arXiv subjects

Haiyan Wang

Publications and source records attributed to Haiyan Wang.

At least 19 recordsLinked to original sources

arXiv2026

A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics

Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database querying, key performance indicator (KPI) analysis, demand forecasting, and performance diagnosis require heterogeneous expertise spanning data engineering, operations research, and domain knowledge. In this work, we propose an agentic system for supply chain analytics that bridges the gap between business decision-making and technical expertise, where a coordinator agent interprets user intent and delegates sub-tasks to specialized agents. The system supports both exploratory analysis and deterministic workflows, enabling planners to transition between ad hoc questions and structured processes. Domain logic is encapsulated within specialist agents and prompts, yielding a scalable, modular, and auditable design and lowering the cost of functional extension through prompt-centric development. We evaluate the proposed architecture on a test environment that replicates multi-echelon inventory management operations. Results show that our multi-agent design achieves a 90\% accuracy, which is competitive with a single agent baseline while reducing input token usage by roughly fourfold, substantially improving scalability and cost-efficiency. Furthermore, we provide case studies to demonstrate interpretable suboptimality detection and automated forecast optimization, illustrating how agentic architectures can effectively combine open-ended exploratory analysis and deterministic supply chain analytics workflows, and provide a practical pathway toward more accessible and extensible decision-support systems.

cs.AI↗

arXiv2026

Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection

Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents and fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), which uses inter-document relationships to improve extraction accuracy in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. Our experiments demonstrate up to 98% precision in outlier detection across 6 scientific domains, reducing hallucinations and letting researchers focus on genuinely ambiguous cases.

cs.AI↗

arXiv2026

A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization

Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.

cs.AI↗

arXiv2026

200 mm Wafer-Scale Monolithic 3D Integration of Atomic Layer-Deposited Oxide Semiconductors

Monolithic 3D (M3D) integration offers a pathway to overcome the scaling limits of conventional silicon complementary metal-oxide-semiconductor (CMOS) technology by extending dense vertical stacking of multifunctional logic and memory devices. Here, we demonstrate wafer-scale M3D integration of three tiers of atomic-layer-deposited (ALD) indium oxide (InOx)-based devices (>100,000 fabricated), including ferroelectric, enhancement-mode, and depletion-mode field-effect transistors, on 200 mm silicon wafers. We achieve threshold voltage standard deviation as low as 0.04 V, average electron mobility up to 91.6 cm2V-1s-1, and fully functional cross-tier circuits. A four-tier 3D computing-in-memory (CIM) accelerator targeting large language model workloads is developed using a custom InOx process design kit, delivering 1.4x to 2.9x speedup and comparable energy-delay product improvements over 2D baselines. These results establish ALD InOx M3D integration as a scalable and CMOS-compatible platform for next-generation artificial intelligence hardware and advanced electronics.

physics.app-ph↗

arXiv2026

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations, while overlooking the generation quality after unlearning. This can easily lead to hallucinated or rigid responses, thereby affecting the usability and safety of the unlearned model. To address this issue, we propose ASRU, a controllable multimodal unlearning framework that incorporates generation quality as a core evaluation objective. ASRU first induces initial refusal behavior through activation redirection, and then optimizes fine-grained refusal boundaries using a customized reward function, thereby achieving a better trade-off between target knowledge unlearning and model utility. Experiments on Qwen3-VL show that ASRU significantly improves unlearning effectiveness (+24.6%) on average and generation quality (5.8X) on average while effectively preserving model utility, using only a small amount of retained supervision data.

cs.CL↗

arXiv2026

Monogenic functions over real alternative *-algebras: the several hypercomplex variables case

The notion of monogenic (or regular) functions, which is a correspondence of holomorphic functions, has been studied extensively in hypercomplex analysis, including quaternionic, octonionic, and Clifford analysis. Recently, the concept of monogenic functions over real alternative $\ast$-algebras has been introduced to unify several classical monogenic functions theories. In this paper, we initiate the study of monogenic functions of several hypercomplex variables over real alternative $\ast$-algebras, which naturally extends the theory of several complex variables to a very general setting. In this new setting, we develop some fundamental properties, such as Bochner-Martinelli formula, Plemelj-Sokhotski formula, and Hartogs extension theorem.

