arXiv subjects

Guodong Zhou

Publications and source records attributed to Guodong Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2026

DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE

In the literature, prior research on Security-oriented Video Understanding (SVU) has predominantly focused on detecting and localize the threats (e.g., shootings, robberies) in videos, while largely lacking the effective capability to generate and evaluate the threat causes. Motivated by these gaps, this paper introduces a new chat paradigm SVU task, i.e., In-depth Security-oriented Video Understanding (DeepSVU), which aims to not only identify and locate the threats but also attribute and evaluate the causes threatening segments. Furthermore, this paper reveals two key challenges in the proposed task: 1) how to effectively model the coarse-to-fine physical-world information (e.g., human behavior, object interactions and background context) to boost the DeepSVU task; and 2) how to adaptively trade off these factors. To tackle these challenges, this paper proposes a new Unified Physical-world Regularized MoE (UPRM) approach. Specifically, UPRM incorporates two key components: the Unified Physical-world Enhanced MoE (UPE) Block and the Physical-world Trade-off Regularizer (PTR), to address the above two challenges, respectively. Extensive experiments conduct on our DeepSVU instructions datasets (i.e., UCF-C instructions and CUVA instructions) demonstrate that UPRM outperforms several advanced Video-LLMs as well as non-VLM approaches. Such information.These justify the importance of the coarse-to-fine physical-world information in the DeepSVU task and demonstrate the effectiveness of our UPRM in capturing such information.

cs.CV↗

arXiv2026

Efficient Long-Document Reranking via Block-Level Embeddings and Top-k Interaction Refinement

Dense encoders and LLM-based rerankers struggle with long documents: single-vector representations dilute fine-grained relevance, while cross-encoders are often too expensive for practical reranking. We present an efficient long-document reranking framework based on block-level embeddings. Each document is segmented into short blocks and encoded into block embeddings that can be precomputed offline. Given a query, we encode it once and score each candidate document by aggregating top-k query-block similarities with a simple weighted sum, yielding a strong and interpretable block-level relevance signal. To capture dependencies among the selected blocks and suppress redundancy, we introduce Top-k Interaction Refinement (TIR), a lightweight setwise module that applies query-conditioned attention over the top-k blocks and produces a bounded residual correction to block scores. TIR introduces only a small number of parameters and operates on top-k blocks, keeping query-time overhead low. Experiments on long-document reranking benchmarks (TREC DL and MLDR-zh) show that block representations substantially improve over single-vector encoders, and TIR provides consistent additional gains over strong long-document reranking baselines while maintaining practical reranking latency. For example, on TREC DL 2023, NDCG at 10 improves from 0.395 to 0.451 with the same block budget k = 65, using at most 4095 tokens. The resulting model supports interpretability by exposing which blocks drive each document's score and how refinement redistributes their contributions.

cs.IR↗

arXiv2026

PCoKG: Personality-aware Commonsense Reasoning with Debate

Most commonsense reasoning models overlook the influence of personality traits, limiting their effectiveness in personalized systems such as dialogue generation. To address this limitation, we introduce the Personality-aware Commonsense Knowledge Graph (PCoKG), a structured dataset comprising 521,316 quadruples. We begin by employing three evaluators to score and filter events from the ATOMIC dataset, selecting those that are likely to elicit diverse reasoning patterns across different personality types. For knowledge graph construction, we leverage the role-playing capabilities of large language models (LLMs) to perform reasoning tasks. To enhance the quality of the generated knowledge, we incorporate a debate mechanism consisting of a proponent, an opponent, and a judge, which iteratively refines the outputs through feedback loops. We evaluate the dataset from multiple perspectives and conduct fine-tuning and ablation experiments using multiple LLM backbones to assess PCoKG's robustness and the effectiveness of its construction pipeline. Our LoRA-based fine-tuning results indicate a positive correlation between model performance and the parameter scale of the base models. Finally, we apply PCoKG to persona-based dialogue generation, where it demonstrates improved consistency between generated responses and reference outputs. This work bridges the gap between commonsense reasoning and individual cognitive differences, enabling the development of more personalized and context-aware AI systems.

