arXiv subjects

Xiao-Yu Zhang

Publications and source records attributed to Xiao-Yu Zhang.

At least 19 recordsLinked to original sources

arXiv2026

CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection

The proliferation of Large Language Models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks from surface-level textual noise to deep cognitive and logical manipulation. This shift severely undermines existing detectors, which conventionally rely on static attack assumptions and fixed training distributions. To bridge this gap, we introduce CogniDir, an adaptive distributional learning framework that reformulates robust detection as a dynamic data mixture optimization problem for social media content safety. Grounded in cognitive psychology, we first formalize mechanism-specific cognitive adversarial paradigms to systematically expose deep-seated detector vulnerabilities. To address the vulnerability heterogeneity, CogniDir derives an information-theoretic score coupling empirical accuracy with probabilistic confidence, which is then mapped to adaptive sampling proportions through a Dirichlet-mean parameterization. This formulation enables smooth, feedback-driven reallocation of training exposure toward the most brittle attack mechanisms. Experimental results on three benchmarks demonstrate that CogniDir yields state-of-the-art robustness, improving F1 scores by up to 17.9% over competitive baselines under heterogeneous, AI-generated adversarial pressures.

cs.LG↗

arXiv2026

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rises significantly when the thinking mode is activated, where the critical routing decisions are concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks.

cs.CL↗

arXiv2026

Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation

Publishing private face recognition~(FR) training datasets is privacy-sensitive because faces expose identity information. Private FR training dataset publication mitigates this risk by releasing protected proxies as substitutes for private training faces. However, training FR models with such data introduces an identity paradox: \emph{the identity cues that make released faces useful for recognition supervision are also the cues that make them linkable to real individuals.} A protected face should be decoupled from the original identity, yet still behave as a reliable identity sample for training. Removing these cues too aggressively may destroy the class structure needed for recognition learning, whereas preserving them too faithfully may increase source-identity linkability. We argue that this paradox stems from conflating source-aligned identity semantics with recognition-useful proxy identity geometry. The former should be suppressed to reduce linkage to private individuals, while the latter should be preserved for FR learning. Based on this insight, we propose \textbf{Private Face Distillation}, an identity-decoupling and geometry-preserving framework. It uses Orthogonal Geometry Preservation to construct decoupled proxy identities from private identity representations while maintaining hyperspherical geometry, and Relational Topology Alignment to preserve identity relations for recognition learning. Experiments across multiple domain-shifted FR scenarios show that Private Face Distillation achieves stronger utility than the evaluated publication baselines. On IJB-C surveillance, it improves $\mathrm{TAR}@\mathrm{FAR}{=}1\text{e-}{3}$ by 3.94\% over the baseline while reducing source-identity linkability. These results suggest that private FR training dataset publication should decouple source-identity correspondence while preserving proxy identity geometry.

cs.CV↗

arXiv2026

Knowing You at First Glance: Inferring Apparent Personality from Faces

Inferring apparent personality from facial images is important in social scenarios for embodied agents in human-robot interaction. Unlike inferring intrinsic personality traits via conversation, this task models first-impression personality perception based solely on facial appearance before interaction begins. Existing studies mainly focus on the Big Five personality model and often rely on language or multimodal inputs. As a result, it remains unclear whether facial cues alone can support meaningful associations with perceived personality traits. This question is particularly relevant for MBTI types, which are widely used in practice and more readily interpretable by large language models. To this end, we propose \textbf{GlanceFace}, an end-to-end framework for apparent personality inference leveraging vision-language models to introduce semantic priors and a semantic-enhanced facial representation module to capture subtle personality-related cues, together with an uncertainty-aware learning strategy to handle noisy and subjective annotations. Extensive experiments demonstrate strong performance on MBTI-based apparent personality benchmarks and reveal relationships between facial characteristics and perceived personality traits, highlighting its potential to support adaptive initial interaction strategies for embodied agents. The code and dataset are available at https://github.com/MrHuan3/GlanceFace.

