arXiv subjects

Yang Chen

Publications and source records attributed to Yang Chen.

At least 217 records · Page 12Linked to original sources

arXiv2025

Kalman Filtering of Stationary Graph Signals

In this paper, we propose a novel definition of stationary graph signals, formulated with respect to a symmetric graph shift, such as the graph Laplacian. We show that stationary graph signals can be generated by transmitting white noise through polynomial graph channels, and that their stationarity is preserved under polynomial channel transmission. In this paper, we also investigate Kalman filtering to dynamical systems characterized by polynomial state and observation matrices. We demonstrate that Kalman filtering maintains the stationarity of graph signals, while effectively incorporating both system dynamics and noise structure. In comparison to the static inverse filtering method and naive zero-signal strategy, the Kalman filtering procedure yields more accurate and adaptive signal estimates, highlighting its robustness and versatility in graph signal processing.

eess.SP↗

arXiv2025

The Impact of Automation on Risk-Taking: The Role of Sense of Agency

Automation significantly alters human behavior, particularly risk-taking. Previous researches have paid limited attention to the underlying characteristics of automation and their mechanisms of influence on risk-taking. This study investigated how automation affects risk-taking and examined the role of sense of agency therein. By quantifying sense of agency through subjective ratings, this research explored the impact of automation level and reliability level on risk-taking. The results of three experiments indicated that automation reduced the level of risk-taking; higher automation level was associated with lower sense of agency and lower risk-taking, with sense of agency playing a complete mediating role; higher automation reliability was associated with higher sense of agency and higher risk-taking, with sense of agency playing a partial mediating role. The study concludes that automation influences risk-taking, such that higher automation level or lower reliability is associated with a lower likelihood of risk-taking. Sense of agency mediates the impact of automation on risk-taking, and automation level and reliability have different effects on risk-taking.

cs.HC↗

arXiv2025

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded performance on unseen classes. This limitation is due to the inherent bias in the training data towards the seen classes. To address this issue, we propose a novel soft prompt learning method, named Mixture-of-Prompts Distillation (MoPD), which can effectively transfer useful knowledge from hard prompts manually hand-crafted (a.k.a. teacher prompts) to the learnable soft prompt (a.k.a. student prompt), thereby enhancing the generalization ability of soft prompts on unseen classes. Moreover, the proposed MoPD method utilizes a gating network that learns to select hard prompts used for prompt distillation. Extensive experiments demonstrate that the proposed MoPD method outperforms state-of-the-art baselines especially on on unseen classes.

cs.CV↗

arXiv2025

GeV Gamma-Rays from Molecular Clouds Illuminated by Particles Diffusing from the Adjacent Supernova Remnant G335.2+0.1 Confined in an Expanding Bubble

We report the detection of GeV gamma-ray emission likely associated with supernova remnant (SNR) G335.2+0.1 and the finding of a molecular cloud ($\sim20$--$30^\prime$ in angular size) that is very likely in physical contact with the SNR and responsible for the gamma-ray emission. Using the 16.8 yr Fermi-LAT data, an extended emission, with a significance of 13.5 $σ$ and a radius 0.24° in 0.2--500 GeV in the uniform-disk model, was found to the adjacent east of the SNR. With archival Mopra CO-line data, a large molecular clump at local-standard-of-rest velocity $\sim-48$ to $-43$ km s$^{-1}$ was revealed appearing coincident with the gamma-ray source. The SNR was found located in a cavity encircled by a 'C'-shaped ring-like molecular shell at $-45$ to $-43$ km s$^{-1}$. This morphological agreement, together with the position-velociy diagrams made along lines cutting across the cavity, suggests that the SNR was evolving in the expanding molecular bubble created by the stellar wind of the progenitor with a mass $\gtrsim 15 M_{\mathrm{sun}}$. The giant molecular cloud, visible at around $-46$ km s$^{-1}$, and the associated SNR are thus estimated to lie at a kinematic distance of 3.1 kpc, with the HI absorption taken into account. We suggest that the SNR has entered the radiative phase after the blastwave recently struck the cavity wall. With the evolutionary scenario of the SNR, we demonstrate that the gamma-ray emission reported here can be naturally interpreted by the hadronic interaction between the accelerated protons that escaped from the SNR shock and the eastern large molecular clump.