math.CV↗

arXiv2026

PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models

Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge injection or complete subject-level deletion, which fail to capture realistic, personalized deletion requests that require fine-grained factual control. In this paper, we introduce PPU-Bench, a real-world and fine-tuning-free benchmark for personalized partial unlearning in MLLMs. PPU-Bench contains 24K multimodal and unimodal samples derived from pre-existing knowledge of 500 public figures under three progressively challenging settings: Complete, Selective, and Personalized unlearning. The benchmark evaluates whether methods can remove target knowledge while preserving non-target facts, model utility, and cross-modal consistency. Extensive experiments show that Complete Unlearning often suppresses visual identity rather than factual knowledge, while Selective and Personalized Unlearning expose significant forget--retain trade-offs and challenges in intra-subject factual boundaries. Robustness analysis under cross-image and prompt-based attacks reveals distinct vulnerabilities across different unlearning settings. Motivated by these findings, we propose Boundary-Aware Optimization (BAO), which explicitly models intra-subject forget-retain boundaries. Experimental results on two representative methods demonstrate that BAO can effectively enforce intra-subject factual boundaries.

cs.CV↗

arXiv2026

Sharing is caring: data sharing in multi-agent supply chains

Modern supply networks are complex interconnected systems. Multi-agent models are increasingly explored to optimise their performance. Most research assumes agents will have full observability of the system by having a single policy represent the agents, which seems unrealistic as this requires companies to share their data. The alternative is to develop a Hidden-Markov Process with separate policies, making the problem challenging to solve. In this paper, we propose a multi-agent system where the factory agent can share information downstream, increasing the observability of the environment. It can choose to share no information, lie, tell the truth or combine these in a mixed strategy. The results show that data sharing can boost the performance, especially when combined with a cooperative reward shaping. In the high demand scenario there is limited ability to change the strategy and therefore no data sharing approach benefits both agents. However, lying benefits the factory enough for an overall system improvement, although only by a relatively small amount compared to the overall reward. In the low demand scenario, the most successful data sharing is telling the truth which benefits all actors significantly.

cs.MA↗

arXiv2026

Necessary and Sufficient Conditions for Existence of a Unique Solution to Gamma Moment Closure for the Stochastic Ricker Equation

This paper investigates the stochastic Ricker difference equation $X_{n+1} = X_n \exp(r(1-X_n)) \varepsilon_n$, where $X_n$ is a random variable representing the population size and $\{\varepsilon_n\}$ denotes independent random perturbations with $E[\varepsilon_n] = 1$ and $E[\varepsilon_n^2] = v > 1$. We derive a closed system of difference equations for the mean and variance of $X_n$ using the Gamma moment-closure technique and numerically verify the validity of the Gamma moment-closure approximation. By constructing an auxiliary function, we establish the necessary and sufficient condition, $v < (2 - e^{-r})^2$, for the existence of the positive unique feasible equilibrium. We further verify its local stability with numerical analysis. Monte Carlo simulations confirm the validity of the Gamma moment approximation and illustrate how the interplay between the intrinsic growth rate $r$ and noise intensity $v$ determines population persistence. The results provide a unified theoretical framework for analyzing stochastic Gamma dynamics, offering new biological insights into the stabilizing and destabilizing effects of environmental variability.

math.PR↗

arXiv2025

Low-Complexity Channel Estimation for Internet of Vehicles AFDM Communications With Sparse Bayesian Learning

Affine frequency division multiplexing (AFDM) has been considered as a promising waveform to enable high-reliable connectivity in the internet of vehicles. However, accurate channel estimation is critical and challenging to achieve the expected performance of the AFDM systems in doubly-dispersive channels. In this paper, we propose a sparse Bayesian learning (SBL) framework for AFDM systems and develop a dynamic grid update strategy with two off-grid channel estimation methods, i.e., grid-refinement SBL (GR-SBL) and grid-evolution SBL (GE-SBL) estimators. Specifically, the GR-SBL employs a localized grid refinement method and dynamically updates grid for a high-precision estimation. The GE-SBL estimator approximates the off-grid components via first-order linear approximation and enables gradual grid evolution for estimation accuracy enhancement. Furthermore, we develop a distributed computing scheme to decompose the large-dimensional channel estimation model into multiple manageable small-dimensional sub-models for complexity reduction of GR-SBL and GE-SBL, denoted as distributed GR-SBL (D-GR-SBL) and distributed GE-SBL (D-GE-SBL) estimators, which also support parallel processing to reduce the computational latency. Finally, simulation results demonstrate that the proposed channel estimators outperform existing competitive schemes. The GR-SBL estimator achieves high-precision estimation with fine step sizes at the cost of high complexity, while the GE-SBL estimator provides a better trade-off between performance and complexity. The proposed D-GR-SBL and D-GE-SBL estimators effectively reduce complexity and maintain comparable performance to GR-SBL and GE-SBL estimators, respectively.

cs.IT↗

arXiv2025

Secure Multi-Key Homomorphic Encryption with Application to Privacy-Preserving Federated Learning

