore the cosmic expansion history via a statistical method to obtain the redshift information of GW sources' host galaxies using galaxy catalogs. The theoretical analysis of the dark siren method relies on the modeling of the population of SMBHBs. Using a population model consistent with the latest SGWB observations is essential, as the SGWB provides significant information about the distribution of SMBHBs. In this work, we employ a quasar-based model, which can self-consistently account for the SGWB amplitude, to estimate the population of SMBHBs. We constrain the Hubble constant using the mock GW data from different detection cases of PTAs in the future. Our results show that a PTA consisting of 100 pulsars with a white noise level of 20 ns could measure the Hubble constant with a precision close to $1\%$ over a 10-year observation period, and a PTA with 200 pulsars may achieve this goal over a 5-year observation period. The results indicate that modeling the SMBHB population significantly influences the analysis of dark sirens, and SMBHB dark sirens have the potential to be developed as a valuable cosmological probe.

astro-ph.CO↗

arXiv2025

Molecular Insights into Yb(III) Speciation in Sulfate-Bearing Hydrothermal Fluids from X-ray Absorption Spectra Informed by ab initio Molecular Dynamics

Rare earth elements (REEs) are critical for advanced technologies, yet in hydrothermal aqueous solutions the molecular level details of their interaction with ligands that control their geochemical transport and deposition remain poorly understood. This study elucidates the coordination behavior of Yb(III) in sulfate-rich hydrothermal fluids using in situ extended X-ray absorption fine structure (EXAFS) spectroscopy and ab initio molecular dynamics (AIMD) simulations. By integrating multi-angle EXAFS with AIMD-derived constraints, we precisely resolve Yb(III) coordination structures and ligand interactions under hydrothermal conditions. At room temperature, Yb (III) is coordinated by five water molecules and two sulfate ligands (coordination number, CN = 8), forming a distorted square antiprism geometry. Increasing temperature induces progressive dehydration, reducing the hydration shell and favoring stronger sulfate complexation. At 200 Celsius, sulfate ligands reorganize around Yb(III), shifting its geometry to a capped dodecahedron (CN = 7). At 300 Celsius, sulfate binding dominates, leading to structural reorganization that parallels the onset of sulfate mineral precipitation, consistent with the retrograde solubility of REE sulfates. These findings provide direct molecular-scale evidence that sulfate acts as both a transport and deposition ligand, critically influencing REE mobility in geochemical environments. Our results can also help to refine thermodynamic models of REE speciation in high-temperature hydrothermal fluids and improve our understanding of REE ore formation processes in nature.

physics.chem-ph↗

arXiv2025

CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration

With the increasing demand for efficient and flexible robotic exploration solutions, Reinforcement Learning (RL) is becoming a promising approach in the field of autonomous robotic exploration. However, current RL-based exploration algorithms often face limited environmental reasoning capabilities, slow convergence rates, and substantial challenges in Sim-To-Real (S2R) transfer. To address these issues, we propose a Curriculum Learning-based Transformer Reinforcement Learning Algorithm (CTSAC) aimed at improving both exploration efficiency and transfer performance. To enhance the robot's reasoning ability, a Transformer is integrated into the perception network of the Soft Actor-Critic (SAC) framework, leveraging historical information to improve the farsightedness of the strategy. A periodic review-based curriculum learning is proposed, which enhances training efficiency while mitigating catastrophic forgetting during curriculum transitions. Training is conducted on the ROS-Gazebo continuous robotic simulation platform, with LiDAR clustering optimization to further reduce the S2R gap. Experimental results demonstrate the CTSAC algorithm outperforms the state-of-the-art non-learning and learning-based algorithms in terms of success rate and success rate-weighted exploration time. Moreover, real-world experiments validate the strong S2R transfer capabilities of CTSAC.

cs.RO↗

arXiv2025

A robust score test in g-computation for covariate adjustment in randomized clinical trials leveraging different variance estimators via influence functions

