Searcharxiv⌕ Search

arXiv subjects

Jun Yan

Publications and source records attributed to Jun Yan.

At least 37 records · Page 2Linked to original sources
arXiv2026

O-RAN Xapps Conflict Prediction Using Graph Convolutional Networks

O-RAN hosts many intelligent applications known as eXtended Applications (xApps). xApps are applications that leverage advanced algorithms to make dynamic decisions for network optimization. Each application operates with distinct optimization objectives and is managed by independent operators while accessing shared network resources. Conflicts occur when a deployed xApp's objective interferes with another xApp, resulting in incompatible actions or decisions that may negatively impact network performance. The lack of a unified mechanism to coordinate and prioritize actions across different applications can lead to various types of conflicts. Conflict prediction in O-RAN is the proactive analytical process by which potential interactions or behaviors that may lead to conflicts between network applications are identified in advance, before they manifest in the operational system. In our paper, we introduce a novel data-driven Graph Convolutional Network-based method called GRAPH-based Intelligent xApp Conflict Prediction and Analysis (GRAPHICA). It predicts three types of conflicts and pinpoints the root causes. GRAPHICA captures the complex, hidden dependencies among the xApps, controlled parameters, and key performance indicators in O-RAN to predict potential conflicts. Then, it identifies the root causes contributing to the predicted conflicts. The proposed method is evaluated using highly imbalanced synthetic datasets, in which conflict instances constitute between 40 % and merely 10 % of the data. This evaluation setting is designed to reflect realistic operational environments where conflicts are infrequent, thereby enabling a comprehensive assessment of the model's performance under real-world conditions. Experimental results demonstrate an F1-score over 98 % for the synthesized datasets with varying levels of class imbalance.

cs.NI↗
arXiv2026

Beyond Normal References: Discriminative Few-Shot Anomaly Detection

This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomalous examples are available as references during inference. Existing FSAD methods rely on normal-only references through normality matching, ignoring the discriminative clues in anomalous references, while directly fitting both references can overfit to the seen anomalies. We introduce IDEAL, an intrinsic deviation learning framework that leverages both reference types to learn intrinsic deviation patterns characterizing generalizable abnormality as deviations from normality. IDEAL decomposes the learning process into two novel components: 1) a Normal Variation Eraser to suppress nuisance normal variations that may lead to noisy deviations from normality, thereby highlighting anomaly-relevant deviation representations; 2) an Intrinsic Deviation Encoder to decompose these denoised deviation representations into intrinsic deviation vectors capturing the most discriminative orthogonal deviation directions. At inference, IDEAL scores query-to-normal deviations preserved after projection onto the learned intrinsic deviation vectors, enabling generalization for both seen and unseen anomalies. Extensive experiments on eight real-world datasets show that IDEAL generalizes effectively to unseen anomalies and consistently outperforms existing state-of-the-art FSAD methods. Code and data will be available at \href{https://github.com/mala-lab/IDEAL}{https://github.com/mala-lab/IDEAL}.

cs.CV↗
arXiv2026

When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study

Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective is optimized. In practice, Stochastic Gradient Descent (SGD) optimizer remains the default optimization choice for AT, whereas adaptive optimizers often improve standard training but may yield inferior robustness. Recently, the Muon optimizer, which orthogonalizes matrix-valued updates via an approximate polar decomposition, has achieved notable success in large-scale training at a memory cost comparable to SGD. This raises a security-relevant question: \textit{can orthogonalized optimization improve AT under strong and heterogeneous threat models?} Focusing on this problem, we conduct a comprehensive theoretical and empirical study. Theoretically, we show that Muon imposes a spectral-norm stability ceiling on matrix updates, limiting uncontrolled spectral growth in the training dynamics without explicitly shrinking the learned weights. Empirically, across five architectures and three $\ell_p$ threat models ($\ell_\infty$, $\ell_1$, $\ell_2$) and their union, Muon is competitive with SGD on CNNs and substantially outperforms AdamW on both CNNs and ViTs. These results identify optimizer geometry as a security-relevant factor in adversarial training, while clarifying the empirical regimes in which orthogonalized updates are beneficial. Overall, our findings highlight optimizer design as a security-critical component of AT.

