Searcharxiv⌕ Search

arXiv subjects

Mei Wang

Publications and source records attributed to Mei Wang.

At least 19 recordsLinked to original sources
arXiv2026

CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling

Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models can perform chaptering from textualized video inputs, but they remain costly and brittle for content-dense lecture videos with long transcripts, smooth topic transitions, and detailed chapter outputs. A scalable segment-then-caption paradigm reduces this cost, but introduces two new challenges: boundary error propagation and fragmented cross-chapter context. We propose \textbf{CausalChapter}, an intervention-inspired framework for long-video chaptering that estimates prediction-level influence through lightweight masking and removal interventions. For boundary localization, our Local Dependency Shift module detects drops in predictive dependency between adjacent temporal windows; for chapter description generation, our Cross-Segment Support Selection module reranks historical contexts according to their support for the current prediction. Experiments on long-video chaptering benchmarks show that CausalChapter improves boundary localization, chapter description quality, and cross-chapter coherence.

cs.CV↗
arXiv2026

Frobenius Galois expansions of substructural logics:Algebraization, Kalman equivalence and positive cone semantics

The main aim of this paper is to introduce a Frobenius--Galois expansion of the substructural logic $\mathbf{FL}_{ew}$ and develop its algebraic and categorical semantics. The resulting logic, denoted by $\mathbf{FL}^{\mathbf{FGC}}_{ew}$, is obtained by adjoining a pair of unary connectives forming a Galois connection and satisfying suitable Frobenius-type compatibility conditions. Firstly, we prove that $\mathbf{FL}^{\mathbf{FGC}}_{ew}$ is algebraizable in the sense of Blok and Pigozzi and identify its equivalent algebraic semantics with the variety of Frobenius-adjoint residuated lattices, establishing the conservativity over $\mathbf{FL}_{ew}$ and relating its finite model property to residual finiteness of finitely generated free algebras. Secondly, for the distributive setting, we lift the Kalman construction to the Frobenius-adjoint algebraic framework. More precisely, we establish a categorical equivalence between Frobenius-adjoint residuated distributive lattices and Frobenius-adjoint $c$-differential residuated distributive lattices with the condition $\mathbf{CK}$. This equivalence yields a positive-cone representation of the former structures and, in turn, a logical counterpart of the categorical correspondence. Finally, for the distributive extension $\mathbf{FL}^{\mathbf{FGC},d}_{ew}$, we prove that derivability, validity over Frobenius-adjoint residuated distributive lattices, and validity over the corresponding positive cones determine the same consequence relation, and further show that this correspondence preserves equational and quasi-equational consequence, conservativity, and finite countermodels. These results provide a unified algebraic, categorical, and logical framework for Frobenius--Galois expansions of substructural logics.

math.LO↗
arXiv2026

Machine learning for the design and prediction of soft-magnetic electromagnetic shielding FeCo-based alloys in laser cladding

Electromagnetic shielding materials play a pivotal role in both aerospace applications and daily life. However, their design and manufacturing still face persistent challenges. Machine learning demonstrates significant potential in accelerating material development and compositions optimization. Furthermore, laser additive manufacturing provides powerful technical support for fabricating multi-component, multifunctional electromagnetic shielding materials with tailored properties. In this study, the multiple machine learning strategies have been proposed, based on experimental derivation and soft magnetic material databases, to accelerate the design of multifunctional FeCo-based alloys for electromagnetic interference (EMI) shielding within an almost infinite compositional space. This work presents a novel approach for the rapid and automated discovery of multifunctional alloys with optimized EMI shielding effectiveness, as well as enhanced magnetic and electrical properties.

cond-mat.mtrl-sci↗
arXiv2026

MESS: Fast and Private Semantic Search on Multi-Graph HNSW

Semantic search systems map data to a high-dimensional vector space and support retrieval of similar data via approximate nearest neighbor search. When the system is hosted by an untrusted cloud provider, there is no privacy for the data or the query. Our goal is to design a system with three properties: privacy, accuracy, and efficiency. Existing works adopt either homomorphic encryption (HE), oblivious RAM (ORAM), or a differential privacy (DP) approach. They fall short of achieving all three properties. In this paper, we present MESS, a system that realizes our goal. It maps the original vectors into binary codes, applies locality-sensitive hashing (LSH) and randomized response, and constructs a multi-graph Hierarchical Navigable Small World (HNSW) index over the perturbed codes. MESS ensures data, query, and access pattern privacy. It also ensures search pattern privacy via a two-phase query perturbation mechanism. The multi-graph index mitigates the impact of perturbation on result quality, thereby achieving accuracy. MESS is efficient because search is performed directly over perturbed codes, without the overhead of homomorphic encryption or ORAM. We give formal analysis of the system's privacy and extensive evaluation of its performance. The results show that MESS achieves up to 15.08\times lower latency than state-of-the-art baselines.