astro-ph.HE↗

arXiv2025

Challenging Bug Prediction and Repair Models with Synthetic Bugs

Bugs are essential in software engineering; many research studies in the past decades have been proposed to detect, localize, and repair bugs in software systems. Effectiveness evaluation of such techniques requires complex bugs, i.e., those that are hard to detect through testing and hard to repair through debugging. From the classic software engineering point of view, a hard-to-repair bug differs from the correct code in multiple locations, making it hard to localize and repair. Hard-to-detect bugs, on the other hand, manifest themselves under specific test inputs and reachability conditions. These two objectives, i.e., generating hard-to-detect and hard-to-repair bugs, are mostly aligned; a bug generation technique can change multiple statements to be covered only under a specific set of inputs. However, these two objectives are conflicting for learning-based techniques: A bug should have a similar code representation to the correct code in the training data to challenge a bug prediction model to distinguish them. The hard-to-repair bug definition remains the same but with a caveat: the more a bug differs from the original code, the more distant their representations are and easier to be detected. We propose BugFarm, to transform arbitrary code into multiple complex bugs. BugFarm leverages LLMs to mutate code in multiple locations (hard-to-repair). To ensure that multiple modifications do not notably change the code representation, BugFarm analyzes the attention of the underlying model and instructs LLMs to only change the least attended locations (hard-to-detect). Our comprehensive evaluation of 435k+ bugs from over 1.9M mutants generated by BUGFARM and two alternative approaches demonstrates our superiority in generating bugs that are hard to detect by learning-based bug prediction approaches and hard-to-repair by state-of-the-art learning-based program repair technique.

cs.SE↗

arXiv2025

Conformalized Tensor Completion with Riemannian Optimization

Tensor data, or multi-dimensional arrays, is a data format popular in multiple fields such as social network analysis, recommender systems, and brain imaging. It is not uncommon to observe tensor data containing missing values, and tensor completion aims at estimating the missing values given the partially observed tensor. Sufficient efforts have been spared on devising scalable tensor completion algorithms, but few on quantifying the uncertainty of the estimator. In this paper, we nest the uncertainty quantification (UQ) of tensor completion under a split conformal prediction framework and establish the connection of the UQ problem to a problem of estimating the missing propensity of each tensor entry. We model the data missingness of the tensor with a tensor Ising model parameterized by a low-rank tensor parameter. We propose to estimate the tensor parameter by maximum pseudo-likelihood estimation (MPLE) with a Riemannian gradient descent algorithm. Extensive simulation studies have been conducted to justify the validity of the resulting conformal interval. We apply our method to the regional total electron content (TEC) reconstruction problem. Supplemental materials of the paper are available online.

stat.ME↗

arXiv2025

Mirages and Large TeV Halo-Pulsar Offsets from Cosmic Ray Propagation

The study of extended $γ$-ray sources usually assumes symmetric diffusion of cosmic rays. However, recent observations of multiple sources near single pulsars and significant offsets between TeV halo centroids and their parent pulsars suggest that this assumption is overly simplistic. In this Letter, we demonstrate that asymmetric propagation of cosmic rays near their accelerators may create multiple TeV sources instead of a single symmetric source. This mechanism also explains the large offsets between TeV halo centroids and their pulsars. We demonstrate that several perplexing detected sources can be naturally explained without invoking additional invisible accelerators.

astro-ph.HE↗

arXiv2025

Semantic-guided LoRA Parameters Generation

Low-Rank Adaptation (LoRA) has demonstrated strong generalization capabilities across a variety of tasks for efficiently fine-tuning AI models, especially on resource-constrained edges. However, in real-world applications, edge users often exhibit task-specific preferences that are difficult to handle with a unified model trained under a closed-world assumption, and the challenge may further increase when there are significant domain shifts between training and deployment. Meanwhile, retraining/fine-tuning models for each user is also impractical due to its cost-intensive nature and privacy concerns over raw data utilization from edges. To address these challenges, we propose Semantic-guided LoRA Parameter Generation (SG-LoRA), the first of its kind framework to efficiently produce user-specific LoRA parameters without any additional training on user tasks or access to user-specific data. Concretely, SG-LoRA uses task descriptions as the semantic bridge, measuring their proximity to a set of known expert tasks in a shared embedding space. Based on this semantic guidance, it models the target task's LoRA parameter distribution to generate high-performing parameters for novel tasks. SG-LoRA enables the real-time construction of LoRA models aligned with individual intents by distilling knowledge from prominent LoRA experts and, meanwhile, offering a privacy-preserving solution for personalized model adaptation in a novel zero-shot open-world setting proposed in this work. Extensive experiments on multiple challenging tasks confirm the superior performance and remarkable adaptability of SG-LoRA. Code is available at https://github.com/keepgoingjkg/SG-LoRA.

