Searcharxiv⌕ Search

arXiv subjects

Junming Liu

Publications and source records attributed to Junming Liu.

At least 37 records · Page 2Linked to original sources
arXiv2025

Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE

Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration, however, also introduces a new and critical attack surface. Attackers can exploit these components by injecting malicious instructions into untrusted external sources, effectively hijacking the Agent to perform harmful operations beyond the user's intention or awareness. This emerging threat has quickly attracted research attention, leading to various proposed attack vectors, such as hijacking Model Context Protocol (MCP) Servers to access private data. However, most existing approaches lack stealth and persistence, limiting their practical impact. We propose the Cuckoo Attack, a novel attack that achieves stealthy and persistent command execution by embedding malicious payloads into configuration files. These files, commonly used in AI-IDEs, execute system commands during routine operations, without displaying execution details to the user. Once configured, such files are rarely revisited unless an obvious runtime error occurs, creating a blind spot for attackers to exploit. We formalize our attack paradigm into two stages, including initial infection and persistence. Based on these stages, we analyze the practicality of the attack execution process and identify the relevant exploitation techniques. Furthermore, we analyze the impact of Cuckoo Attack, which can not only invade the developer's local computer but also achieve supply chain attacks through the spread of configuration files. We contribute seven actionable checkpoints for vendors to evaluate their product security. The critical need for these checks is demonstrated by our end-to-end Proof of Concept, which validated the proposed attack across nine mainstream Agent and AI-IDE pairs.

cs.CR↗
arXiv2025

TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling

Multivariate time series data typically comprises two distinct modalities: variable semantics and sampled numerical observations. Traditional time series models treat variables as anonymous statistical signals, overlooking the rich semantic information embedded in variable names and data descriptions. However, these textual descriptors often encode critical domain knowledge that is essential for robust and interpretable modeling. Here we present TimeMKG, a multimodal causal reasoning framework that elevates time series modeling from low-level signal processing to knowledge informed inference. TimeMKG employs large language models to interpret variable semantics and constructs structured Multivariate Knowledge Graphs that capture inter-variable relationships. A dual-modality encoder separately models the semantic prompts, generated from knowledge graph triplets, and the statistical patterns from historical time series. Cross-modality attention aligns and fuses these representations at the variable level, injecting causal priors into downstream tasks such as forecasting and classification, providing explicit and interpretable priors to guide model reasoning. The experiment in diverse datasets demonstrates that incorporating variable-level knowledge significantly improves both predictive performance and generalization.

cs.LG↗
arXiv2025

FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments

Multimodal data are often incomplete and exhibit Non-Independent and Identically Distributed (Non-IID) characteristics in real-world scenarios. These inherent limitations lead to both modality heterogeneity through partial modality absence and data heterogeneity from distribution divergence, creating fundamental challenges for effective federated learning (FL). To address these coupled challenges, we propose FedRecon, the first method targeting simultaneous missing modality reconstruction and Non-IID adaptation in multimodal FL. Our approach first employs a lightweight Multimodal Variational Autoencoder (MVAE) to reconstruct missing modalities while preserving cross-modal consistency. Distinct from conventional imputation methods, we achieve sample-level alignment through a novel distribution mapping mechanism that guarantees both data consistency and completeness. Additionally, we introduce a strategy employing global generator freezing to prevent catastrophic forgetting, which in turn mitigates Non-IID fluctuations. Extensive evaluations on multimodal datasets demonstrate FedRecon's superior performance in modality reconstruction under Non-IID conditions, surpassing state-of-the-art methods. The code will be released upon paper acceptance.

cs.LG↗
arXiv2025

From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation

Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where small K values omit crucial information and large K values introduce noise. To address this, we introduce the Dynamic Passage Selector (DPS), a novel reranking framework that treats passage selection as a supervised learning problem. Unlike traditional point-wise or list-wise methods, DPS is fine-tuned to capture inter-passage dependencies and dynamically select the most relevant set of passages for generation. As a seamless plug-and-play module, DPS requires no modifications to the standard RAG pipeline. Comprehensive evaluations on five benchmarks show that DPS consistently outperforms state-of-the-art rerankers and fine-tuning methods. Notably, on the challenging MuSiQue dataset, DPS improves the F1-score by 30.06% and 15.4% over strong baselines like Qwen3-reranker and RankingGPT, respectively. Our results demonstrate that by enabling adaptive evidence selection, DPS substantially enhances reasoning capabilities in complex RAG scenarios.