cs.CR↗
arXiv2026

PC-MIL: Decoupling Feature Resolution from Supervision Scale in Whole-Slide Learning

Whole-slide image (WSI) classification in computational pathology is commonly formulated as slide-level Multiple Instance Learning (MIL) with a single global bag representation. However, slide-level MIL is fundamentally underconstrained: optimizing only global labels encourages models to aggregate features without learning anatomically meaningful localization. This creates a mismatch between the scale of supervision and the scale of clinical reasoning. Clinicians assess tumor burden, focal lesions, and architectural patterns within millimeter-scale regions, whereas standard MIL is trained only to predict whether "somewhere in the slide there is cancer." As a result, the model's inductive bias effectively erases anatomical structure. We propose Progressive-Context MIL (PC-MIL), a framework that treats the spatial extent of supervision as a first-class design dimension. Rather than altering magnification, patch size, or introducing pixel-level segmentation, we decouple feature resolution from supervision scale. Using fixed 20x features, we vary MIL bag extent in millimeter units and anchor supervision at a clinically motivated 2mm scale to preserve comparable tumor burden and avoid confounding scale with lesion density. PC-MIL progressively mixes slide- and region-level supervision in controlled proportions, enabling explicit train-context x test-context analysis. On 1,476 prostate WSIs from five public datasets for binary cancer detection, we show that anatomical context is an independent axis of generalization in MIL, orthogonal to feature resolution: modest regional supervision improves cross-context performance, and balanced multi-context training stabilizes accuracy across slide and regional evaluation without sacrificing global performance. These results demonstrate that supervision extent shapes MIL inductive bias and support anatomically grounded WSI generalization.

cs.CV↗
arXiv2026

SIMPLER: H&E-Informed Representation Learning for Structured Illumination Microscopy

Structured Illumination Microscopy (SIM) enables rapid, high-contrast optical sectioning of fresh tissue without staining or physical sectioning, making it promising for intraoperative and point-of-care diagnostics. Recent foundation and large-scale self-supervised models in digital pathology have demonstrated strong performance on section-based modalities such as Hematoxylin and Eosin (H&E) and immunohistochemistry (IHC). However, these approaches are predominantly trained on thin tissue sections and do not explicitly address thick-tissue fluorescence modalities such as SIM. When transferred directly to SIM, performance is constrained by substantial modality shift, and naive fine-tuning often overfits to modality-specific appearance rather than underlying histological structure. We introduce SIMPLER (Structured Illumination Microscopy-Powered Learning for Embedding Representations), a cross-modality self-supervised pretraining framework that leverages H&E as a semantic anchor to learn reusable SIM representations. H&E encodes rich cellular and glandular structure aligned with established clinical annotations, while SIM provides rapid, nondestructive imaging of fresh tissue. During pretraining, SIM and H&E are progressively aligned through adversarial, contrastive, and reconstruction-based objectives, encouraging SIM embeddings to internalize histological structure from H&E without collapsing modality-specific characteristics. A single pretrained SIMPLER encoder transfers across multiple downstream tasks, including multiple instance learning and morphological clustering, consistently outperforming SIM models trained from scratch or H&E-only pretraining. These results suggest that histology-guided cross-modal pretraining yields biologically grounded SIM embeddings suitable for broad downstream reuse.

cs.CV↗
arXiv2026

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the RAG workflow, this paper analyzes the underlying vulnerability mechanisms and systematically categorizes core threat vectors such as data poisoning, adversarial attacks, and membership inference attacks. Based on this threat assessment, we construct a taxonomy of RAG defense technologies from a dual perspective encompassing both input and output stages. The input-side analysis reviews data protection mechanisms including dynamic access control, homomorphic encryption retrieval, and adversarial pre-filtering. The output-side examination summarizes advanced leakage prevention techniques such as federated learning isolation, differential privacy perturbation, and lightweight data sanitization. To establish a unified benchmark for future experimental design, we consolidate authoritative test datasets, security standards, and evaluation frameworks. To the best of our knowledge, this paper presents the first end-to-end survey dedicated to the security of RAG systems. Distinct from existing literature that isolates specific vulnerabilities, we systematically map the entire pipeline-providing a unified analysis of threat models, defense mechanisms, and evaluation benchmarks. By enabling deep insights into potential risks, this work seeks to foster the development of highly robust and trustworthy next-generation RAG systems.