cs.LG↗

arXiv2025

Meta-Inverse Reinforcement Learning for Mean Field Games via Probabilistic Context Variables

Designing suitable reward functions for numerous interacting intelligent agents is challenging in real-world applications. Inverse reinforcement learning (IRL) in mean field games (MFGs) offers a practical framework to infer reward functions from expert demonstrations. While promising, the assumption of agent homogeneity limits the capability of existing methods to handle demonstrations with heterogeneous and unknown objectives, which are common in practice. To this end, we propose a deep latent variable MFG model and an associated IRL method. Critically, our method can infer rewards from different yet structurally similar tasks without prior knowledge about underlying contexts or modifying the MFG model itself. Our experiments, conducted on simulated scenarios and a real-world spatial taxi-ride pricing problem, demonstrate the superiority of our approach over state-of-the-art IRL methods in MFGs.

cs.LG↗

arXiv2025

Adaptive Contrast Adjustment Module: A Clinically-Inspired Plug-and-Play Approach for Enhanced Fetal Plane Classification

Fetal ultrasound standard plane classification is essential for reliable prenatal diagnosis but faces inherent challenges, including low tissue contrast, boundary ambiguity, and operator-dependent image quality variations. To overcome these limitations, we propose a plug-and-play adaptive contrast adjustment module (ACAM), whose core design is inspired by the clinical practice of doctors adjusting image contrast to obtain clearer and more discriminative structural information. The module employs a shallow texture-sensitive network to predict clinically plausible contrast parameters, transforms input images into multiple contrast-enhanced views through differentiable mapping, and fuses them within downstream classifiers. Validated on a multi-center dataset of 12,400 images across six anatomical categories, the module consistently improves performance across diverse models, with accuracy of lightweight models increasing by 2.02 percent, accuracy of traditional models increasing by 1.29 percent, and accuracy of state-of-the-art models increasing by 1.15 percent. The innovation of the module lies in its content-aware adaptation capability, replacing random preprocessing with physics-informed transformations that align with sonographer workflows while improving robustness to imaging heterogeneity through multi-view fusion. This approach effectively bridges low-level image features with high-level semantics, establishing a new paradigm for medical image analysis under real-world image quality variations.

cs.CV↗

arXiv2025

Contrastive clustering based on regular equivalence for influential node identification in complex networks

Identifying influential nodes in complex networks is a fundamental task in network analysis with wide-ranging applications across domains. While deep learning has advanced node influence detection, existing supervised approaches remain constrained by their reliance on labeled data, limiting their applicability in real-world scenarios where labels are scarce or unavailable. While contrastive learning demonstrates significant potential for performance enhancement, existing approaches predominantly rely on multiple-embedding generation to construct positive/negative sample pairs. To overcome these limitations, we propose ReCC (\textit{r}egular \textit{e}quivalence-based \textit{c}ontrastive \textit{c}lustering), a novel deep unsupervised framework for influential node identification. We first reformalize influential node identification as a label-free deep clustering problem, then develop a contrastive learning mechanism that leverages regular equivalence-based similarity, which captures structural similarities between nodes beyond local neighborhoods, to generate positive and negative samples. This mechanism is integrated into a graph convolutional network to learn node embeddings that are used to differentiate influential from non-influential nodes. ReCC is pre-trained using network reconstruction loss and fine-tuned with a combined contrastive and clustering loss, with both phases being independent of labeled data. Additionally, ReCC enhances node representations by combining structural metrics with regular equivalence-based similarities. Extensive experiments demonstrate that ReCC outperforms state-of-the-art approaches across several benchmarks.