cs.CV↗

arXiv2026

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

Existing benchmarks have laid the foundation for travel planning agents by establishing API-centric paradigms. However, as the capabilities of Autonomous Agents continue to advance, their evaluation must evolve beyond simple tool execution toward handling the inherent complexities of the open web. Current benchmarks bypass core cognitive hurdles: they fail to account for information noise, ignore multi-source factual contradictions, and overlook the necessity of grounding visual perception into logical planning. We introduce VeriTrip, a verifiable benchmark designed to meet the increasing demands for agent robustness and reliability. VeriTrip shifts the evaluation focus to evidence-grounded reasoning over unstructured multimodal web corpora. It establishes a Multimodal Retrieval Base (MRB) derived from real-world sources, forcing agents to autonomously orchestrate queries across heterogeneous data. A synchronized Verifiable Knowledge Base (VKB) enables a cell-wise verification protocol that precisely quantifies factual reliability, distinguishing systematic reasoning failures from parametric hallucinations. Our evaluations across leading MLLMs reveal a critical \textit{retrieval-reasoning trade-off}: the cognitive load of autonomous retrieval significantly erodes instruction retention. VeriTrip provides the rigorous foundation necessary for the next generation of planning agents capable of operating in unconstrained, multimodal environments.

cs.AI↗

arXiv2026

Neutrinoless double-beta decay of the $Δ^-$ resonance

The subprocess $nn\to ppe^-e^-$ is a key ingredient in the interpretation of nuclear neutrinoless double-beta decay. Intermediate $Δ$ resonances may provide additional enhancements to this transition. We take a first step toward a $Δ$-full description of $nn\to ppe^-e^-$ by investigating the neutrinoless double-beta decay $Δ^- \to p e^-e^-$ in the framework of chiral effective field theory. We systematically derive the long-range contribution from light-Majorana-neutrino exchange through loop diagrams and incorporate the short-range part through counterterms required by renormalization. We predict the pion-mass dependence of the decay amplitude in the kinematic configuration with collinear electrons. Furthermore, to facilitate lattice-QCD matching, we calculate the decay amplitude in the degenerate $Δ$-nucleon mass limit and provide the corresponding long-range prediction.

hep-ph↗

arXiv2026

Multimodal Graph Network Modeling for Human-Object Interaction Detection with PDE Graph Diffusion

Existing GNN-based Human-Object Interaction (HOI) detection methods rely on simple MLPs to fuse instance features and propagate information. However, this mechanism is largely empirical and lack of targeted information propagation process. To address this problem, we propose Multimodal Graph Network Modeling (MGNM) for HOI detection with Partial Differential Equation (PDE) graph diffusion. Specifically, we first design a multimodal graph network framework that explicitly models the HOI detection task within a four-stage graph structure. Next, we propose a novel PDE diffusion mechanism to facilitate information propagation within this graph. This mechanism leverages multimodal features to propaganda information via a white-box PDE diffusion equation. Furthermore, we design a variational information squeezing (VIS) mechanism to further refine the multimodal features extracted from CLIP, thereby mitigating the impact of noise inherent in pretrained Vision-Language Models. Extensive experiments demonstrate that our MGNM achieves state-of-the-art performance on two widely used benchmarks: HICO-DET and V-COCO. Moreover, when integrated with a more advanced object detector, our method yields significant performance gains while maintaining an effective balance between rare and non-rare categories.

