arXiv subjects

Fang Fang

Publications and source records attributed to Fang Fang.

At least 37 records · Page 2Linked to original sources

arXiv2026

AI-Empowered Resource Allocation for Wirelessly Powered Pinching-Antenna Systems

This paper considers a multi-user system, where the users first harvest energy from the base station and then use the harvested energy to transmit information via non-orthogonal multiple access (NOMA). A pinching antenna array is adopted to assist the energy transfer and information transmission, owing to its ability to adapt to dynamic propagation conditions. To enhance the system's energy efficiency (EE), we formulate a joint optimization problem involving antenna positioning, transmit power control, and time-switching ratio selection. The problem is non-convex due to the coupled variables, nonlinear energy-harvesting characteristics, and uncertainties in user locations and battery states. To effectively solve this problem, a deep reinforcement learning-based algorithm is proposed to autonomously learn near-optimal resource allocation policies in dynamic environments. Simulation results demonstrate that the proposed PA-assisted scheme achieves significant gains in EE compared with conventional fixed-antenna schemes.

eess.SP↗

arXiv2026

Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection

The rapid advancement of large language models has increasingly blurred the boundary between human-written and AI-generated text, raising societal risks such as misinformation dissemination, authorship ambiguity, and threats to intellectual property rights. These concerns highlight the urgent need for effective and reliable detection methods. While existing training-free approaches often achieve strong performance by aggregating token-level signals into a global score, they typically assume uniform token contributions, making them less robust under short sequences or localized token modifications. To address these limitations, we propose Exons-Detect, a training-free method for AI-generated text detection based on an exon-aware token reweighting perspective. Exons-Detect identifies and amplifies informative exonic tokens by measuring hidden-state discrepancy under a dual-model setting, and computes an interpretable translation score from the resulting importance-weighted token sequence. Empirical evaluations demonstrate that Exons-Detect achieves state-of-the-art detection performance and exhibits strong robustness to adversarial attacks and varying input lengths. In particular, it attains a 2.2\% relative improvement in average AUROC over the strongest prior baseline on DetectRL.

cs.CL↗

arXiv2026

Visual Distraction Undermines Moral Reasoning in Vision-Language Models

Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as AI systems evolve from text-based assistants to embodied agents. Current safety techniques demonstrate success in textual contexts, but concerns remain about generalization to visual inputs. Existing moral evaluation benchmarks rely on textonly formats and lack systematic control over variables that influence moral decision-making. Here we show that visual inputs fundamentally alter moral decision-making in state-of-the-art (SOTA) Vision-Language Models (VLMs), bypassing text-based safety mechanisms. We introduce Moral Dilemma Simulation (MDS), a multimodal benchmark grounded in Moral Foundation Theory (MFT) that enables mechanistic analysis through orthogonal manipulation of visual and contextual variables. The evaluation reveals that the vision modality activates intuition-like pathways that override the more deliberate and safer reasoning patterns observed in text-only contexts. These findings expose critical fragilities where language-tuned safety filters fail to constrain visual processing, demonstrating the urgent need for multimodal safety alignment.

cs.AI↗

arXiv2026

Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication

Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end training. Specifically, we enforce topological consistency by penalizing Wasserstein distances between cubical persistence diagrams of original and reconstructed images, and between Vietoris--Rips persistence of latent features before and after the channel to promote a robust latent manifold. TopoJSCC is based on end-to-end learning and requires no side information. Experiments show improved topology preservation and peak signal-to-noise ratio (PSNR) in low signal-to-noise ratio (SNR) and bandwidth-ratio regimes.

cs.LG↗

arXiv2026

Realization of the SI Second Defined by Geometric Mean of Multiple Clock Transitions

The current definition of the SI second is based on the 133Cs ground-state hyperfine transition in the microwave domain, with the most accurate realizations achieving fractional frequency uncertainties of about (1-2)E16. In contrast, state-of-the-art optical clocks now demonstrate estimated uncertainties two to three orders of magnitude lower, prompting discussion on the redefinition of the SI second. Several options for the new definition have been proposed, one of which introduces a constant N defined as the weighted geometric mean of multiple clock transition frequencies. In this work, we investigate how N can be practically realized when not all defining transitions are available and when multiple optical clocks operate with different performance levels and non-overlapping uptimes. We consider two complementary realization and reconstruction routes. One route is based on geometric-mean combinations, and the other is based on arithmetic-mean combinations. We derive consistent uncertainty expressions that incorporate both measurement uncertainties and, where required, uncertainties of recommended frequencies or frequency ratios. Using analytic three-transition case studies, we identify the parameter regimes in which each route yields a lower total uncertainty and provide explicit conditions for the crossover between them. We further address the dominant role of dead time when a hydrogen maser serves as a flywheel reference by introducing a time-segmented, time-weighted combination based on coefficient and covariance matrices, which accounts for overlapping operation and correlations across measurement intervals. Our findings offer practical guidance for minimizing total uncertainty in multi-clock realizations and contribute to ongoing efforts toward redefining the SI second.

