Searcharxiv⌕ Search

arXiv subjects

Ying Zhang

Publications and source records attributed to Ying Zhang.

At least 127 records · Page 7Linked to original sources
arXiv2026

REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and information integrity. This motivates detectors that are not only accurate but also forensically explainable. While recent multimodal approaches improve interpretability, many rely on post-hoc rationalizations or coarse visual cues, without constructing verifiable chains of evidence, thus often leading to poor generalization. We introduce REVEAL-Bench, a reasoning-enhanced multimodal benchmark for AI-generated image forensics, structured around explicit chains of forensic evidence derived from lightweight expert models and consolidated into step-by-step chain-of-evidence traces. Based on this benchmark, we propose REVEAL (\underline{R}easoning-\underline{e}nhanced Forensic E\underline{v}id\underline{e}nce \underline{A}na\underline{l}ysis), an explainable forensic framework trained with expert-grounded reinforcement learning. Our reward design jointly promotes detection accuracy, evidence-grounded reasoning stability, and explanation faithfulness. Extensive experiments demonstrate significantly improved cross-domain generalization and more faithful explanations to baseline detectors. All data and codes will be released.

cs.CV↗
arXiv2026

FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips

Foley art plays a pivotal role in enhancing immersive auditory experiences in film, yet manual creation of spatio-temporally aligned audio remains labor-intensive. We propose FoleyDesigner, a novel framework inspired by professional Foley workflows, integrating film clip analysis, spatio-temporally controllable Foley generation, and professional audio mixing capabilities. FoleyDesigner employs a multi-agent architecture for precise spatio-temporal analysis. It achieves spatio-temporal alignment through latent diffusion models trained on spatio-temporal cues extracted from video frames, combined with large language model (LLM)-driven hybrid mechanisms that emulate post-production practices in film industry. To address the lack of high-quality stereo audio datasets in film, we introduce FilmStereo, the first professional stereo audio dataset containing spatial metadata, precise timestamps, and semantic annotations for eight common Foley categories. For applications, the framework supports interactive user control while maintaining seamless integration with professional pipelines, including 5.1-channel Dolby Atmos systems compliant with ITU-R BS.775 standards, thereby offering extensive creative flexibility. Extensive experiments demonstrate that our method achieves superior spatio-temporal alignment compared to existing baselines, with seamless compatibility with professional film production standards. The project page is available at https://gekiii996.github.io/FoleyDesigner/ .

cs.CV↗
arXiv2026

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly hijack an agent's action space, such as file writes, shell commands, and network requests, despite existing safeguards. We introduce Document-Driven Implicit Payload Execution (DDIPE), which embeds malicious logic in code examples and configuration templates within skill documentation. Because agents reuse these examples during normal tasks, the payload executes without explicit prompts. Using an LLM-driven pipeline, we generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories. Across four frameworks and five models, DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses. Static analysis detects most cases, but 2.5% evade both detection and alignment. Responsible disclosure led to four confirmed vulnerabilities and two fixes.

cs.CR↗
arXiv2026

A Framework for Human-AI Q-Matrix Refinement: A NeuralCDM Evaluation

Q-matrices are a cornerstone of theory-driven assessment and learning analytics, making item demands and students' underlying knowledge components and misconceptions explicit and actionable. However, Q-matrices are typically crafted by experts, making them time-consuming to build, prone to subjectivity, and difficult to validate empirically. We propose a framework for human-AI Q-matrix refinement in which large language models (LLMs) generate candidate Q-matrices using structured, misconception-aware prompting, and NeuralCDM provides an empirical evaluation layer to compare candidates based on how well they explain student response data. We apply the framework to a thermodynamics assessment dataset and benchmark locally deployed LLMs against cloud-served models. Results show that iteratively refined LLM-generated Q-matrices can exceed expert-baseline model fit (AUC 0.780 vs. 0.717), and that locally deployed models achieve comparable performance to cloud APIs, supporting privacy-preserving deployment.

cs.CY↗
arXiv2026

How Can ChatGPT Support Human Security Testers to Help Mitigate Supply Chain Attacks?