cs.CL↗
arXiv2025

Ta2Pd3Te8: A potential candidate of 1D van der Waals stacked thermoelectric materials

Discovering new thermoelectric (TE) materials is an eternal goal in the TE field. Excellent TE materials have ranged from 3D stacked to 2D stacked bulk. However, the 1D stacked receives little attention due to the scarcity in quantity. In this work, it is predicted that 1D van der Waals (vdW) stacked Ta2Pd3Te8 crystal is a compelling candidate for TE applications by combining first-principles calculations with phonon and electron Boltzmann transport equations and molecular dynamics methods. We find that Ta2Pd3Te8 crystal has mechanical, dynamical, and thermal stabilities, and its TE properties are featured by strong anisotropy, high power factor (PF) and low lattice thermal conductivity. The results indicate the ZT values of n-type Ta2Pd3Te8 at 900 K along a, b and c axes reach 0.48, 0.39 and 0.22, respectively. We propose that enlarging the bandgap can weaken the bipolar effect and thus significantly increases ZT to 1.11. The findings in the work not only stimulate more theoretical works on 1D vdW stacked TE materials, but also provide valuable information for experimentally improving TE materials.

cond-mat.mtrl-sci↗
arXiv2025

HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation

While Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge, conventional single-agent RAG remains fundamentally limited in resolving complex queries demanding coordinated reasoning across heterogeneous data ecosystems. We present HM-RAG, a novel Hierarchical Multi-agent Multimodal RAG framework that pioneers collaborative intelligence for dynamic knowledge synthesis across structured, unstructured, and graph-based data. The framework is composed of three-tiered architecture with specialized agents: a Decomposition Agent that dissects complex queries into contextually coherent sub-tasks via semantic-aware query rewriting and schema-guided context augmentation; Multi-source Retrieval Agents that carry out parallel, modality-specific retrieval using plug-and-play modules designed for vector, graph, and web-based databases; and a Decision Agent that uses consistency voting to integrate multi-source answers and resolve discrepancies in retrieval results through Expert Model Refinement. This architecture attains comprehensive query understanding by combining textual, graph-relational, and web-derived evidence, resulting in a remarkable 12.95% improvement in answer accuracy and a 3.56% boost in question classification accuracy over baseline RAG systems on the ScienceQA and CrisisMMD benchmarks. Notably, HM-RAG establishes state-of-the-art results in zero-shot settings on both datasets. Its modular architecture ensures seamless integration of new data modalities while maintaining strict data governance, marking a significant advancement in addressing the critical challenges of multimodal reasoning and knowledge synthesis in RAG systems. Code is available at https://github.com/ocean-luna/HMRAG.

cs.CL↗
arXiv2024

Exploring ChatGPT's Capabilities on Vulnerability Management

Recently, ChatGPT has attracted great attention from the code analysis domain. Prior works show that ChatGPT has the capabilities of processing foundational code analysis tasks, such as abstract syntax tree generation, which indicates the potential of using ChatGPT to comprehend code syntax and static behaviors. However, it is unclear whether ChatGPT can complete more complicated real-world vulnerability management tasks, such as the prediction of security relevance and patch correctness, which require an all-encompassing understanding of various aspects, including code syntax, program semantics, and related manual comments. In this paper, we explore ChatGPT's capabilities on 6 tasks involving the complete vulnerability management process with a large-scale dataset containing 70,346 samples. For each task, we compare ChatGPT against SOTA approaches, investigate the impact of different prompts, and explore the difficulties. The results suggest promising potential in leveraging ChatGPT to assist vulnerability management. One notable example is ChatGPT's proficiency in tasks like generating titles for software bug reports. Furthermore, our findings reveal the difficulties encountered by ChatGPT and shed light on promising future directions. For instance, directly providing random demonstration examples in the prompt cannot consistently guarantee good performance in vulnerability management. By contrast, leveraging ChatGPT in a self-heuristic way -- extracting expertise from demonstration examples itself and integrating the extracted expertise in the prompt is a promising research direction. Besides, ChatGPT may misunderstand and misuse the information in the prompt. Consequently, effectively guiding ChatGPT to focus on helpful information rather than the irrelevant content is still an open problem.

cs.SE↗
arXiv2024

Room-temperature sub-100 nm Néel-type skyrmions in non-stoichiometric van der Waals ferromagnet $\rm Fe_{3-x}GaTe_{2}$ with ultrafast laser writability