physics.atom-ph↗

arXiv2026

On Dual-Fed Pinching Antenna Systems with In-Waveguide Attenuation

Pinching antenna systems (PAS) have recently emerged as a promising architecture for flexible and reconfigurable wireless communications. However, their performance is fundamentally constrained by in-waveguide attenuation, which is non-negligible in practical dielectric waveguides and can severely degrade the achievable data rate, particularly for long waveguides. To overcome this limitation, we propose a dual-fed PAS (DF-PAS), in which each waveguide is equipped with two feed points located at the two ends, enabling dynamic feed-point selection based on user locations. This design effectively shortens the in-waveguide propagation distance and mitigates attenuation-induced power loss without modifying the waveguide structure or the PA actuation mechanism. We investigate the DF-PAS in both single- and multi-waveguide scenarios. For the single-waveguide case, we derive closed-form high-SNR approximations of the ergodic rate and obtain closed-form solutions for the optimal PA position and feed-point selection under time-division multiple access (TDMA). We then extend DF-PAS to a multi-waveguide scenario, where we first derive closed-form high-SNR approximations of the ergodic rate and then formulate a joint optimization problem over feed-point selection, PA placement, and beamforming under general orthogonal multiple access (OMA). To solve this problem efficiently, we develop a two-phase optimization framework that integrates greedy feed-point switching, gradient-based PA placement, and WMMSE-based beamforming. Simulation results demonstrate that the proposed DF-PAS consistently outperforms conventional single-fed PAS (SF-PAS) across various network configurations, validating its effectiveness as a practical and scalable solution for mitigating in-waveguide attenuation in PAS-enabled wireless networks.

eess.SP↗

arXiv2026

Secure Semantic Communications via AI Defenses: Fundamentals, Solutions, and Future Directions

Semantic communication (SemCom) redefines wireless communication from reproducing symbols to transmitting task-relevant semantics. However, this AI-native architecture also introduces new vulnerabilities, as semantic failures may arise from adversarial perturbations to models, corrupted training data, desynchronized priors, or misaligned inference even when lower-layer transmission reliability and cryptographic protection remain intact. This survey provides a defense-centered and system-oriented synthesis of security in SemCom via AI defense. We analyze AI-centric threat models by consolidating existing studies and organizing attack surfaces across model-level, channel-realizable, knowledge-based, and networked inference vectors. Building on this foundation, we present a structured taxonomy of defense strategies organized by where semantic integrity can be compromised in SemCom systems despite correct symbol delivery, spanning semantic encoding, wireless transmission, knowledge integrity, and coordination among multiple agents. These categories correspond to distinct security failure modes, including representation fragility, channel-realizable manipulation, semantic prior poisoning or desynchronization, and adversarial propagation through distributed inference. We also examine security utility operating envelopes that capture tradeoffs among semantic fidelity, robustness, latency, and energy under realistic constraints, survey evaluation frameworks and representative applications, and identify open challenges in cross-layer composition and deployment-time certification. Overall, this survey offers a unified system-level perspective that enables readers to understand major threat and defense mechanisms in AI-native SemCom systems and to leverage emerging security techniques in the design and deployment of robust SemCom architectures for next-generation intelligent networks.

cs.CR↗

arXiv2026

Dimension-Reduced Cosine Expansions via Tensor Decomposition: Methodology and Applications to Credit Exposure Quantification

This paper initiates a series of studies on a COS-tensor framework, as an efficient alternative to MC for large and liquid portfolios characterized by a modest number of dominant risk factors but a large number of trades. The framework is built on three key insights. First, the cumulative distribution function (CDF) of portfolio level mark-to-market (MtM) values and exposures can be recovered in the Fourier domain by first numerically evaluating their characteristic functions and subsequently applying the one-dimensional COS method. Second, the curse of dimensionality arising in the evaluation of netting-set characteristic functions is mitigated by dimension-reduced cosine expansions derived by combining Fourier-cosine series representations with tensor decomposition techniques. This reformulation shifts the main computational burden from online evaluation to an offline training stage. Third, the offline training can be performed directly in the Fourier domain by reapplying the core idea of the COS method. This improves both training speed and accuracy by more than two orders of magnitude compared with gradient-based training in the physical domain. This paper establishes the core methodology of dimension-reduced cosine expansions, together with the efficient training algorithm, and applies it to netting-set-level MtM and exposure calculations. Among several tensor decomposition techniques, we focus on Canonical Polyadic Decomposition (CPD) for CCR quantification due to its simplicity and transparency, which are particularly appealing in practical risk-management applications. Numerical experiments on netting sets comprising tens of thousands of trades driven by seven risk factors demonstrate that the proposed method achieves relative errors below 0.1% while requiring only a small fraction of the runtime of MC simulation.