Developers often build software on top of third-party libraries (Libs) to improve productivity, but these libraries may contain vulnerabilities that enable supply chain attacks. Existing tools detect vulnerable dependencies, yet developers often distrust their reports without concrete exploit evidence. Manually crafting such demonstrations is costly, and tool support is lacking. To help developers enhance software security, in this study, we systematically explored the usage of a large language model (LLM) --ChatGPT-4.0--to generate security tests, which unit tests demonstrate how vulnerable library dependencies facilitate the supply chain attacks to given Apps. In our exploration, we defined prompt templates to take in the various vulnerability-relevant information we manually collected, and generated prompts from those templates to query ChatGPT for security test generation. We found that ChatGPT-generated tests demonstrated 24 pieces of evidence or proof of vulnerability for 49 Apps. To assess the consistency of test generation, we also evaluated another five state-of-the-art LLMs. All the models generated security tests for at least 17 cases that successfully demonstrate the vulnerabilities. We filed six reports for the newly revealed vulnerabilities in Apps, and got four Common Vulnerability Entries (CVEs) assigned. Our use of ChatGPT outperformed two state-of-the-art security test generators (TRANSFER and SIEGE), by generating a lot more tests and achieving more attacks.

cs.CR↗
arXiv2026

A Hypergraph-Based Framework for Exploratory Business Intelligence

Business Intelligence (BI) analysis is evolving towards Exploratory BI, an iterative, multi-round exploration paradigm where analysts progressively refine their understanding. However, traditional BI systems impose critical limits for Exploratory BI: heavy reliance on expert knowledge, high computational costs, static schemas, and lack of reusability. We present ExBI, a novel system that introduces the hypergraph data model with operators, including Source, Join, and View, to enable dynamic schema evolution and materialized view reuse. Using sampling-based algorithms with provable estimation guarantees, ExBI addresses the computational bottlenecks, while maintaining analytical accuracy. Experiments on LDBC datasets demonstrate that ExBI achieves significant speedups over existing systems: on average 16.21x (up to 146.25x) compared to Neo4j and 46.67x (up to 230.53x) compared to MySQL, while maintaining high accuracy with an average error rate of only 0.27% for COUNT, enabling efficient and accurate large-scale exploratory BI workflows.

cs.DB↗
arXiv2026

Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study

Accurate lesion segmentation is essential in medical image analysis, yet most existing methods are designed for specific anatomical sites or imaging modalities, limiting their generalizability. Recent vision-language foundation models enable concept-driven segmentation in natural images, offering a promising direction for more flexible medical image analysis. However, concept-prompt-based lesion segmentation, particularly with the latest Segment Anything Model 3 (SAM3), remains underexplored. In this work, we present a systematic evaluation of SAM3 for lesion segmentation. We assess its performance using geometric bounding boxes and concept-based text and image prompts across multiple modalities, including multiparametric MRI, CT, ultrasound, dermoscopy, and endoscopy. To improve robustness, we incorporate additional prior knowledge, such as adjacent-slice predictions, multiparametric information, and prior annotations. We further compare different fine-tuning strategies, including partial module tuning, adapter-based methods, and full-model optimization. Experiments on 13 datasets covering 11 lesion types demonstrate that SAM3 achieves strong cross-modality generalization, reliable concept-driven segmentation, and accurate lesion delineation. These results highlight the potential of concept-based foundation models for scalable and practical medical image segmentation. Code and trained models will be released at: https://github.com/apple1986/lesion-sam3

eess.IV↗
arXiv2026

Utilizing Adversarial Training for Robust Voltage Control: An Adaptive Deep Reinforcement Learning Method

Adversarial training is a defense method that trains machine learning models on intentionally perturbed attack inputs, so they learn to be robust against adversarial examples. This paper develops a robust voltage control framework for distribution networks with high penetration of distributed energy resources (DERs). Conventional voltage control methods are vulnerable to strategic cyber attacks, as they typically consider only random or black-box perturbations. To address this, we formulate white-box adversarial attacks using Projected Gradient Descent (PGD) and train a deep reinforcement learning (DRL) agent adversarially. The resulting policy adapts in real time to high-impact, strategically optimized perturbations. Simulations on DER-rich networks show that the approach maintains voltage stability and operational efficiency under realistic attack scenarios, highlighting the effectiveness of gradient-based adversarial DRL in enhancing robustness and adaptability in modern distribution system control.