cs.CR↗
arXiv2026

A categorical equivalence for monadic algebras of first-order substructural logics motivated by Kalman's construction

The category $\mathbb{DRDL'}$, whose objects are c-differential residuated distributive lattices that satisfy the condition $\mathbf{CK}$, is the image of the category $\mathbb{RDL}$, whose objects are residuated distributive lattices, under the categorical equivalence (Kalman functor) $\mathbf{K}$. The main goal of this paper is to lift this equivalence $\mathbf{K}$ to the category $\mathbb{MRDL}$, whose objects are monadic residuated distributive lattices, and the category $\mathbb{MDRDL'}$, whose objects are pairs formed by an object of $\mathbb{DRDL'}$ and a center universal quantifier. Firstly, based on the variety of monadic FL$_\textrm{e}$-algebras, we introduce the concept of monadic residuated lattices and study some of their further algebraic properties, proving the classes of monadic residuated distributive lattices and monadic c-differential residuated distributive lattices are in one-to-one correspondence. Subsequently, based on this corresponding relation, we prove that there exists a categorical equivalence between the categories $\mathbb{MRDL}$ and $\mathbb{MDRDL'}$. The results of this paper not only generalizes the works of Sagastume and San Mart\'{i}n in [Mathematical Logic Quarterly, {\bf 60}(2014), 375--388], but also addresses and overcomes the limitations identified in the works of [Studia Logica, {\bf 111}(2023), 361--390]. Finally, this paper concludes with some applications regarding descriptions of a 2-contextual translation.

math.LO↗
arXiv2026

SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language Models

While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual understanding, they often struggle when faced with the unstructured and ambiguous nature of human-generated sketches. This limitation is particularly pronounced in the underexplored task of visual grading, where models should not only solve a problem but also diagnose errors in hand-drawn diagrams. Such diagnostic capabilities depend on complex structural, semantic, and metacognitive reasoning. To bridge this gap, we introduce SketchJudge, a novel benchmark tailored for evaluating MLLMs as graders of hand-drawn STEM diagrams. SketchJudge encompasses 1,015 hand-drawn student responses across four domains: geometry, physics, charts, and flowcharts, featuring diverse stylistic variations and distinct error types. Evaluations on SketchJudge demonstrate that even advanced MLLMs lag significantly behind humans, validating the benchmark's effectiveness in exposing the fragility of current vision-language alignment in symbolic and noisy contexts. All data, code, and evaluation scripts are publicly available at https://github.com/yuhangsu82/SketchJudge.

cs.CV↗
arXiv2025

Fake-in-Facext: Towards Fine-Grained Explainable DeepFake Analysis

The advancement of Multimodal Large Language Models (MLLMs) has bridged the gap between vision and language tasks, enabling the implementation of Explainable DeepFake Analysis (XDFA). However, current methods suffer from a lack of fine-grained awareness: the description of artifacts in data annotation is unreliable and coarse-grained, and the models fail to support the output of connections between textual forgery explanations and the visual evidence of artifacts, as well as the input of queries for arbitrary facial regions. As a result, their responses are not sufficiently grounded in Face Visual Context (Facext). To address this limitation, we propose the Fake-in-Facext (FiFa) framework, with contributions focusing on data annotation and model construction. We first define a Facial Image Concept Tree (FICT) to divide facial images into fine-grained regional concepts, thereby obtaining a more reliable data annotation pipeline, FiFa-Annotator, for forgery explanation. Based on this dedicated data annotation, we introduce a novel Artifact-Grounding Explanation (AGE) task, which generates textual forgery explanations interleaved with segmentation masks of manipulated artifacts. We propose a unified multi-task learning architecture, FiFa-MLLM, to simultaneously support abundant multimodal inputs and outputs for fine-grained Explainable DeepFake Analysis. With multiple auxiliary supervision tasks, FiFa-MLLM can outperform strong baselines on the AGE task and achieve SOTA performance on existing XDFA datasets. The code and data will be made open-source at https://github.com/lxq1000/Fake-in-Facext.