Realizing room-temperature magnetic skyrmions in two-dimensional van der Waals ferromagnets offers unparalleled prospects for future spintronic applications. However, due to the intrinsic spin fluctuations that suppress atomic long-range magnetic order and the inherent inversion crystal symmetry that excludes the presence of the Dzyaloshinskii-Moriya interaction, achieving room-temperature skyrmions in 2D magnets remains a formidable challenge. In this study, we target room-temperature 2D magnet $\rm Fe_3GaTe_2$ and unveil that the introduction of iron-deficient into this compound enables spatial inversion symmetry breaking, thus inducing a significant Dzyaloshinskii-Moriya interaction that brings about room-temperature Néel-type skyrmions with unprecedentedly small size. To further enhance the practical applications of this finding, we employ a homemade in-situ optical Lorentz transmission electron microscopy to demonstrate ultrafast writing of skyrmions in $\rm Fe_{3-x}GaTe_2$ using a single femtosecond laser pulse. Our results manifest the $\rm Fe_{3-x}GaTe_2$ as a promising building block for realizing skyrmion-based magneto-optical functionalities.

cond-mat.mtrl-sci↗
arXiv2021

Volterra type operators on minimal Mobius invariant space

In this note, we mainly study operator-theoretic properties on Besov space $B_{1}$ on the unit disc. This space is the minimal Mobius invariant space. Firstly, we consider the boundedness of Volterra type operators. Secondly, we prove that Volterra type operators belong to the Deddens algebra of composition operator. Thirdly, we obtain estimates for the essential norm of Volterra type operators. Finally, we give a complete characterization of spectrum of Volterra type operators.

math.CV↗
arXiv2021

High-throughput screening of quaternary compounds and new insight for excellent thermoelectric performance

It is well known that the high electric conductivity, large Seebeck coefficient, and low thermal conductivity are preferred for enhancing thermoelectric performance, but unfortunately, these properties are strongly inter-correlated with no rational scenario for their efficient decoupling. This big dilemma for thermoelectric research appeals for alternative strategic solutions, while the high-throughput screening is one of them. In this work, we start from total 3136 real electronic structures of the huge X2YZM4 quaternary compound family and perform the high-throughput searching in terms of enhanced thermoelectric properties. The comprehensive data-mining allows an evaluation of the electronic and phonon characteristics of those promising thermoelectric materials. More importantly, a new insight that the enhanced thermoelectric performance benefits substantially from the coexisting quasi-Dirac and heavy fermions plus strong optical-acoustic phonon hybridization, is proposed. This work provides a clear guidance to theoretical screening and experimental realization and thus towards development of performance-excellent thermoelectric materials.

physics.app-ph↗
arXiv2021

Invariant subspace of composition operators on Hardy space

We consider the invariant subspace of composition operators on Hardy space $H^p$ where the composition operators corresponding to a function $φ$ that is a holomorphic self-map of $\mathbb D$. Firstly, we discuss composition operators $C_φ$ on subspace $H_{α,β}^p$ of Hardy space $H^p$. We will explore the invariant subspaces for $C_φ$ in various special cases. Secondly, we consider Beurling type invariant subspace for $C_φ$. When $θ$ is a inner function, we prove that $θH^p$ is invariant for $C_φ$ if and only if $\displaystyle{\frac{θ\circφ}θ}$ belongs to $\mathcal S(\mathbb D)$. Thirdly, we obtain that $z^nH^p$ is nontrivial invariant subspace for Deddends algebras $\mathcal D_{C_φ}$ when $C_φ$ is a compact composition operator and $φ$ satisfies that $φ(0)=0$ and $\parallelφ\parallel_\infty<1$.

math.FA↗
arXiv2020

Complex symmetric weighted Composition Differentiation Operators

In this note, we completely characterize complex symmetric weighted composition differentiation operator on the Hardy space $H^2$ with respect to the conjugation operator $C_{λ,α}$. Meanwhile, the normal and self-adjoint of the weighted composition differentiation operators on the Hardy space $H^2$ are also studied. This note could be considered as a continuation of the work initiated by Fatehi and Hammond.

math.FA↗
arXiv2020

Job2Vec: Job Title Benchmarking with Collective Multi-View Representation Learning