cs.SI↗

arXiv2025

Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language

Flexible tool selection reflects a complex cognitive ability that distinguishes humans from other species, yet computational models that capture this ability remain underdeveloped. We developed a framework using low-dimensional attribute representations to bridge visual tool perception and linguistic task understanding. We constructed a comprehensive dataset (ToolNet) containing 115 common tools labeled with 13 carefully designed attributes spanning physical, functional, and psychological properties, paired with natural language scenarios describing tool usage. Visual encoders (ResNet or ViT) extract attributes from tool images while fine-tuned language models (GPT-2, LLaMA, DeepSeek) derive required attributes from task descriptions. Our approach achieves 74% accuracy in tool selection tasks-significantly outperforming direct tool matching (20%) and smaller multimodal models (21%-58%), while approaching performance of much larger models like GPT-4o (73%) with substantially fewer parameters. Human evaluation studies validate our framework's alignment with human decision-making patterns, and generalization experiments demonstrate effective performance on novel tool categories. Ablation studies revealed that manipulation-related attributes (graspability, elongation, hand-relatedness) consistently prove most critical across modalities. This work provides a parameter-efficient, interpretable solution that mimics human-like tool cognition, advancing both cognitive science understanding and practical applications in tool selection tasks.

cs.CV↗

arXiv2025

HIP: Model-Agnostic Hypergraph Influence Prediction via Distance-Centrality Fusion and Neural ODEs

Predicting user influence in social networks is a critical problem, and hypergraphs, as a prevalent higher-order modeling approach, provide new perspectives for this task. However, the absence of explicit cascade or infection probability data makes it particularly challenging to infer influence in hypergraphs. To address this, we introduce HIP, a unified and model-independent framework for influence prediction without knowing the underlying spreading model. HIP fuses multi-dimensional centrality indicators with a temporally reinterpreted distance matrix to effectively represent node-level diffusion capacity in the absence of observable spreading. These representations are further processed through a multi-hop Hypergraph Neural Network (HNN) to capture complex higher-order structural dependencies, while temporal correlations are modeled using a hybrid module that combines Long Short-Term Memory (LSTM) networks and Neural Ordinary Differential Equations (Neural ODEs). Notably, HIP is inherently modular: substituting the standard HGNN with the advanced DPHGNN, and the LSTM with xLSTM, yields similarly strong performance, showcasing its architectural generality and robustness. Empirical evaluations across 14 real-world hypergraph datasets demonstrate that HIP consistently surpasses existing baselines in prediction accuracy, resilience, and identification of top influencers, all without relying on any diffusion trajectories or prior knowledge of the spreading model. These findings underline HIP's effectiveness and adaptability as a general-purpose solution for influence prediction in complex hypergraph environments.

cs.SI↗

arXiv2025

Think as Cardiac Sonographers: Marrying SAM with Left Ventricular Indicators Measurements According to Clinical Guidelines

Left ventricular (LV) indicator measurements following clinical echocardiog-raphy guidelines are important for diagnosing cardiovascular disease. Alt-hough existing algorithms have explored automated LV quantification, they can struggle to capture generic visual representations due to the normally small training datasets. Therefore, it is necessary to introduce vision founda-tional models (VFM) with abundant knowledge. However, VFMs represented by the segment anything model (SAM) are usually suitable for segmentation but incapable of identifying key anatomical points, which are critical in LV indicator measurements. In this paper, we propose a novel framework named AutoSAME, combining the powerful visual understanding of SAM with seg-mentation and landmark localization tasks simultaneously. Consequently, the framework mimics the operation of cardiac sonographers, achieving LV indi-cator measurements consistent with clinical guidelines. We further present fil-tered cross-branch attention (FCBA) in AutoSAME, which leverages relatively comprehensive features in the segmentation to enhance the heatmap regression (HR) of key points from the frequency domain perspective, optimizing the vis-ual representation learned by the latter. Moreover, we propose spatial-guided prompt alignment (SGPA) to automatically generate prompt embeddings guid-ed by spatial properties of LV, thereby improving the accuracy of dense pre-dictions by prior spatial knowledge. The extensive experiments on an echocar-diography dataset demonstrate the efficiency of each design and the superiori-ty of our AutoSAME in LV segmentation, landmark localization, and indicator measurements. The code will be available at https://github.com/QC-LIU-1997/AutoSAME.