cs.CV↗

arXiv2026

Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics

While Vision-Language Models (VLMs) like CLIP have emerged as a dominant paradigm for generalizable deepfake detection, a representational disconnect remains: their semantic-centric pre-training is ill-suited for capturing non-semantic artifacts inherent to hyper-realistic synthesis. In this work, we identify a failure mode termed Optimization Collapse, where detectors trained with Sharpness-Aware Minimization (SAM) degenerate to random guessing on non-semantic forgeries once the perturbation radius exceeds a narrow threshold. To theoretically formalize this collapse, we propose the Critical Optimization Radius (COR) to quantify the geometric stability of the optimization landscape, and leverage the Gradient Signal-to-Noise Ratio (GSNR) to measure generalization potential. We establish a theorem proving that COR increases monotonically with GSNR, thereby revealing that the geometric instability of SAM optimization originates from degraded intrinsic generalization potential. This result identifies the layer-wise attenuation of GSNR as the root cause of Optimization Collapse in detecting non-semantic forgeries. Although naively reducing perturbation radius yields stable convergence under SAM, it merely treats the symptom without mitigating the intrinsic generalization degradation, necessitating enhanced gradient fidelity. Building on this insight, we propose the Contrastive Regional Injection Transformer (CoRIT), which integrates a computationally efficient Contrastive Gradient Proxy (CGP) with three training-free strategies: Region Refinement Mask to suppress CGP variance, Regional Signal Injection to preserve CGP magnitude, and Hierarchical Representation Integration to attain more generalizable representations. Extensive experiments demonstrate that CoRIT mitigates optimization collapse and achieves state-of-the-art generalization across cross-domain and universal forgery benchmarks.

cs.CV↗

arXiv2026

One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry

Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves stability by constraining a conservative objective, it shares a fundamental limitation with GRPO: reliance on a fixed aggregation geometry that ignores the evolving and heterogeneous nature of each trajectory. In this work, we unify these approaches under Power-Mean Policy Optimization (PMPO), a generalized framework that parameterizes the aggregation geometry via the power-mean geometry exponent p. Within this framework, GRPO and GMPO are recovered as special cases. Theoretically, we demonstrate that adjusting p modulates the concentration of gradient updates, effectively reweighting tokens based on their advantage contribution. To determine p adaptively, we introduce a Clip-aware Effective Sample Size (ESS) mechanism. Specifically, we propose a deterministic rule that maps a trajectory clipping fraction to a target ESS. Then, we solve for the specific p to align the trajectory induced ESS with this target one. This allows PMPO to dynamically transition between the aggressive arithmetic mean for reliable trajectories and the conservative geometric mean for unstable ones. Experiments on multiple mathematical reasoning benchmarks demonstrate that PMPO outperforms strong baselines.

cs.CL↗

arXiv2025

Production of $J/ψp \bar p$ in electron-positron collisions

The discoveries of the hidden-charm $P_c$ pentaquarks by the LHCb Collaboration have been not confirmed by other experiments yet. It is desirable to investigate the feasibility of observing them in other experiments. We present an order-of-magnitude estimate of the cross section of the $e^+e^-\to J/ψp \bar p$ process, where the hidden-charm pentaquarks may be searched for, and find it to be of $\mathcal{O}(4~\text{fb})$ when the $e^+e^-$ c.m. energy is around 6 GeV. The cross section for $e^+e^-\to P_c \bar p$ is then estimated to be $\lesssim \mathcal{O}(0.1~\text{pb})$. Thus, it is promising to search for $P_c$ at the future high-luminosity super tau-charm facilities with annual integrated luminosity about $1~ab^{-1}$. We also predict the branching fraction of $Υ\to J/ψp\bar p$ to be of $\mathcal{O}(2\times 10^{-6})$, which can be tested at $B$ factories.

hep-ph↗

arXiv2025

Straighter Flow Matching via a Diffusion-Based Coupling Prior

Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling strategy for straightening trajectories to few-step generation. To address this issue, we propose a novel approach, Straighter trajectories of Flow Matching (StraightFM). It straightens trajectories with the coupling strategy from the entire distribution level. More specifically, during training, StraightFM creates couplings of images and noise via one diffusion model as a coupling prior to straighten trajectories for few-step generation. Our coupling strategy can also integrate with the existing coupling direction from real data to noise, improving image quality in few-step generation. Experimental results on pixel space and latent space show that StraightFM yields attractive samples within 5 steps. Moreover, our unconditional StraightFM is seamlessly compatible with training-free multimodal conditional generation, maintaining high-quality image generation in few steps.