cs.CV↗
arXiv2025

Discerning minds or generic tutors? Evaluating instructional guidance capabilities in Socratic LLMs

The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. While prior research has primarily examined their ability to generate Socratic questions, it often overlooks a critical aspect: adaptively guiding learners in accordance with their cognitive states. This study moves beyond question generation to emphasize instructional guidance capability. We ask: Can LLMs emulate expert tutors who dynamically adjust strategies in response to learners' states? To investigate this, we propose GuideEval, a benchmark grounded in authentic educational dialogues that evaluates pedagogical guidance through a three-phase behavioral framework: (1) Perception, inferring learner states; (2) Orchestration, adapting instructional strategies; and (3) Elicitation, stimulating proper reflections. Empirical results indicate that existing LLMs often fail to provide effective adaptive scaffolding when learners experience confusion or require redirection. To complement the quantitative evaluation, we conduct a detailed failure case analysis, providing an intuitive understanding of these shortcomings. Furthermore, we introduce a behavior-guided finetuning strategy that leverages behavior-prompted instructional dialogues, substantially enhancing guidance performance. By shifting the focus from isolated content evaluation to learner-centered state-aware interaction, our work advocates a more dialogic paradigm for evaluating Socratic LLMs.

cs.CL↗
arXiv2025

From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation

Large Language Models (LLMs) have demonstrated remarkable capabilities in mathematical problem-solving. However, the transition from providing answers to generating high-quality educational questions presents significant challenges that remain underexplored. To advance Educational Question Generation (EQG) and facilitate LLMs in generating pedagogically valuable and educationally effective questions, we introduce EQGBench, a comprehensive benchmark specifically designed for evaluating LLMs' performance in Chinese EQG. EQGBench establishes a five-dimensional evaluation framework supported by a dataset of 900 evaluation samples spanning three fundamental middle school disciplines: mathematics, physics, and chemistry. The dataset incorporates user queries with varying knowledge points, difficulty gradients, and question type specifications to simulate realistic educational scenarios. Through systematic evaluation of 46 mainstream large models, we reveal significant room for development in generating questions that reflect educational value and foster students' comprehensive abilities.

cs.CL↗
arXiv2025

VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs

Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reasoning, and domain-specific tasks. However, their capacity to reason over multiple, visually similar inputs remains insufficiently explored. Such fine-grained comparative reasoning is central to real-world tasks, especially in mathematics and education, where learners must often distinguish between nearly identical diagrams to identify correct solutions. To address this gap, we present VisioMath, a curated benchmark of 1,800 high-quality K-12 mathematics problems in which all candidate answers are diagrams with subtle visual similarities. A comprehensive evaluation of state-of-the-art LMMs, covering both leading closed-source systems and widely adopted open-source models, reveals a consistent decline in accuracy as inter-image similarity increases. Analysis indicates that the dominant failure mode stems from image-text misalignment: rather than grounding reasoning in textual cues, models often resort to shallow positional heuristics, resulting in systematic errors. We further explore three alignment-oriented strategies, spanning training-free approaches and finetuning, and achieve substantial accuracy gains. We hope that VisioMath will serve as a rigorous benchmark and catalyst for developing LMMs toward deeper diagram understanding, precise comparative reasoning, and grounded multi-image-text integration.

cs.AI↗
arXiv2025

SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving

Large Language Models (LLMs) have achieved remarkable performance across a wide range of mathematical benchmarks. However, concerns remain as to whether these successes reflect genuine reasoning or superficial pattern recognition. Existing evaluation methods, which typically focus either on the final answer or on the intermediate reasoning steps, reduce mathematical reasoning to a shallow input-output mapping, overlooking its inherently multi-stage and multi-dimensional cognitive nature. Inspired by Polya's problem-solving theory, we propose SMART, a benchmark that decomposes mathematical problem-solving into four cognitive dimensions: Semantic Understanding, Mathematical Reasoning, Arithmetic Computation, and Reflection & Refinement, and introduces dimension-specific tasks to measure the corresponding cognitive processes of LLMs. We apply SMART to 22 state-of-the-art open- and closed-source LLMs and uncover substantial discrepancies in their capabilities across dimensions. Our findings reveal genuine weaknesses in current models and motivate a new metric, the All-Pass Score, designed to better capture true problem-solving capability.