cs.LG↗
arXiv2026

Unobserved Heterogeneity in Threshold Regression Based on the Hitting Times of a Reflected Brownian Motion for Recurrent Hypoglycemia

Analyses of recurrent hypoglycemia are critical for effective treatment management in diabetic patients. Typically, within-subject dependency in such analyses is captured through subject-level frailty. Recent research has modeled recurrent hypoglycemia using the first hitting times of a reflected Brownian motion. A close examination of this approach reveals that it does not adequately account for varying frailties among individuals, which indicate notable heterogeneity. To address this gap, we propose a finite mixture model of the first hitting time distribution of the reflected Brownian motion. This model allows for component-specific regression coefficients and frailty parameters, providing nuanced insights into how risk factors differently affect patient subgroups. We employ a Bayesian framework for inference, utilizing Markov chain Monte Carlo for estimation. Model selection is conducted using the Deviance Information Criterion and the Logarithm of the Pseudo-Marginal Likelihood. The effectiveness of these criteria is assessed through simulation studies. Application to recurrent hypoglycemia modeling revealed two subgroups with different risk profiles, as reflected in their volatilities. Bayesian model comparison criteria favor the model with component specific regression coefficients for volatilities. The subgroup with lower volatility exhibits a larger variance and, hence, a greater level of heterogeneity.

stat.ME↗
arXiv2026

FedHPro: Federated Hyper-Prototype Learning via Gradient Matching

Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of learnable global class-wise prototypes to preserve underlying semantic knowledge across clients. The hyper-prototypes are optimized via gradient matching to align with class-relevant characteristics distilled directly from clients' real samples, rather than prototype-level descriptors. We further propose FedHPro, a Federated Hyper-Prototype Learning framework, to leverage hyper-prototypes to promote inter-class separability via mutual-contrastive learning with client-specific margin, while encouraging intra-class uniformity through a consistency penalty. Comprehensive experiments under diverse heterogeneous scenarios confirm that 1) hyper-prototypes produce a more semantically consistent global signal, and 2) FedHPro achieves state-of-the-art performance on several benchmark datasets. Code is available at \href{https://github.com/mala-lab/FedHPro}{https://github.com/mala-lab/FedHPro}.

cs.CV↗
arXiv2026

An Erdős--Szekeres type result for words with repeats

We prove an Erdős--Szekeres type result for finite words over $\mathbb{N}$ with repeated values. Specifically, we define a \emph{repeat} in a word to be an occurrence of a value which is not its first occurrence. We define an occurrence of a \emph{pattern} $π$ in a word $w$ to be a (not necessarily consecutive) subword of $w$ that is order isomorphic to $π$. In this note, we show that every word with $kn^6+1$ repeats contains one of the following patterns: $0^{k+2}$, $0011\cdots nn$, $nn\cdots1100$, $012 \cdots n012 \cdots n$, $012 \cdots nn\cdots 210$, $n\cdots 210012\cdots n$, $n\cdots 210n\cdots 210$. Moreover, when $k=1$, we show that this is best possible by constructing a word with $n^6$ repeats that does not contain any of these patterns.

math.CO↗
arXiv2026

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards

Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable rewards. Their outputs lack ground-truth answers, their trajectories span many tool-augmented decisions, and standard post-training offers little mechanism for turning past attempts into reusable experience. In this work, we argue that rubrics should serve not merely as final-answer evaluators, but as the shared interface that structures policy execution, judge feedback, and agent memory. Based on this view, we introduce RubricEM, a rubric-guided reinforcement learning framework that combines stagewise policy decomposition with reflection-based meta-policy evolution. RubricEM first makes research trajectories stage-aware by conditioning planning, evidence gathering, review, and synthesis on self-generated rubrics. It then assigns credit with Stage-Structured GRPO, which uses stagewise rubric judgments to provide denser semantic feedback for long-horizon optimization. In parallel, RubricEM trains a shared-backbone reflection meta-policy that distills judged trajectories into reusable rubric-grounded guidance for future attempts. The resulting RubricEM-8B achieves strong performance across four long-form research benchmarks, outperforming comparable open models and approaching proprietary deep-research systems. Beyond final performance, we perform thorough analyses to understand the key ingredients of RubricEM.