Multi-Key Homomorphic Encryption (MKHE), proposed by Lopez-Alt et al. (STOC 2012), allows for performing arithmetic computations directly on ciphertexts encrypted under distinct keys. Subsequent works by Chen and Dai et al. (CCS 2019) and Kim and Song et al. (CCS 2023) extended this concept by proposing multi-key BFV/CKKS variants, referred to as the CDKS scheme. These variants incorporate asymptotically optimal techniques to facilitate secure computation across multiple data providers. In this paper, we identify a critical security vulnerability in the CDKS scheme when applied to multiparty secure computation tasks, such as privacy-preserving federated learning (PPFL). In particular, we show that CDKS may inadvertently leak plaintext information from one party to others. To mitigate this issue, we propose a new scheme, SMHE (Secure Multi-Key Homomorphic Encryption), which incorporates a novel masking mechanism into the multi-key BFV and CKKS frameworks to ensure that plaintexts remain confidential throughout the computation. We implement a PPFL application using SMHE and demonstrate that it provides significantly improved security with only a modest overhead in homomorphic evaluation. For instance, our PPFL model based on multi-key CKKS incurs less than a 2\times runtime and communication traffic increase compared to the CDKS-based PPFL model. The code is publicly available at https://github.com/JiahuiWu2022/SMHE.git.

cs.CR↗

arXiv2025

Revisiting Broken Windows Theory

We revisit the longstanding question of how physical structures in urban landscapes influence crime. Leveraging machine learning-based matching techniques to control for demographic composition, we estimate the effects of several types of urban structures on the incidence of violent crime in New York City and Chicago. We additionally contribute to a growing body of literature documenting the relationship between perception of crime and actual crime rates by separately analyzing how the physical urban landscape shapes subjective feelings of safety. Our results are twofold. First, in consensus with prior work, we demonstrate a "broken windows" effect in which abandoned buildings, a sign of social disorder, are associated with both greater incidence of crime and a heightened perception of danger. This is also true of types of urban structures that draw foot traffic such as public transportation infrastructure. Second, these effects are not uniform within or across cities. The criminogenic effects of the same structure types across two cities differ in magnitude, degree of spatial localization, and heterogeneity across subgroups, while within the same city, the effects of different structure types are confounded by different demographic variables. Taken together, these results emphasize that one-size-fits-all approaches to crime reduction are untenable and policy interventions must be specifically tailored to their targets.

cs.LG↗

arXiv2025

Structure-aware Hypergraph Transformer for Diagnosis Prediction in Electronic Health Records

Electronic Health Records (EHR) systematically organize patient health data through standardized medical codes, serving as a comprehensive and invaluable source for predictive modeling. Graph neural networks (GNNs) have demonstrated effectiveness in modeling interactions between medical codes within EHR. However, existing GNN-based methods are inadequate due to: a) their reliance on pairwise relations fails to capture the inherent higher-order dependencies in clinical data, and b) the localized message-passing scheme limits representation power. To address these issues, this paper proposes a novel Structure-aware HyperGraph Transformer (SHGT) framework following three-fold ideas: a) employing a hypergraph structural encoder to capture higher-order interactions among medical codes, b) integrating the Transformer architecture to reason over the entire hypergraph, and c) designing a tailored loss function incorporating hypergraph reconstruction to preserve the hypergraph's original structure. Experiments on real-world EHR datasets demonstrate that the proposed SHGT outperforms existing state-of-the-art models on diagnosis prediction.

cs.LG↗

arXiv2025

Privacy-Preserving Federated Learning Scheme with Mitigating Model Poisoning Attacks: Vulnerabilities and Countermeasures

The privacy-preserving federated learning schemes based on the setting of two honest-but-curious and non-colluding servers offer promising solutions in terms of security and efficiency. However, our investigation reveals that these schemes still suffer from privacy leakage when considering model poisoning attacks from malicious users. Specifically, we demonstrate that the privacy-preserving computation process for defending against model poisoning attacks inadvertently leaks privacy to one of the honest-but-curious servers, enabling it to access users' gradients in plaintext. To address both privacy leakage and model poisoning attacks, we propose an enhanced privacy-preserving and Byzantine-robust federated learning (PBFL) scheme, comprising three components: (1) a two-trapdoor fully homomorphic encryption (FHE) scheme to bolster users' privacy protection; (2) a novel secure normalization judgment method to preemptively thwart gradient poisoning; and (3) an innovative secure cosine similarity measurement method for detecting model poisoning attacks without compromising data privacy. Our scheme guarantees privacy preservation and resilience against model poisoning attacks, even in scenarios with heterogeneous, non-IID (Independently and Identically Distributed) datasets. Theoretical analyses substantiate the security and efficiency of our scheme, and extensive experiments corroborate the efficacy of our private attacks. Furthermore, the experimental results demonstrate that our scheme accelerates training speed while reducing communication overhead compared to the state-of-the-art PBFL schemes.