eess.SY↗
arXiv2026

Hyperbolic Multimodal Generative Representation Learning for Generalized Zero-Shot Multimodal Information Extraction

Multimodal information extraction (MIE) constitutes a set of essential tasks aimed at extracting structural information from Web texts with integrating images, to facilitate the structural construction of Web-based semantic knowledge. To address the expanding category set including newly emerging entity types or relations on websites, prior research proposed the zero-shot MIE (ZS-MIE) task which aims to extract unseen structural knowledge with textual and visual modalities. However, the ZS-MIE models are limited to recognizing the samples that fall within the unseen category set, and they struggle to deal with real-world scenarios that encompass both seen and unseen categories. The shortcomings of existing methods can be ascribed to two main aspects. On one hand, these methods construct representations of samples and categories within Euclidean space, failing to capture the hierarchical semantic relationships between the two modalities within a sample and their corresponding category prototypes. On the other hand, there is a notable gap in the distribution of semantic similarity between seen and unseen category sets, which impacts the generative capability of the ZS-MIE models. To overcome the disadvantages, we delve into the generalized zero-shot MIE (GZS-MIE) task and propose the hyperbolic multimodal generative representation learning framework (HMGRL). The variational information bottleneck and autoencoder networks are reconstructed with hyperbolic space for modeling the multi-level hierarchical semantic correlations among samples and prototypes. Furthermore, the proposed model is trained with the unseen samples generated by the decoder, and we introduce the semantic similarity distribution alignment loss to enhance the model's generalization performance. Experimental evaluations on two benchmark datasets underscore the superiority of HMGRL compared to existing baseline methods.

cs.MM↗
arXiv2026

Electric-Field-induced Two-Dimensional Fully Compensated Ferrimagnetism and Emergent Transport Phenomena

The recent discovery of altermagnetism has demonstrated that spin-split electronic band structures can emerge in magnetic systems with zero net magnetization. In contrast, fully compensated ferrimagnetic (fFIM) systems remain far less explored, despite exhibiting similar characteristics such as vanishing magnetization and spin-split bands. Here, based on first-principles calculations combined with theoretical analysis, we demonstrate that monolayer CoS and CoSe can be driven into fFIM states by an external electric field. These materials possess collinear antiferromagnetic ground states with out-of-plane Néel vectors, and their electronic bands are spin degenerate due to $\mathcal{PT}$ symmetry. When an out-of-plane electric field is applied, $\mathcal{PT}$ symmetry is broken, inducing fFIM states with pronounced spin splitting. Moreover, we show that the resulting fFIM states host fully spin-polarized currents, anomalous Hall effects, and magneto-optical Kerr and Faraday effects. Our results establish monolayer CoS and CoSe as promising platforms for electric-field-controlled fFIM states and spintronic applications.

cond-mat.mtrl-sci↗
arXiv2026

Node Role-Guided LLMs for Dynamic Graph Clustering

Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing how complex real-world systems evolve over time. However, existing methods are predominantly black-box models. They lack interpretability in their clustering decisions and fail to provide semantic explanations of why clusters form or how they evolve, severely limiting their use in safety-critical domains such as healthcare or transportation. To address these limitations, we propose an end-to-end interpretable framework that maps continuous graph embeddings into discrete semantic concepts through learnable prototypes. Specifically, we first decompose node representations into orthogonal role and clustering subspaces, so that nodes with similar roles (e.g., hubs, bridges) but different cluster affiliations can be properly distinguished. We then introduce five node role prototypes (Leader, Contributor, Wanderer, Connector, Newcomer) in the role subspace as semantic anchors, transforming continuous embeddings into discrete concepts to facilitate LLM understanding of node roles within communities. Finally, we design a hierarchical LLM reasoning mechanism to generate both clustering results and natural language explanations, while providing consistency feedback as weak supervision to refine node representations. Experimental results on four synthetic and six real-world benchmarks demonstrate the effectiveness, interpretability, and robustness of DyG-RoLLM. Code is available at https://github.com/Clearloveyuan/DyG-RoLLM.

cs.LG↗
arXiv2026

LLM-FK: Multi-Agent LLM Reasoning for Foreign Key Detection in Large-Scale Complex Databases