cs.CV↗

arXiv2025

RealisVSR: Detail-enhanced Diffusion for Real-World 4K Video Super-Resolution

Video Super-Resolution (VSR) has achieved significant progress through diffusion models, effectively addressing the over-smoothing issues inherent in GAN-based methods. Despite recent advances, three critical challenges persist in VSR community: 1) Inconsistent modeling of temporal dynamics in foundational models; 2) limited high-frequency detail recovery under complex real-world degradations; and 3) insufficient evaluation of detail enhancement and 4K super-resolution, as current methods primarily rely on 720P datasets with inadequate details. To address these challenges, we propose RealisVSR, a high-frequency detail-enhanced video diffusion model with three core innovations: 1) Consistency Preserved ControlNet (CPC) architecture integrated with the Wan2.1 video diffusion to model the smooth and complex motions and suppress artifacts; 2) High-Frequency Rectified Diffusion Loss (HR-Loss) combining wavelet decomposition and HOG feature constraints for texture restoration; 3) RealisVideo-4K, the first public 4K VSR benchmark containing 1,000 high-definition video-text pairs. Leveraging the advanced spatio-temporal guidance of Wan2.1, our method requires only 5-25% of the training data volume compared to existing approaches. Extensive experiments on VSR benchmarks (REDS, SPMCS, UDM10, YouTube-HQ, VideoLQ, RealisVideo-720P) demonstrate our superiority, particularly in ultra-high-resolution scenarios.

eess.IV↗

arXiv2025

Production of $1^{-+}$ exotic charmonium-like states in electron-positron collisions

The absence of observed charmonium-like states with the exotic quantum numbers $J^{PC}=1^{-+}$ has prompted us to investigate the production rates of the $1^{-+}$ $D\bar D_1(2420)$ and $D^*\bar D_1(2420)$ hadronic molecules, which we refer to as $η_{c1}$ and $η_{c1}^{\prime}$, respectively, in electron-positron collisions. Assuming a hadronic molecular nature for the vector charmonium-like states $ψ(4360)$ and $ψ(4415)$, we evaluate the radiative decay widths of $ψ(4360)\toγη_{c1}$ and $ψ(4415)\toγη_{c1}^{\prime}$. Using these decay widths, we estimate the cross sections for producing $η_{c1}$ and $η_{c1}^{\prime}$ in electron-positron annihilations, as well as the event numbers at the planned Super $τ$-Charm Facility. Our results suggest that the ideal energy region for observing these states is around $4.44$ and $4.50$ GeV, just above the $D^* \bar D_1(2420)$ and $D^*\bar D_2^*(2460)$ thresholds, respectively.

hep-ph↗

arXiv2025

Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data

Synthetic data is gaining increasing popularity for face recognition technologies, mainly due to the privacy concerns and challenges associated with obtaining real data, including diverse scenarios, quality, and demographic groups, among others. It also offers some advantages over real data, such as the large amount of data that can be generated or the ability to customize it to adapt to specific problem-solving needs. To effectively use such data, face recognition models should also be specifically designed to exploit synthetic data to its fullest potential. In order to promote the proposal of novel Generative AI methods and synthetic data, and investigate the application of synthetic data to better train face recognition systems, we introduce the 2nd FRCSyn-onGoing challenge, based on the 2nd Face Recognition Challenge in the Era of Synthetic Data (FRCSyn), originally launched at CVPR 2024. This is an ongoing challenge that provides researchers with an accessible platform to benchmark i) the proposal of novel Generative AI methods and synthetic data, and ii) novel face recognition systems that are specifically proposed to take advantage of synthetic data. We focus on exploring the use of synthetic data both individually and in combination with real data to solve current challenges in face recognition such as demographic bias, domain adaptation, and performance constraints in demanding situations, such as age disparities between training and testing, changes in the pose, or occlusions. Very interesting findings are obtained in this second edition, including a direct comparison with the first one, in which synthetic databases were restricted to DCFace and GANDiffFace.