cs.CV↗

arXiv2025

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) by integrating external knowledge bases, whose construction is often time-consuming and laborious. If an adversary extracts the knowledge base verbatim, it not only severely infringes the owner's intellectual property but also enables the adversary to replicate the application's functionality for unfair competition. Previous works on knowledge base extraction are limited either by low extraction coverage (usually less than 4%) in query-based attacks or by impractical assumptions of white-box access in embedding-based optimization methods. In this work, we propose CopyBreakRAG, an agent-based black-box attack that reasons from feedback and adaptively generates new adversarial queries for progressive extraction. By balancing exploration and exploitation through curiosity-driven queries and feedback-guided query refinement, our method overcomes the limitations of prior approaches and achieves significantly higher extraction coverage in realistic black-box settings. Experimental results show that CopyBreakRAG outperforms the state-of-the-art black-box approach by 45% on average in terms of chunk extraction ratio from applications built with mainstream RAG frameworks, and extracts over 70% of the data from the knowledge base in applications on commercial platforms including OpenAI's GPTs and ByteDance's Coze when essential protection is in place.

cs.CR↗

arXiv2025

Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering

Large Multimodal Models (LMMs) have shown generalized zero-shot capabilities in diverse domain question-answering (QA) tasks, including graph QA that involves complex graph topologies. However, most current approaches use only a single type of graph representation, namely Topology Representation Form (TRF), such as prompt-unified text descriptions or style-fixed visual styles. Those "one-size-fits-all" approaches fail to consider the specific preferences of different models or tasks, often leading to incorrect or overly long responses. To address this, we first analyze the characteristics and weaknesses of existing TRFs, and then design a set of TRFs, denoted by $F_{ZS}$, tailored to zero-shot graph QA. We then introduce a new metric, Graph Response Efficiency (GRE), which measures the balance between the performance and the brevity in graph QA. Built on these, we develop the DynamicTRF framework, which aims to improve both the accuracy and conciseness of graph QA. To be specific, DynamicTRF first creates a TRF Preference (TRFP) dataset that ranks TRFs based on their GRE scores, to probe the question-specific TRF preferences. Then it trains a TRF router on the TRFP dataset, to adaptively assign the best TRF from $F_{ZS}$ for each question during the inference. Extensive experiments across 7 in-domain algorithmic graph QA tasks and 2 out-of-domain downstream tasks show that DynamicTRF significantly enhances the zero-shot graph QA of LMMs in terms of accuracy

cs.CL↗

arXiv2025

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Multimodal Large Language Models (MLLMs) exhibit impressive performance across various visual tasks. Subsequent investigations into enhancing their visual reasoning abilities have significantly expanded their performance envelope. However, a critical bottleneck in the advancement of MLLMs toward deep visual reasoning is their heavy reliance on curated image-text supervision. To solve this problem, we introduce a novel framework, ``Reasoning-Rendering-Visual-Feedback'' (RRVF), that enables MLLMs to learn complex visual reasoning from only raw images. This framework builds on the ``Asymmetry of Verification'' principle, i.e., verifying the rendered output against the source image is substantially easier than performing deep visual reasoning to generate a faithful, structured representation such as code. We demonstrate that this relative ease provides an ideal reward signal for optimization via Reinforcement Learning (RL), thereby reducing reliance on image-text supervision. RRVF implements a closed-loop iterative process encompassing reasoning, rendering, and visual feedback components, enabling the model to perform complex reasoning, including self-correction through multi-turn interactions. This process is optimized end-to-end using the GRPO algorithm. Extensive evaluations are conducted on image-to-code generation across two diverse domains: data charts and web interfaces. The RRVF-trained model not only outperforms existing similarly sized open-source MLLMs and supervised fine-tuning baselines but also exhibits superior generalization. Notably, the model outperforms the more advanced MLLM used to generate visual feedback during training. Code is available at https://github.com/L-O-I/RRVF.

cs.CV↗

arXiv2025

Marine Chlorophyll Prediction and Driver Analysis based on LSTM-RF Hybrid Models

Marine chlorophyll concentration is an important indicator of ecosystem health and carbon cycle strength, and its accurate prediction is crucial for red tide warning and ecological response. In this paper, we propose a LSTM-RF hybrid model that combines the advantages of LSTM and RF, which solves the deficiencies of a single model in time-series modelling and nonlinear feature portrayal. Trained with multi-source ocean data(temperature, salinity, dissolved oxygen, etc.), the experimental results show that the LSTM-RF model has an R^2 of 0.5386, an MSE of 0.005806, and an MAE of 0.057147 on the test set, which is significantly better than using LSTM (R^2 = 0.0208) and RF (R^2 =0.4934) alone , respectively. The standardised treatment and sliding window approach improved the prediction accuracy of the model and provided an innovative solution for high-frequency prediction of marine ecological variables.

cs.LG↗