Job Title Benchmarking (JTB) aims at matching job titles with similar expertise levels across various companies. JTB could provide precise guidance and considerable convenience for both talent recruitment and job seekers for position and salary calibration/prediction. Traditional JTB approaches mainly rely on manual market surveys, which is expensive and labor-intensive. Recently, the rapid development of Online Professional Graph has accumulated a large number of talent career records, which provides a promising trend for data-driven solutions. However, it is still a challenging task since (1) the job title and job transition (job-hopping) data is messy which contains a lot of subjective and non-standard naming conventions for the same position (e.g., Programmer, Software Development Engineer, SDE, Implementation Engineer), (2) there is a large amount of missing title/transition information, and (3) one talent only seeks limited numbers of jobs which brings the incompleteness and randomness modeling job transition patterns. To overcome these challenges, we aggregate all the records to construct a large-scale Job Title Benchmarking Graph (Job-Graph), where nodes denote job titles affiliated with specific companies and links denote the correlations between jobs. We reformulate the JTB as the task of link prediction over the Job-Graph that matched job titles should have links. Along this line, we propose a collective multi-view representation learning method (Job2Vec) by examining the Job-Graph jointly in (1) graph topology view, (2)semantic view, (3) job transition balance view, and (4) job transition duration view. We fuse the multi-view representations in the encode-decode paradigm to obtain a unified optimal representation for the task of link prediction. Finally, we conduct extensive experiments to validate the effectiveness of our proposed method.

cs.AI↗
arXiv2020

Electric-field-driven Non-volatile Multi-state Switching of Individual Skyrmions in a Multiferroic Heterostructure

Electrical manipulation of skyrmions attracts considerable attention for its rich physics and promising applications. To date, such a manipulation is realized mainly via spin-polarized current based on spin-transfer torque or spin-orbital torque effect. However, this scheme is energy-consuming and may produce massive Joule heating. To reduce energy dissipation and risk of heightened temperatures of skyrmion-based devices, an effective solution is to use electric field instead of current as stimulus. Here, we realize an electric-field manipulation of skyrmions in a nanostructured ferromagnetic/ferroelectrical heterostructure at room temperature via an inverse magneto-mechanical effect. Intriguingly, such a manipulation is non-volatile and exhibits a multi-state feature. Numerical simulations indicate that the electric-field manipulation of skyrmions originates from strain-mediated modification of effective magnetic anisotropy and Dzyaloshinskii-Moriya interaction. Our results open a direction for constructing low-energy-dissipation, non-volatile, and multi-state skyrmion-based spintronic devices.

cond-mat.mtrl-sci↗
arXiv2020

A Gd@C82-based single molecular electret device with switchable electrical polarization

Single molecular electrets exhibiting single molecule electric polarization switching have been long desired as a platform for extremely small non-volatile storage devices, although it is controversial because of the poor stability of single molecular electric dipoles. Here we study the single molecular device of GdC82, where the encapsulated Gd atom forms a charge center, and we have observed a gate controlled switching behavior between two sets of single electron transport stability diagrams. The switching is operated in a hysteresis loop with a coercive gate field of around 0.5Vnm. Theoretical calculations have assigned the two conductance diagrams to corresponding energy levels of two states that the Gd atom is trapped at two different sites of the C82 cage, which possess two different permanent electrical dipole orientations. The two dipole states are stabilized by the anisotropic energy and separated by a transition energy barrier of 70 meV. Such switching is then accessed to the electric field driven reorientation of individual dipole while overcoming the barriers by the coercive gate field, and demonstrates the creation of a single molecular electret.

cond-mat.mes-hall↗
arXiv2019

Strict singularity of Volterra type operators on Hardy spaces

In this paper, we first characterize the boundedness and compactness of Volterra type operator $S_gf(z) = \int_0^z f'(ζ)g(ζ)dζ, \ z \in \mathbb{D},$ defined on Hardy spaces $H^p, \, 0< p <\infty$. The spectrum of $S_g$ is also obtained. Then we prove that $S_g$ fixes an isomorphic copy of $\ell^p$ and an isomorphic copy of $\ell^2$ if the operator $S_g$ is not compact on $H^p (1\leq p<\infty)$. In particular, this implies that the strict singularity of the operator $S_g$ coincides with the compactness of the operator $S_g$ on $H^p$. At last, we post an open question for further study.

math.FA↗
arXiv2019

Strict singularity of weighted composition operators on derivative Hardy spaces

We prove that the weighted composition operator $W_{ϕ,φ}$ fixes an isomorphic copy of $\ell^p$ if the operator $W_{ϕ,φ}$ is not compact on the derivative Hardy space $S^p$. In particular, this implies that the strict singularity of the operator $W_{ϕ,φ}$ coincides with the compactness of it on $S^p$. Moreover, when $p\neq2$, we characterize the conditions for those weighted composition operators $W_{ϕ,φ}$ on $S^p$ which fix an isomorphic copy of $\ell^2$ .

math.FA↗