Detecting missing foreign keys (FKs) requires accurately modeling semantic dependencies across database schemas, which conventional heuristic-based methods are fundamentally limited in capturing. We propose LLM-FK, the first fully automated multi-agent framework for FK detection, designed to address three core challenges that hinder naive LLM-based solutions in large-scale complex databases: combinatorial search space explosion, ambiguous inference under limited context, and global inconsistency arising from isolated local predictions. LLM-FK coordinates four specialized agents: a Profiler that decomposes the FK detection problem into the task of validating FK candidate column pairs and prunes the search space via a unique-key-driven schema decomposition strategy; an Interpreter that injects self-augmented domain knowledge; a Refiner that constructs compact structural representations and performs multi-perspective chain-of-thought reasoning; and a Verifier that enforces schema-wide consistency through a holistic conflict resolution strategy. Experiments on five benchmark datasets demonstrate that LLM-FK consistently achieves F1-scores above 93%, surpassing existing baselines by 15% on the large-scale MusicBrainz database, while reducing the candidate search space by two to three orders of magnitude without losing true FKs and maintaining robustness under challenging conditions like missing data. These results demonstrate the effectiveness and scalability of LLM-FK in real-world databases.

cs.DB↗
arXiv2026

Unified model for breathing solitons in fibre lasers: Mechanisms across below- and above-threshold regimes

The emergence of breathing solitons in mode-locked lasers presents a fundamental challenge for the theoretical modelling of mode locking, with the mechanisms underlying below- and above-threshold breathing solitons, and the origins of their distinct nonlinear dynamics, remaining poorly understood. Here, we develop a model that incorporates both spatial and temporal gain dynamics, enabling us to elucidate the origins of these two classes of pulsating states. We show that below-threshold breathing solitons arise from the interplay between Q-switching and soliton shaping, whereas Kerr nonlinearity and dispersion dominate the formation of above-threshold breathers. The model further captures the markedly different dynamical properties of these regimes. Experimental observations corroborate the simulations, validating the predictive power of the framework. Beyond providing a refined theoretical basis for ultrafast laser design, this work advances the broader understanding of non-equilibrium dynamics in mode-locked lasers and offers new perspectives on breathing soliton phenomena across diverse physical systems.

physics.optics↗
arXiv2026

Intelligent Diagnosis Using Dual-Branch Attention Network for Rare Thyroid Carcinoma Recognition with Ultrasound Imaging

Heterogeneous morphological features and data imbalance pose significant challenges in rare thyroid carcinoma classification using ultrasound imaging. To address this issue, we propose a novel multitask learning framework, Channel-Spatial Attention Synergy Network (CSASN), which integrates a dual-branch feature extractor - combining EfficientNet for local spatial encoding and ViT for global semantic modeling, with a cascaded channel-spatial attention refinement module. A residual multiscale classifier and dynamically weighted loss function further enhance classification stability and accuracy. Trained on a multicenter dataset comprising more than 2000 patients from four clinical institutions, our framework leverages a residual multiscale classifier and dynamically weighted loss function to enhance classification stability and accuracy. Extensive ablation studies demonstrate that each module contributes significantly to model performance, particularly in recognizing rare subtypes such as FTC and MTC carcinomas. Experimental results show that CSASN outperforms existing single-stream CNN or Transformer-based models, achieving a superior balance between precision and recall under class-imbalanced conditions. This framework provides a promising strategy for AI-assisted thyroid cancer diagnosis.

eess.IV↗
arXiv2026

From "What" to "How": Constrained Reasoning for Autoregressive Image Generation

Autoregressive image generation has seen recent improvements with the introduction of chain-of-thought and reinforcement learning. However, current methods merely specify "What" details to depict by rewriting the input prompt, yet fundamentally fail to reason about "How" to structure the overall image. This inherent limitation gives rise to persistent issues, such as spatial ambiguity directly causing unrealistic object overlaps. To bridge this gap, we propose CoR-Painter, a novel framework that pioneers a "How-to-What" paradigm by introducing Constrained Reasoning to guide the autoregressive generation. Specifically, it first deduces "How to draw" by deriving a set of visual constraints from the input prompt, which explicitly govern spatial relationships, key attributes, and compositional rules. These constraints steer the subsequent generation of a detailed description "What to draw", providing a structurally sound and coherent basis for accurate visual synthesis. Additionally, we introduce a Dual-Objective GRPO strategy that specifically optimizes the textual constrained reasoning and visual projection processes to ensure the coherence and quality of the entire generation pipeline. Extensive experiments on T2I-CompBench, GenEval, and WISE demonstrate that our method achieves state-of-the-art performance, with significant improvements in spatial metrics (e.g., +5.41% on T2I-CompBench).