cs.AI↗
arXiv2025

Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants

Faces and humans are crucial elements in social interaction and are widely included in everyday photos and videos. Therefore, a deep understanding of faces and humans will enable multi-modal assistants to achieve improved response quality and broadened application scope. Currently, the multi-modal assistant community lacks a comprehensive and scientific evaluation of face and human understanding abilities. In this paper, we first propose a hierarchical ability taxonomy that includes three levels of abilities. Then, based on this taxonomy, we collect images and annotations from publicly available datasets in the face and human community and build a semi-automatic data pipeline to produce problems for the new benchmark. Finally, the obtained Face-Human-Bench includes a development set and a test set, each with 1800 problems, supporting both English and Chinese. We conduct evaluations over 25 mainstream multi-modal large language models (MLLMs) with our Face-Human-Bench, focusing on the correlation between abilities, the impact of the relative position of targets on performance, and the impact of Chain of Thought (CoT) prompting on performance. We also explore which abilities of MLLMs need to be supplemented by specialist models. The dataset and evaluation code have been made publicly available at https://face-human-bench.github.io.

cs.CV↗
arXiv2024

Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition

The study of oracle characters plays an important role in Chinese archaeology and philology. However, the difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. In this paper, we develop a novel unsupervised domain adaptation (UDA) method, i.e., unsupervised attention regularization net?work (UARN), to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data. First, we experimentally prove that existing UDA methods are not always consistent with human priors and cannot achieve optimal performance on the target domain. For these oracle characters with flip-insensitivity and high inter-class similarity, model interpretations are not flip-consistent and class-separable. To tackle this challenge, we take into consideration visual perceptual plausibility when adapting. Specifically, our method enforces attention consistency between the original and flipped images to achieve the model robustness to flipping. Simultaneously, we constrain attention separability between the pseudo class and the most confusing class to improve the model discriminability. Extensive experiments demonstrate that UARN shows better interpretability and achieves state-of-the-art performance on Oracle-241 dataset, substantially outperforming the previously structure-texture separation network by 8.5%.

cs.CV↗
arXiv2024

An Efficient Privacy-aware Split Learning Framework for Satellite Communications

In the rapidly evolving domain of satellite communications, integrating advanced machine learning techniques, particularly split learning, is crucial for enhancing data processing and model training efficiency across satellites, space stations, and ground stations. Traditional ML approaches often face significant challenges within satellite networks due to constraints such as limited bandwidth and computational resources. To address this gap, we propose a novel framework for more efficient SL in satellite communications. Our approach, Dynamic Topology Informed Pruning, namely DTIP, combines differential privacy with graph and model pruning to optimize graph neural networks for distributed learning. DTIP strategically applies differential privacy to raw graph data and prunes GNNs, thereby optimizing both model size and communication load across network tiers. Extensive experiments across diverse datasets demonstrate DTIP's efficacy in enhancing privacy, accuracy, and computational efficiency. Specifically, on Amazon2M dataset, DTIP maintains an accuracy of 0.82 while achieving a 50% reduction in floating-point operations per second. Similarly, on ArXiv dataset, DTIP achieves an accuracy of 0.85 under comparable conditions. Our framework not only significantly improves the operational efficiency of satellite communications but also establishes a new benchmark in privacy-aware distributed learning, potentially revolutionizing data handling in space-based networks.

cs.LG↗
arXiv2024

Faceptor: A Generalist Model for Face Perception

With the comprehensive research conducted on various face analysis tasks, there is a growing interest among researchers to develop a unified approach to face perception. Existing methods mainly discuss unified representation and training, which lack task extensibility and application efficiency. To tackle this issue, we focus on the unified model structure, exploring a face generalist model. As an intuitive design, Naive Faceptor enables tasks with the same output shape and granularity to share the structural design of the standardized output head, achieving improved task extensibility. Furthermore, Faceptor is proposed to adopt a well-designed single-encoder dual-decoder architecture, allowing task-specific queries to represent new-coming semantics. This design enhances the unification of model structure while improving application efficiency in terms of storage overhead. Additionally, we introduce Layer-Attention into Faceptor, enabling the model to adaptively select features from optimal layers to perform the desired tasks. Through joint training on 13 face perception datasets, Faceptor achieves exceptional performance in facial landmark localization, face parsing, age estimation, expression recognition, binary attribute classification, and face recognition, achieving or surpassing specialized methods in most tasks. Our training framework can also be applied to auxiliary supervised learning, significantly improving performance in data-sparse tasks such as age estimation and expression recognition. The code and models will be made publicly available at https://github.com/lxq1000/Faceptor.

cs.CV↗