cs.AI↗

arXiv2026

Modified Rota-Baxter operators of non-zero weight on $3$-Lie algebras

In this paper, we introduce the notion of modified Rota-Baxter operators of non-zero weight on $3$-Lie algebras and provide some examples. Next, we give various constructions of modified Rota-Baxter operators of non-zero weight according to constructions of $3$-Lie algebras. Furthermore, we define a cohomology of modified Rota-Baxter operators of non-zero weight on $3$-Lie algebras with coefficients in a suitable representation. As an application, we study formal deformations of modified Rota-Baxter operators of non-zero weight that are generated by the above-defined cohomology. In the final part of the paper, we construct two $L_\infty[1]$-algebra structures whose Maurer-Cartan elements correspond to relative and absolute modified Rota-Baxter $3$-Lie algebra structures of nonzero weight, respectively. Lastly, we compare our $L_\infty[1]$-algebraic approach with the deformation-controlling $L_\infty[1]$-algebra for relative Rota-Baxter $3$-Lie operators developed by Hou, Sheng, and Zhou.

math.RA↗

arXiv2026

$A_{\infty}$-structures on the additive decomposition of the Tate-Hochschild cohomology of a finite group algebra

Firstly, for a finite group algebra, we provide a computational framework $\widehat{m}_n$ for the Tate-Hochschild cochain complex in terms of the additive decomposition, by decomposing each planar n-ary tree into local two children and local three children. Secondly, we give all $\widehat{m}_2$ formulas of the Tate-Hochschild cochain complex in terms of the additive decomposition. Thirdly, we give explicit $A_{\infty}$-multiplication formulas for both the Hochschild cochain complex and the Hochschild chain complex under additive decompositions. Finally, we give $A_{\infty}$-multiplication formulas in the context of abelian groups.

math.KT↗

arXiv2025

Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios

In the literature, existing human-centric emotional motion generation methods primarily focus on boosting performance within a single scale-fixed dataset, largely neglecting the flexible and scale-increasing motion scenarios (e.g., sports, dance), whereas effectively learning these newly emerging scenarios can significantly enhance the model's real-world generalization ability. Inspired by this, this paper proposes a new LLM-Centric Lifelong Empathic Motion Generation (L^2-EMG) task, which aims to equip LLMs with the capability to continually acquire emotional motion generation knowledge across different unseen scenarios, potentially contributing to building a closed-loop and self-evolving embodied agent equipped with both empathy and intelligence. Further, this paper poses two key challenges in the L^2-EMG task, i.e., the emotion decoupling challenge and the scenario adapting challenge. To this end, this paper proposes an Emotion-Transferable and Scenario-Adapted Mixture of Experts (ES-MoE) approach which designs a causal-guided emotion decoupling block and a scenario-adapted expert constructing block to address the two challenges, respectively. Especially, this paper constructs multiple L^2-EMG datasets to validate the effectiveness of the ES-MoE approach. Extensive evaluations show that ES-MoE outperforms advanced baselines.

cs.AI↗

arXiv2025

RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA

Large language models (LLMs) often generate hallucinations in knowledge-intensive QA due to parametric knowledge limitations. While existing methods like KG-CoT improve reliability by integrating knowledge graph (KG) paths, they suffer from rigid hop-count selection (solely question-driven) and underutilization of reasoning paths (lack of guidance). To address this, we propose RFKG-CoT: First, it replaces the rigid hop-count selector with a relation-driven adaptive hop-count selector that dynamically adjusts reasoning steps by activating KG relations (e.g., 1-hop for direct "brother" relations, 2-hop for indirect "father-son" chains), formalized via a relation mask. Second, it introduces a few-shot in-context learning path guidance mechanism with CoT (think) that constructs examples in a "question-paths-answer" format to enhance LLMs' ability to understand reasoning paths. Experiments on four KGQA benchmarks show RFKG-CoT improves accuracy by up to 14.7 pp (Llama2-7B on WebQSP) over KG-CoT. Ablations confirm the hop-count selector and the path prompt are complementary, jointly transforming KG evidence into more faithful answers.

cs.CL↗

arXiv2025

Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis via Intermediate Representation and Language Model

Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown promise, these classifiers are often susceptible to adversarial attacks, undermining their reliability. To address this issue, recent studies have aimed to enhance the robustness of PDF classifiers. Despite these efforts, the feature engineering underlying these studies remains outdated. Consequently, even with the application of cutting-edge machine learning techniques, these approaches fail to fundamentally resolve the issue of feature instability. To tackle this, we propose a novel approach for PDF feature extraction and PDF malware detection. We introduce the PDFObj IR (PDF Object Intermediate Representation), an assembly-like language framework for PDF objects, from which we extract semantic features using a pretrained language model. Additionally, we construct an Object Reference Graph to capture structural features, drawing inspiration from program analysis. This dual approach enables us to analyze and detect PDF malware based on both semantic and structural features. Experimental results demonstrate that our proposed classifier achieves strong adversarial robustness while maintaining an exceptionally low false positive rate of only 0.07% on baseline dataset compared to state-of-the-art PDF malware classifiers.