cs.CV↗
arXiv2026

On Discrete Ambiguity Functions of Random Communication Waveforms

This paper provides a fundamental characterization of the discrete ambiguity functions (AFs) of random communication waveforms under arbitrary orthonormal modulation with random constellation symbols, which serve as a key metric for evaluating the delay-Doppler sensing performance in future ISAC applications. A unified analytical framework is developed for two types of AFs, namely the discrete periodic AF (DP-AF) and the fast-slow time AF (FST-AF), where the latter may be seen as a small-Doppler approximation of the DP-AF. By analyzing the expectation of squared AFs, we derive exact closed-form expressions for both the expected sidelobe level (ESL) and the expected integrated sidelobe level (EISL) under the DP-AF and FST-AF formulations. For the DP-AF, we prove that the normalized EISL is identical for all orthogonal waveforms. To gain structural insights, we introduce a matrix representation based on the finite Weyl-Heisenberg (WH) group, where each delay-Doppler shift corresponds to a WH operator acting on the ISAC signal. This WH-group viewpoint yields sharp geometric constraints on the lowest sidelobes: The minimum ESL can only occur along a one-dimensional cut or over a set of widely dispersed delay-Doppler bins. Consequently, no waveform can attain the minimum ESL over any compact two-dimensional region, leading to a no-optimality (no-go) result under the DP-AF framework. For the FST-AF, the closed-form ESL and EISL expressions reveal a constellation-dependent regime governed by its kurtosis: The OFDM modulation achieves the minimum ESL for sub-Gaussian constellations, whereas the OTFS waveform becomes optimal for super-Gaussian constellations. Finally, four representative waveforms, namely, SC, OFDM, OTFS, and AFDM, are examined under both frameworks, and all theoretical results are verified through numerical examples.

cs.IT↗
arXiv2026

Efficient Approximate Nearest Neighbor Search under Multi-Attribute Range Filter

Nearest neighbor search on high-dimensional vectors is fundamental in modern AI and database systems. In many real-world applications, queries involve constraints on multiple numeric attributes, giving rise to range-filtering approximate nearest neighbor search (RFANNS). While there exist RFANNS indexes for single-attribute range predicates, extending them to the multi-attribute setting is nontrivial and often ineffective. In this paper, we propose KHI, an index for multi-attribute RFANNS that combines an attribute-space partitioning tree with HNSW graphs attached to tree nodes. A skew-aware splitting rule bounds the tree height by $O(\log n)$, and queries are answered by routing through the tree and running greedy search on the HNSW graphs. Experiments on four real-world datasets show that KHI consistently achieves high query throughput while maintaining high recall. Compared with the state-of-the-art RFANNS baseline, KHI improves QPS by $2.46\times$ on average and up to $16.22\times$ on the hard dataset, with larger gains for smaller selectivity, larger $k$, and higher predicate cardinality.

cs.DB↗
arXiv2026

Joint analysis for multivariate longitudinal and event time data with a change point anchored at interval-censored event time

Huntington's disease (HD) is an autosomal dominant neurodegenerative disorder characterized by motor dysfunction, psychiatric disturbances, and cognitive decline. The onset of HD is marked by severe motor impairment, which may be predicted by prior cognitive decline and, in turn, exacerbate cognitive deficits. Clinical data, however, are often collected at discrete time points, so the timing of disease onset is subject to interval censoring. To address the challenges posed by such data, we develop a joint model for multivariate longitudinal biomarkers with a change point anchored at an interval-censored event time. The model simultaneously assesses the effects of longitudinal biomarkers on the event time and the changes in biomarker trajectories following the event. We conduct a comprehensive simulation study to demonstrate the finite-sample performance of the proposed method for causal inference. Finally, we apply the method to PREDICT-HD, a multisite observational cohort study of prodromal HD individuals, to ascertain how cognitive impairment and motor dysfunction interact during disease progression.

stat.ME↗