G-computation has become a widely used robust method for estimating unconditional (marginal) treatment effects with covariate adjustment in the analysis of randomized clinical trials. Statistical inference in this context typically relies on the Wald test or Wald interval, which can be easily implemented using a consistent variance estimator. However, existing literature suggests that when sample sizes are small or when parameters of interest are near boundary values, Wald-based methods may be less reliable due to type I error rate inflation and insufficient interval coverage. In this article, we propose a robust score test for g-computation estimators in the context of two-sample treatment comparisons. The proposed test is asymptotically valid under simple and stratified (biased-coin) randomization schemes, even when regression models are misspecified. These test statistics can be conveniently computed using existing variance estimators, and the corresponding confidence intervals have closed-form expressions, making them convenient to implement. Through extensive simulations, we demonstrate the superior finite-sample performance of the proposed method. Finally, we apply the proposed method to reanalyze a completed randomized clinical trial. The new analysis using our proposed score test achieves statistical significance, whilst reducing the issue of type I error inflation.

stat.ME↗

arXiv2025

A search for sterile neutrinos in interacting dark energy models using DESI baryon acoustic oscillations and DES supernovae data

Sterile neutrinos can influence the evolution of the universe, and thus cosmological observations can be used to search for sterile neutrinos. In this study, we utilized the latest baryon acoustic oscillations data from DESI, combined with the cosmic microwave background data from Planck and the five-year supernova data from DES, to constrain the interacting dark energy (IDE) models involving both cases of massless and massive sterile neutrinos. We consider four typical forms of the interaction term $Q=βH ρ_{\rm de}$, $Q=βH ρ_{\rm c}$, $Q=βH_{0} ρ_{\rm de}$, and $Q=βH_{0} ρ_{\rm c}$, respectively. Our analysis indicates that the current data provide only a hint of the existence of massless sterile neutrinos (as dark radiation) at about the $1σ$ level. In contrast, no evidence supports the existence of massive sterile neutrinos. Furthermore, in IDE models, the inclusion of (massless/massive) sterile neutrinos has a negligible impact on the constraint of the coupling parameter $β$. The IDE model of $Q=βH ρ_{\rm c}$ with sterile neutrinos does not favor an interaction. However, the other three IDE models with sterile neutrinos support an interaction in which dark energy decays into dark matter.

astro-ph.CO↗

arXiv2025

Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors

Conventional Federated Learning (FL) involves collaborative training of a global model while maintaining user data privacy. One of its branches, decentralized FL, is a serverless network that allows clients to own and optimize different local models separately, which results in saving management and communication resources. Despite the promising advancements in decentralized FL, it may reduce model generalizability due to lacking a global model. In this scenario, managing data and model heterogeneity among clients becomes a crucial problem, which poses a unique challenge that must be overcome: How can every client's local model learn generalizable representation in a decentralized manner? To address this challenge, we propose a novel Decentralized FL technique by introducing Synthetic Anchors, dubbed as DeSA. Based on the theory of domain adaptation and Knowledge Distillation (KD), we theoretically and empirically show that synthesizing global anchors based on raw data distribution facilitates mutual knowledge transfer. We further design two effective regularization terms for local training: 1) REG loss that regularizes the distribution of the client's latent embedding with the anchors and 2) KD loss that enables clients to learn from others. Through extensive experiments on diverse client data distributions, we showcase the effectiveness of DeSA in enhancing both inter- and intra-domain accuracy of each client.

cs.LG↗

arXiv2025

Enhanced Multi-Tuple Extraction for Alloys: Integrating Pointer Networks and Augmented Attention

Extracting high-quality structured information from scientific literature is crucial for advancing material design through data-driven methods. Despite the considerable research in natural language processing for dataset extraction, effective approaches for multi-tuple extraction in scientific literature remain scarce due to the complex interrelations of tuples and contextual ambiguities. In the study, we illustrate the multi-tuple extraction of mechanical properties from multi-principal-element alloys and presents a novel framework that combines an entity extraction model based on MatSciBERT with pointer networks and an allocation model utilizing inter- and intra-entity attention. Our rigorous experiments on tuple extraction demonstrate impressive F1 scores of 0.963, 0.947, 0.848, and 0.753 across datasets with 1, 2, 3, and 4 tuples, confirming the effectiveness of the model. Furthermore, an F1 score of 0.854 was achieved on a randomly curated dataset. These results highlight the model's capacity to deliver precise and structured information, offering a robust alternative to large language models and equipping researchers with essential data for fostering data-driven innovations.