cs.CV↗

arXiv2024

Magnifier: Detecting Network Access via Lightweight Traffic-based Fingerprints

Network access detection plays a crucial role in global network management, enabling efficient network monitoring and topology measurement by identifying unauthorized network access and gathering detailed information about mobile devices. Existing methods for endpoint-based detection primarily rely on deploying monitoring software to recognize network connections. However, the challenges associated with developing and maintaining such systems have limited their universality and coverage in practical deployments, especially given the cost implications of covering a wide array of devices with heterogeneous operating systems. To tackle the issues, we propose Magnifier for mobile device network access detection that, for the first time, passively infers access patterns from backbone traffic at the gateway level. Magnifier's foundation is the creation of device-specific access patterns using the innovative Domain Name Forest (dnForest) fingerprints. We then employ a two-stage distillation algorithm to fine-tune the weights of individual Domain Name Trees (dnTree) within each dnForest, emphasizing the unique device fingerprints. With these meticulously crafted fingerprints, Magnifier efficiently infers network access from backbone traffic using a lightweight fingerprint matching algorithm. Our experimental results, conducted in real-world scenarios, demonstrate that Magnifier exhibits exceptional universality and coverage in both initial and repetitive network access detection in real-time. To facilitate further research, we have thoughtfully curated the NetCess2023 dataset, comprising network access data from 26 different models across 7 brands, covering the majority of mainstream mobile devices. We have also made both the Magnifier prototype and the NetCess2023 dataset publicly available\footnote{https://github.com/SecTeamPolaris/Magnifier}.

cs.NI↗

arXiv2024

Bardeen-Dirac Stars in AdS Spacetime

In this paper, we construct a static spherical symmetric Bardeen-Dirac Stars (BDSs) in the four-dimensional Anti-de Sitter (AdS) spacetime, which consists of the electromagnetic field and Dirac field coupled to gravity. We investigate the ADM mass, Noether charge and light rings of BDSs in AdS spacetime. In asymptotically Minkowski spacetime, the maximum frequency of BDSs is one. However, we observe that the maximum frequency of BDSs increases as the cosmological constant decreases in AdS spacetime. Additionally, BDSs can exhibit extreme behavior at low frequencies, refer to as Frozen Bardeen-Dirac stars (FBDSs) in AdS spacetime. FBDSs have a critical event horizon, where the metric function gtt is very close to zero. The matter is entirely encapsulated by this critical horizon, highly concentrated within it. When the magnetic charge is fixed, the FBDSs gradually disappear as the cosmological constant decreases.

gr-qc↗

arXiv2024

GAN Inversion for Image Editing via Unsupervised Domain Adaptation

Existing GAN inversion methods work brilliantly in reconstructing high-quality (HQ) images while struggling with more common low-quality (LQ) inputs in practical application. To address this issue, we propose Unsupervised Domain Adaptation (UDA) in the inversion process, namely UDA-inversion, for effective inversion and editing of both HQ and LQ images. Regarding unpaired HQ images as the source domain and LQ images as the unlabeled target domain, we introduce a theoretical guarantee: loss value in the target domain is upper-bounded by loss in the source domain and a novel discrepancy function measuring the difference between two domains. Following that, we can only minimize this upper bound to obtain accurate latent codes for HQ and LQ images. Thus, constructive representations of HQ images can be spontaneously learned and transformed into LQ images without supervision. UDA-Inversion achieves a better PSNR of 22.14 on FFHQ dataset and performs comparably to supervised methods.

cs.CV↗

arXiv2024

Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub-tasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.

cs.CV↗