cs.CL↗
arXiv2026

ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs

The decline of global shellfish biodiversity poses a severe threat to coastal ecosystems. Although artificial intelligence (AI) technologies show potential for automated ecological monitoring, existing marine benthic datasets often lack adaptation to the complexities of real underwater environments (e.g., variable lighting conditions and diverse species postures), posing challenges for the robust generalization of vision models in practical ecological monitoring. To address this problem, we construct ShellfishNet, a comprehensive image benchmark dataset designed specifically for real-world ecological monitoring constraints. Comprising 8,691 images across 32 taxa, this dataset includes a curated subset annotated with descriptive captions. It is constructed through field photography and web scraping, encompassing samples from complex real-world environments. Based on this benchmark, we systematically evaluate 80 representative neural network models, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), State Space Models (SSMs), and Self-Supervised Learning (SSL) methods. Furthermore, we evaluate the performance of fine-grained visual categorization (FGVC) models and investigate the image captioning capabilities of several mainstream multimodal large language models (MLLMs). Meanwhile, we introduce image corruption benchmark tests to simulate common underwater degradation scenarios (turbidity, severe weather) and assess the robustness of vision models, enabling trustworthy decisions on ecological protection in the wild. ShellfishNet is dedicated to providing a data foundation and a model-evaluation benchmark for the intelligent monitoring of benthic organisms.

cs.CV↗
arXiv2026

SkillOS: Learning Skill Curation for Self-Evolving Agents

LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existing approaches either rely on manual skill curation, prescribe heuristic skill operations, or train for short-horizon skill operations. However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents. SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience. To provide learning signals for curation, we design composite rewards and train on grouped task streams based on skill-relevant task dependencies, where earlier trajectories update the SkillRepo, and later related tasks evaluate these updates. Across multi-turn agentic tasks and single-turn reasoning tasks, SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency, with the learned skill curator generalizing across different executor backbones and task domains. Further analyses show that the learned curator produces more targeted skill use, while the skills in SkillRepo evolve into more richly structured Markdown files that encode higher-level meta-skills over time.

cs.AI↗
arXiv2026

Quantum Knowledge Graph: Modeling Context-Dependent Triplet Validity

Knowledge graphs (KGs) are increasingly used to support large lan guage model (LLM) reasoning, but standard triplet-based KGs treat each relation as globally valid. In many settings, whether a relation should count as evidence depends on the context. We therefore formulate triplet validity as a triplet-specific function of context and refer to this formulation as a Quantum Knowledge Graph (QKG). We instantiate QKG in medicine using a diabetes-centered PrimeKG subgraph, whose 68,651 context-sensitive relations are further annotated with patient-group-specific constraints. We evaluate it in a reasoner--validator pipeline for medical question answering on a KG-grounded subset of MedReason containing 2,788 questions. With Haiku-4.5 as both the Reasoner and the Validator, KG-backed validation significantly improves over a no-validator baseline ($+0.61$ pp), and QKG with context matching yields the largest gain, outperforming both KG validation without context matching ($+0.79$ pp) and the no-validator baseline ($+1.40$ pp; paired McNemar, all $p<0.05$). Under a stronger validator (Qwen-3.6-Plus), the raw QKG gain over the no-validator baseline grows from $+1.40$ pp to $+5.96$ pp; the context-matching gap is non-significant ($p=0.73$) on the raw set but becomes borderline significant ($p=0.05$) after adjustment for knowledge leakage and suspicious questions, consistent with a benchmark-gold ceiling rather than a QKG limitation. Taken together, the results support the view that the value of a KG in LLM-based clinical reasoning lies not merely in storing medically related facts, but in representing whether those facts are applicable to the specific patient context. For reproducibility and further research, we release the curated QKG datasets and source code.\footnote{https://github.com/HKAI-Sci/QKG}

cs.CL↗
arXiv2026

A PDE formulation of Lyapunov stability for contact-type Hamilton-Jacobi equations

We study the Lyapunov stability of stationary solutions to contact-type Hamilton-Jacobi equations on a compact manifold. Previous works typically assume $C^3$ Tonelli Hamiltonians and characterize stability in terms of Mather measures. In this paper, we consider continuous, convex and coercive Hamiltonians and establish verifiable PDE-type criteria for both stability and instability. In particular, the dynamical conditions involving Mather measures are replaced by conditions expressed in terms of the critical value of the Hamiltonian and viscosity subsolutions. This provides a PDE-based framework for stability analysis and reveals connections with various asymptotic behaviors of viscosity solutions.