cs.CR↗

arXiv2025

Characterizing higher Auslander(-Gorenstein) Algebras

It is well known that for Auslander algebras, the category of all (finitely generated) projective modules is an abelian category and this property of abelianness characterizes Auslander algebras by Tachikawa theorem in 1974. Let $n$ be a positive integer. In this paper, by using torsion theoretic methods, we show that $ n $-Auslander algebras can be characterized by the abelianness of the category of modules with projective dimension less than $ n $ and a certain additional property, extending the classical Auslander-Tachikawa theorem. By Auslander-Iyama correspondence a categorical characterization of the class of Artin algebras having $ n $-cluster tilting modules is obtained. Since higher Auslander algebras are a special case of higher Auslander-Gorenstein algebras, the results are given in the general setting as extending previous results of Kong. Moreover, as an application of some results, we give categorical descriptions for the semisimplicity and selfinjectivity of an Artin algebra. Higher Auslander-Gorenstein Algebras are also studied from the viewpoint of cotorsion pairs and, as application, we show that they satisfy in two nice equivalences.

math.RT↗

arXiv2025

A Survey of Long-Document Retrieval in the PLM and LLM Era

The proliferation of long-form documents presents a fundamental challenge to information retrieval (IR), as their length, dispersed evidence, and complex structures demand specialized methods beyond standard passage-level techniques. This survey provides the first comprehensive treatment of long-document retrieval (LDR), consolidating methods, challenges, and applications across three major eras. We systematize the evolution from classical lexical and early neural models to modern pre-trained (PLM) and large language models (LLMs), covering key paradigms like passage aggregation, hierarchical encoding, efficient attention, and the latest LLM-driven re-ranking and retrieval techniques. Beyond the models, we review domain-specific applications, specialized evaluation resources, and outline critical open challenges such as efficiency trade-offs, multimodal alignment, and faithfulness. This survey aims to provide both a consolidated reference and a forward-looking agenda for advancing long-document retrieval in the era of foundation models.

cs.IR↗

arXiv2025

Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective

Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic features facilitate effective knowledge transfer. In contrast, for non-Latin script language (NSL), such as Chinese and Japanese, performance often degrades due to deep structural differences. To address these challenges, we propose an entity-aligned translation (EAT) approach. Leveraging large language models (LLMs), EAT employs a dual-translation strategy to align entities between NSL and English. In addition, we fine-tune LLMs using multilingual Wikipedia data to enhance the entity alignment from source to target languages.

cs.CL↗

arXiv2025

Algebraic Morse theory via Homological Perturbation Lemma

As a generalization of the classical killing-contractible-complexes lemma, we present algebraic Morse theory via homological perturbation lemma, in a form more general than existing presentations in the literature. Two-sided Anick resolutions due to E.~Sköldberg are generalised to algebras given by quivers with relations and a minimality criterion is provided as well. Two applications of algebraic Morse theory are presented. It is shown that the Chinese algebra of rank $n\geq 1$ is homologically smooth and of global dimension $\frac{n(n+1)}{2}$, and the minimal two-sided projective resolution of a Koszul algebra is constructed.

math.KT↗

arXiv2025

A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment

Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist in achieving global understanding and aligning responses with human ethical and quality preferences. To address these issues, we propose GraphMPA, a comprehensive graph-based framework with mode-seeking preference alignment. Our approach constructs a hierarchical document graph using a general similarity measurement, mimicking human cognitive processes for information understanding and synthesis. Additionally, we introduce mode-seeking preference optimization to better align model outputs with human preferences through probability-matching constraints. Extensive experiments on six datasets demonstrate the effectiveness of our \href{https://github.com/tangquanwei/GraphMPA}{GraphMPA}.

cs.CL↗

arXiv2025

Higher Auslander-Gorenstein Algebras And Gabriel Topologies

This paper is devoted to study the relationship between two important notions in ring theory, category theory, and representation theory of Artin algebras; namely, Gabriel topologies and higher Auslander(-Gorenstein) algebras. It is well-known that the class of all torsionless modules over a higher Auslander(-Gorenstein) algebra is a torsion-free class of a hereditary torsion theory that is cogenerated by its injective envelope and so by Gabriel-Maranda correspondence we can define a Gabriel topology on it. We show that higher Auslander(-Gorenstein) algebras can be characterized by this Gabriel topology. This characterization can be considered as a higher version of the Auslander-Buchsbaum-Serre theorem that is considered as one of the most important achievements of the use of homological algebra in the theory of commutative rings. Among some applications, the results also reveal a relation between the projective dimension of a module and the projective dimensions of the annihilator ideals of its objects over higher Auslander algebras.