cs.CL↗

arXiv2025

M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification

Multi-modal fusion holds great promise for integrating information from different modalities. However, due to a lack of consideration for modal consistency, existing multi-modal fusion methods in the field of remote sensing still face challenges of incomplete semantic information and low computational efficiency in their fusion designs. Inspired by the observation that the visual language pre-training model CLIP can effectively extract strong semantic information from visual features, we propose M$^3$amba, a novel end-to-end CLIP-driven Mamba model for multi-modal fusion to address these challenges. Specifically, we introduce CLIP-driven modality-specific adapters in the fusion architecture to avoid the bias of understanding specific domains caused by direct inference, making the original CLIP encoder modality-specific perception. This unified framework enables minimal training to achieve a comprehensive semantic understanding of different modalities, thereby guiding cross-modal feature fusion. To further enhance the consistent association between modality mappings, a multi-modal Mamba fusion architecture with linear complexity and a cross-attention module Cross-SS2D are designed, which fully considers effective and efficient information interaction to achieve complete fusion. Extensive experiments have shown that M$^3$amba has an average performance improvement of at least 5.98\% compared with the state-of-the-art methods in multi-modal hyperspectral image classification tasks in the remote sensing field, while also demonstrating excellent training efficiency, achieving a double improvement in accuracy and efficiency. The code is released at https://github.com/kaka-Cao/M3amba.

cs.CV↗

arXiv2025

Distributed quantum algorithm for the dihedral hidden subgroup problem

To address the issue of excessive quantum resource requirements in Kuperberg's algorithm for the dihedral hidden subgroup problem, this paper proposes a distributed algorithm based on the function decomposition. By splitting the original function into multiple subfunctions and distributing them to multiple quantum nodes for parallel processing, the algorithm significantly reduces the quantum circuit depth and qubit requirements for individual nodes. Theoretical analysis shows that when $n\gg t$ ($t$ is the number of quantum nodes), the time complexity of the distributed version is optimized from $2^{O(\sqrt{n})}$ (the traditional algorithm's complexity) to $2^{o(\sqrt{n-t})}$. Furthermore, we carried out the simulation on the Qiskit platform, and the accuracy of the algorithm is verified. Compared to the original algorithm, the distributed version not only reduces the influence of circuit depth and noise, but also improves the probability of measurement success.

quant-ph↗

arXiv2025

Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models

Human values and their measurement are long-standing interdisciplinary inquiry. Recent advances in AI have sparked renewed interest in this area, with large language models (LLMs) emerging as both tools and subjects of value measurement. This work introduces Generative Psychometrics for Values (GPV), an LLM-based, data-driven value measurement paradigm, theoretically grounded in text-revealed selective perceptions. The core idea is to dynamically parse unstructured texts into perceptions akin to static stimuli in traditional psychometrics, measure the value orientations they reveal, and aggregate the results. Applying GPV to human-authored blogs, we demonstrate its stability, validity, and superiority over prior psychological tools. Then, extending GPV to LLM value measurement, we advance the current art with 1) a psychometric methodology that measures LLM values based on their scalable and free-form outputs, enabling context-specific measurement; 2) a comparative analysis of measurement paradigms, indicating response biases of prior methods; and 3) an attempt to bridge LLM values and their safety, revealing the predictive power of different value systems and the impacts of various values on LLM safety. Through interdisciplinary efforts, we aim to leverage AI for next-generation psychometrics and psychometrics for value-aligned AI.

cs.CL↗

arXiv2025

Revisiting holographic dark energy from the perspective of multi-messenger gravitational wave astronomy: future joint observations with short gamma-ray bursts