math.AP↗
arXiv2026

Generating Effective CoT Traces for Mitigating Causal Hallucination

Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (ECI), particularly in smaller models ($\leq$1.5B parameters). A promising approach to address this issue is to fine-tune them with Chain-of-Thought (CoT) traces. However, there is currently a lack of CoT trace dataset available for ECI. In this paper, we first investigate the essential criteria that effective CoT traces should possess to mitigate causal hallucination in smaller models. We then design a pipeline to generate CoT traces that meet these criteria. Moreover, since there is currently no metric for quantifying causal hallucination, we also introduce a new metric, the Causal Hallucination Rate (CHR), to quantify causal hallucination, guide the formulation of effective CoT trace criteria, and validate the effectiveness of our pipeline. Our experiments show that fine-tuning with the CoT traces generated by our pipeline not only substantially reduces causal hallucination in smaller LLMs but also improves mean accuracy. Moreover, the fine-tuned models exhibit strong cross-dataset and cross-difficulty generalization, as well as robustness under misleading intervention prompts.

cs.CL↗
arXiv2026

Gaussian Graphical Models for Functional Connectivity Analysis: A Statistical Review with Applications to Alzheimer's Disease

Functional connectivity analysis is an important tool for characterizing interactions among brain regions, particularly in studies of neurodegenerative disorders such as Alzheimer's disease (AD). Gaussian graphical models (GGMs) provide a promising statistical framework for estimating functional connectivity by capturing conditional dependence relationships among brain regions. Although a variety of regularized precision matrix estimators have been proposed to estimate sparse conditional dependency structures for GGMs, their comparative performance and practical implications for neuroimaging studies are not well understood. In this work, we present a comprehensive statistical review and empirical evaluation of widely used GGM estimation methods, including the graphical lasso (glasso), ridge-based glasso, graphical elastic net, adaptive glasso, smoothly clipped absolute deviation (SCAD), minimax concave penalty (MCP), constrained $\ell_1$ minimization for inverse matrix estimation (CLIME), and tuning-insensitive graph estimation and regression (TIGER). Their performance is evaluated through extensive data-driven simulations designed to reflect realistic neuroimaging settings, along with an application to an AD cohort study to illustrate methodological differences and their impact on downstream network analysis. In addition, a user-friendly R package, spice, is provided to facilitate implementation and enhance the reproducibility of empirical studies.

stat.ME↗
arXiv2026

Synonymous Codon Usage Bias Overrides Phylogeny to Reflect Convergent Frond Architecture in a Rapidly Radiating Fern Family Thelypteridaceae

Convergent evolution provides powerful evidence for natural selection, yet its molecular basis is typically sought in protein-coding amino acid substitutions. Whether adaptive pressures can drive the convergent evolution of synonymous codon usage bias (CUB) to override phylogenetic history remains a fundamental question. Here, we investigate this within the rapidly radiating fern family Thelypteridaceae by establishing a comparative framework that integrates chloroplast phylogenomics with dimensionality reduction of codon usage, morphological data, and divergence time estimation. Our results reveal that chloroplast CUB patterns are strikingly incongruent with the phylogeny of this family. Instead, they partition species into distinct clusters that strongly correlate with a convergently evolved morphological trait, lamina base architecture, a key adaptation whose radiation we date to the early Neogene. This convergent molecular signal is driven by a specific subset of photosynthesis-related genes (ndhJ, psaA, and psbD), which exhibit a high density of type-specific, third-position codon substitutions. These findings demonstrate that CUB can serve as a powerful, quantifiable indicator of adaptive history, revealing a cryptic layer of molecular convergence linked to the regulation of protein synthesis. Our work providing a new framework for uncovering adaptive histories obscured by complex evolutionary processes.

q-bio.PE↗
arXiv2026

A Cross-graph Tuning-free GNN Prompting Framework

GNN prompting aims to adapt models across tasks and graphs without requiring extensive retraining. However, most existing graph prompt methods still require task-specific parameter updates and face the issue of generalizing across graphs, limiting their performance and undermining the core promise of prompting. In this work, we introduce a Cross-graph Tuning-free Prompting Framework (CTP), which supports both homogeneous and heterogeneous graphs, can be directly deployed to unseen graphs without further parameter tuning, and thus enables a plug-and-play GNN inference engine. Extensive experiments on few-shot prediction tasks show that, compared to SOTAs, CTP achieves an average accuracy gain of 30.8% and a maximum gain of 54%, confirming its effectiveness and offering a new perspective on graph prompt learning.