cs.CR↗

arXiv2025

Affine Frequency Division Multiplexing Over Wideband Doubly-Dispersive Channels With Time-Scaling Effects

The recently proposed affine frequency division multiplexing (AFDM) modulation has been considered as a promising technology for narrowband doubly-dispersive channels. However, the time-scaling effects, i.e., pulse widening and pulse shortening phenomena, in extreme wideband doubly-dispersive channels have not been considered in the literatures. In this paper, we investigate such wideband transmission and develop an efficient transmission structure with chirp-periodic prefix (CPP) and chirp-periodic suffix (CPS) for AFDM system. We derive the input-output relationship of AFDM system under time-scaled wideband doubly-dispersive channels and demonstrate the sparsity in discrete affine Fourier (DAF) domain equivalent channels. We further optimize the AFDM chirp parameters to accommodate the time-scaling characteristics in wideband doubly-dispersive channels and verify the superiority of the derived chirp parameters by pairwise error probability (PEP) analysis. We also develop an efficient cross domain distributed orthogonal approximate message passing (CD-D-OAMP) algorithm for AFDM symbol detection and analyze its corresponding state evolution. By analyzing the detection complexity of CD-D-OAMP detector and evaluating the error performance of AFDM systems based on simulations, we demonstrate that the AFDM system with our optimized chirp parameters outperforms the existing competitive modulation schemes in time-scaled wideband doubly-dispersive channels. Moreover, our proposed CD-D-OAMP detector can achieve the desirable trade-off between the complexity and performance, while supporting parallel computing to significantly reduce the computational latency.

cs.PF↗

arXiv2025

Detecting transitions from steady states to chaos with gamma distribution

In this paper, we introduce a novel method to identify transitions from steady states to chaos in stochastic models, specifically focusing on the logistic and Ricker equations by leveraging the gamma distribution to describe the underlying population. We begin by showing that when the variance is sufficiently small, the stochastic equations converge to their deterministic counterparts. Our analysis reveals that the stochastic equations exhibit two distinct branches of the intrinsic growth rate, corresponding to alternative stable states characterized by higher and lower growth rates. Notably, while the logistic model does not show a transition from a steady state to chaos, the Ricker model undergoes such a transition when the shape parameter of the gamma distribution is small. These findings not only enhance our understanding of the dynamic behavior in biological populations but also provide a robust framework for detecting chaos in complex systems.

math.PR↗

arXiv2025

Genetic Transformer-Assisted Quantum Neural Networks for Optimal Circuit Design

We introduce Genetic Transformer Assisted Quantum Neural Networks (GTQNNs), a hybrid learning framework that combines a transformer encoder with a shallow variational quantum circuit and automatically fine tunes the circuit via the NSGA-II multi objective genetic algorithm. The transformer reduces high-dimensional classical data to a compact, qubit sized representation, while NSGA-II searches for Pareto optimal circuits that (i) maximize classification accuracy and (ii) minimize primitive gate count an essential constraint for noisy intermediate-scale quantum (NISQ) hardware. Experiments on four benchmarks (Iris, Breast Cancer, MNIST, and Heart Disease) show that GTQNNs match or exceed state of the art quantum models while requiring much fewer gates for most cases. A hybrid Fisher information analysis further reveals that the trained networks operate far from barren plateaus; the leading curvature directions increasingly align with the quantum subspace as the qubit budget grows, confirming that the transformer front end has effectively condensed the data. Together, these results demonstrate that GTQNNs deliver competitive performance with a quantum resource budget well suited to present-day NISQ devices.

quant-ph↗

arXiv2025

Analysis of Discrete Stochastic Population Models with Normal Distribution

This paper analyzes a stochastic logistic difference equation under the assumption that the population distribution follows a normal distribution. Our focus is on the mathematical relationship between the average growth rate and a newly introduced concept, the uniform structural growth rate, which captures how growth is influenced by the internal distributional structure of the population. We derive explicit relationships linking the uniform structural growth rate to the parameters of the normal distribution and the variance of a small stochastic perturbation. The analysis reveals the existence of two distinct branches of the uniform structural growth rate, corresponding to alternative population states characterized by higher and lower growth rates. This duality provides deeper insights into the dynamics of population growth under stochastic influences. A sufficient condition for the existence of two uniform structural growth rates is established and rigorously proved, demonstrating that there exist infeasible intervals where no uniform structural growth rate can be defined. We also explore the biological significance of these findings, emphasizing the role of stochastic perturbations and the distribution in shaping population dynamics.

math.PR↗