The advent of third-generation (3G) gravitational-wave (GW) detectors opens new opportunities for multi-messenger observations of binary neutron star merger events, holding significant potential for probing the history of cosmic expansion. In this paper, we investigate the holographic dark energy (HDE) model by using the future GW standard siren data observed from the 3G GW detectors and the short $γ$-ray burst THESEUS-like detector joint observations. We find that GW data alone can achieve a relatively precise estimation of the Hubble constant, with precision of $0.2\%$-$0.6\%$, but its ability to constrain other cosmological parameters remains limited. Nonetheless, since the GW data can break parameter degeneracies generated by the mainstream EM observations, CMB + BAO + SN (CBS), GW standard sirens play a crucial role in enhancing the accuracy of parameter estimation. With the addition of GW data to CBS, the constraints on cosmological parameters $H_0$, $c$ and $Ω_{\rm{m}}$ can be improved by $63\%$-$88\%$, $27\%$-$44\%$ and $55\%$-$70\%$. In summary, observations of GW standard sirens from 3G GW detectors could be pivotal in helping solve the Hubble tension and probe the fundamental nature of dark energy.

astro-ph.CO↗

arXiv2025

Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator

Dataset distillation has emerged as a technique aiming to condense informative features from large, natural datasets into a compact and synthetic form. While recent advancements have refined this technique, its performance is bottlenecked by the prevailing class-specific synthesis paradigm. Under this paradigm, synthetic data is optimized exclusively for a pre-assigned one-hot label, creating an implicit class barrier in feature condensation. This leads to inefficient utilization of the distillation budget and oversight of inter-class feature distributions, which ultimately limits the effectiveness and efficiency, as demonstrated in our analysis. To overcome these constraints, this paper presents the Inter-class Feature Compensator (INFER), an innovative distillation approach that transcends the class-specific data-label framework widely utilized in current dataset distillation methods. Specifically, INFER leverages a Universal Feature Compensator (UFC) to enhance feature integration across classes, enabling the generation of multiple additional synthetic instances from a single UFC input. This significantly improves the efficiency of the distillation budget. Moreover, INFER enriches inter-class interactions during the distillation, thereby enhancing the effectiveness and generalizability of the distilled data. By allowing for the linear interpolation of labels similar to those in the original dataset, INFER meticulously optimizes the synthetic data and dramatically reduces the size of soft labels in the synthetic dataset to almost zero, establishing a new benchmark for efficiency and effectiveness in dataset distillation. In practice, INFER demonstrates state-of-the-art performance across benchmark datasets. For instance, in the ipc = 50 setting on ImageNet-1k with the same compression level, it outperforms SRe2L by 34.5% using ResNet18.

cs.CV↗

arXiv2025

Process-based Self-Rewarding Language Models

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance, which is constrained by the upper limit of human performance. Therefore, Self-Rewarding method has been proposed, where LLMs generate training data by rewarding their own outputs. However, the existing self-rewarding paradigm is not effective in mathematical reasoning scenarios and may even lead to a decline in performance. In this work, we propose the Process-based Self-Rewarding pipeline for language models, which introduces long-thought reasoning, step-wise LLM-as-a-Judge, and step-wise preference optimization within the self-rewarding paradigm. Our new paradigm successfully enhances the performance of LLMs on multiple mathematical reasoning benchmarks through iterative Process-based Self-Rewarding, demonstrating the immense potential of self-rewarding to achieve LLM reasoning that may surpass human capabilities.

cs.CL↗

arXiv2025

SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image Generation

Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer from semantic entanglement, including concept entanglement and improper attribute binding, leading to significant text-image inconsistency. We identify that semantic entanglement arises when certain regions of the latent features attend to incorrect concept and attribute tokens. In this work, we propose the Semantic Protection Diffusion Model (SPDiffusion) to address both concept entanglement and improper attribute binding using only a text prompt as input. The SPDiffusion framework introduces a novel concept region extraction method SP-Extraction to resolve region entanglement in cross-attention, along with SP-Attn, which protects concept regions from the influence of irrelevant attributes and concepts. To evaluate our method, we test it on existing benchmarks, where SPDiffusion achieves state-of-the-art results, demonstrating its effectiveness.

cs.CV↗