cs.LG↗
arXiv2026

DTP-Attack: A decision-based black-box adversarial attack on trajectory prediction

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with gradient information and rely on rigid physical constraints, limiting real-world applicability. We propose DTP-Attack, a decision-based black-box adversarial attack framework tailored for trajectory prediction systems. Our method operates exclusively on binary decision outputs without requiring model internals or gradients, making it practical for real-world scenarios. DTP-Attack employs a novel boundary walking algorithm that navigates adversarial regions without fixed constraints, naturally maintaining trajectory realism through proximity preservation. Unlike existing approaches, our method supports both intention misclassification attacks and prediction accuracy degradation. Extensive evaluation on nuScenes and Apolloscape datasets across state-of-the-art models including Trajectron++ and Grip++ demonstrates superior performance. DTP-Attack achieves 41 - 81% attack success rates for intention misclassification attacks that manipulate perceived driving maneuvers with perturbations below 0.45 m, and increases prediction errors by 1.9 - 4.2 for accuracy degradation. Our method consistently outperforms existing black-box approaches while maintaining high controllability and reliability across diverse scenarios. These results reveal fundamental vulnerabilities in current trajectory prediction systems, highlighting urgent needs for robust defenses in safety-critical autonomous driving applications.

cs.RO↗
arXiv2026

Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report

Electronic health records (EHRs) and other real-world clinical data are essential for clinical research, medical artificial intelligence, and life science, but their sharing is severely limited by privacy, governance, and interoperability constraints. These barriers create persistent data silos that hinder multi-center studies, large-scale model development, and broader biomedical discovery. Existing privacy-preserving approaches, including multi-party computation and related cryptographic techniques, provide strong protection but often introduce substantial computational overhead, reducing the efficiency of large-scale machine learning and foundation-model training. In addition, many such methods make data usable for restricted computation while leaving them effectively invisible to clinicians and researchers, limiting their value in workflows that still require direct inspection, exploratory analysis, and human interpretation. We propose a real-world-data transformation framework for privacy-preserving sharing of structured clinical records. Instead of converting data into opaque representations, our approach constructs transformed numeric views that preserve medical semantics and major statistical properties while, under a clearly specified threat model, provably breaking direct linkage between those views and protected patient-level attributes. Through collaboration between computer scientists and the AI agent \textbf{SciencePal}, acting as a constrained tool inventor under human guidance, we design three transformation operators that are non-reversible within this threat model, together with an additional mixing strategy for high-risk scenarios, supported by theoretical analysis and empirical evaluation under reconstruction, record linkage, membership inference, and attribute inference attacks.

cs.CR↗
arXiv2026

Ordered Ramsey and Turán numbers of alternating paths and their variants

An ordered graph is a graph whose vertex set is equipped with a total order. The ordered complete graph $K_N^<$ is the complete graph with vertex set $[N]$ equipped with the natural ordering of the integers. Given an ordered graph $H$, the ordered Ramsey number $R_<(H)$ is the smallest integer $N$ such that every red/blue edge-colouring of $K_N^<$ contains a monochromatic copy of $H$ with vertices appearing in the same relative order as in $H$. Balko, Cibulka, Král, and Kynčl asked whether, among all ordered paths on $n$ vertices, the ordered Ramsey number is minimised by the alternating path $\mathrm{AP}_n$ -- the ordered path with vertex set $[n]$ such that the vertices encountered along the path are $1, n, 2, n - 1,3, n-2,\dots$. Motivated by this problem, we make progress on establishing the value of $R_<(\mathrm{AP}_n)$ by proving that \[ R_{<}(\mathrm{AP}_n)\leq \left(2+\frac{\sqrt{2}}{2}+o(1)\right)n. \] We then use similar methods to determine the exact ordered Turán number of $\mathrm{AP}_n$, and study the ordered Ramsey and Turán numbers of several related ordered paths.

math.CO↗