math.RT↗

arXiv2025

Deformations of Nijenhuis Lie algebras and Nijenhuis Lie algebroids

This paper is the second in a series dedicated to the operadic study of Nijenhuis structures, focusing on Nijenhuis Lie algebras and Nijenhuis geometry. We introduce the concept of homotopy Nijenhuis Lie algebras and establish that the differential graded (=dg) operad $\mathfrak{NjL}_{\infty}$ governing these structures serves as the minimal model of the operad $\mathfrak{NjL}$ for Nijenhuis Lie algebras. We construct an $L_\infty$-algebra that encodes the simultaneous deformations of Lie brackets and Nijenhuis operators, leading to the deformation cochain complex and an associated cohomology theory for Nijenhuis Lie algebras. Extending these ideas to geometry, we investigate the deformations of geometric Nijenhuis structures. We introduce the notion of a Nijenhuis Lie algebroid-a Lie algebroid equipped with a Nijenhuis structure, which generalizes the classical Nijenhuis structure on vector fields of manifolds. Using the framework of dg manifolds, we construct an $L_\infty$-algebra that governs the simultaneous deformations of Lie algebroid structures and Nijenhuis operators. As a computational application, we prove that a certain class of Nijenhuis operators satisfies the Poincaré Lemma, meaning its cohomology vanishes, which confirms a conjecture by Bolsinov and Konyaev.

math.DG↗

arXiv2025

Deformation theory and Koszul duality for Rota-Baxter systems

This paper investigates Rota-Baxter systems in the sense of Brzeziński from the perspective of operad theory. The minimal model of the Rota-Baxter system operad is constructed, equivalently a concrete construction of its Koszul dual homotopy cooperad is given. The concept of homotopy Rota-Baxter systems and the $L_\infty$-algebra that governs deformations of a Rota-Baxter system are derived from the Koszul dual homotopy cooperad. The notion of infinity-Yang-Baxter pairs is introduced, which is a higher-order generalization of the traditional Yang-Baxter pairs. It is shown that a homotopy Rota-Baxter system structure on the endomorphism algebra of a graded space is equivalent to an associative infinity-Yang-Baxter pair on this graded algebra, thereby generalizing the classical correspondence between Yang-Baxter pairs and Rota-Baxter systems.

math.RA↗

arXiv2025

Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM

Prior studies on Video Anomaly Detection (VAD) mainly focus on detecting whether each video frame is abnormal or not in the video, which largely ignore the structured video semantic information (i.e., what, when, and where does the abnormal event happen). With this in mind, we propose a new chat-paradigm \textbf{M}ulti-scene Video Abnormal Event Extraction and Localization (M-VAE) task, aiming to extract the abnormal event quadruples (i.e., subject, event type, object, scene) and localize such event. Further, this paper believes that this new task faces two key challenges, i.e., global-local spatial modeling and global-local spatial balancing. To this end, this paper proposes a Global-local Spatial-sensitive Large Language Model (LLM) named Sherlock, i.e., acting like Sherlock Holmes to track down the criminal events, for this M-VAE task. Specifically, this model designs a Global-local Spatial-enhanced MoE (GSM) module and a Spatial Imbalance Regulator (SIR) to address the two challenges respectively. Extensive experiments on our M-VAE instruction dataset show the significant advantages of Sherlock over several advanced Video-LLMs. This justifies the importance of global-local spatial information for the M-VAE task and the effectiveness of Sherlock in capturing such information.

cs.CV↗

arXiv2025

Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos

Prior studies on Visual Sentiment Understanding (VSU) primarily rely on the explicit scene information (e.g., facial expression) to judge visual sentiments, which largely ignore implicit scene information (e.g., human action, objection relation and visual background), while such information is critical for precisely discovering visual sentiments. Motivated by this, this paper proposes a new Omni-scene driven visual Sentiment Identifying, Locating and Attributing in videos (Omni-SILA) task, aiming to interactively and precisely identify, locate and attribute visual sentiments through both explicit and implicit scene information. Furthermore, this paper believes that this Omni-SILA task faces two key challenges: modeling scene and highlighting implicit scene beyond explicit. To this end, this paper proposes an Implicit-enhanced Causal MoE (ICM) approach for addressing the Omni-SILA task. Specifically, a Scene-Balanced MoE (SBM) and an Implicit-Enhanced Causal (IEC) blocks are tailored to model scene information and highlight the implicit scene information beyond explicit, respectively. Extensive experimental results on our constructed explicit and implicit Omni-SILA datasets demonstrate the great advantage of the proposed ICM approach over advanced Video-LLMs.

cs.CV↗