q-fin.CP↗

arXiv2026

Parallel Collaborative ADMM Privacy Computing and Adaptive GPU Acceleration for Distributed Edge Networks

Distributed computing has been widely applied in distributed edge networks for reducing the processing burden of high-dimensional data centralization, where a high-dimensional computational task is decomposed into multiple low-dimensional collaborative processing tasks or multiple edge nodes use distributed data to train a global model. However, the computing power of a single-edge node is limited, and collaborative computing will cause information leakage and excessive communication overhead. In this paper, we design a parallel collaborative distributed alternating direction method of multipliers (ADMM) and propose a three-phase parallel collaborative ADMM privacy computing (3P-ADMM-PC2) algorithm for distributed computing in edge networks, where the Paillier homomorphic encryption is utilized to protect data privacy during interactions. Especially, a quantization method is introduced, which maps the real numbers to a positive integer interval without affecting the homomorphic operations. To address the architectural mismatch between large-integer and Graphics Processing Unit (GPU) computing, we transform high-bitwidth computations into low-bitwidth matrix and vector operations. Thus the GPU can be utilized to implement parallel encryption and decryption computations with long keys. Finally, a GPU-accelerated 3P-ADMM-PC2 is proposed to optimize the collaborative computing tasks. Meanwhile, large-scale computational tasks are conducted in network topologies with varying numbers of edge nodes. Experimental results demonstrate that the proposed 3P-ADMM-PC2 has excellent mean square error performance, which is close to that of distributed ADMM without privacy-preserving. Compared to centralized ADMM and distributed ADMM implemented with Central Processing Unit (CPU) computation, the proposed scheme demonstrates a significant speedup ratio.

cs.DC↗

arXiv2026

Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models

Time functions as a fundamental dimension of human cognition, yet the mechanisms by which Large Language Models (LLMs) encode chronological progression remain opaque. We demonstrate that temporal information in their latent space is organized not as discrete clusters but as a continuous, traversable geometry. We introduce the Time Travel Engine (TTE), an interpretability-driven framework that projects diachronic linguistic patterns onto a shared chronological manifold. Unlike surface-level prompting, TTE directly modulates latent representations to induce coherent stylistic, lexical, and conceptual shifts aligned with target eras. By parameterizing diachronic evolution as a continuous manifold within the residual stream, TTE enables fluid navigation through period-specific "zeitgeists" while restricting access to future knowledge. Furthermore, experiments across diverse architectures reveal topological isomorphism between the temporal subspaces of Chinese and English-indicating that distinct languages share a universal geometric logic of historical evolution. These findings bridge historical linguistics with mechanistic interpretability, offering a novel paradigm for controlling temporal reasoning in neural networks.

cs.CL↗

arXiv2026

Pinching Antennas in Blockage-Aware Environments: Modeling, Design, and Optimization

Pinching-antenna (PA) systems have recently emerged as a promising member of the flexible-antenna family due to their ability to dynamically establish line-of-sight (LoS) links. While most existing studies assume ideal environments without obstacles, practical indoor deployments are often obstacle-rich, where LoS blockage significantly degrades performance. This paper investigates pinching-antenna systems in blockage-aware environments by developing a deterministic model for cylinder-shaped obstacles that precisely characterizes LoS conditions without relying on stochastic approximations. Based on this model, a special case is first studied where each PA serves a single user and can only be deployed at discrete positions along the waveguide. In this case, the waveguide-user assignment is obtained via the Hungarian algorithm, and PA positions are refined using a surrogate-assisted block-coordinate search. Then, a general case is considered where each PA serves all users and can be continuously placed along the waveguide. In this case, beamforming and PA positions are jointly optimized by a weighted minimum mean square error integrated deep deterministic policy gradient (WMMSE-DDPG) approach to address non-smooth LoS transitions. Simulation results demonstrate that the proposed algorithms significantly improve system throughput and LoS connectivity compared with benchmark methods. Moreover, the results reveal that pinching-antenna systems can effectively leverage obstacles to suppress co-channel interference, converting potential blockages into performance gains.

eess.SP↗

arXiv2025

Robust and Secure Transmission for Movable-RIS Assisted ISAC with Imperfect Sense Estimation

Reconfigurable intelligent surfaces (RISs) have been extensively applied in integrated sensing and communication (ISAC) systems due to the capability of enhancing physical layer security (PLS). However, conventional static RIS architectures lack the flexibility required for adaptive beam control in multi-user and multifunctional scenarios. To address this issue without introducing additional hardware complexity and power consumption, in this paper, we exploit a movable RIS (MRIS) architecture, which consists of a large fixed sub-surface and a smaller movable sub-surface that slides on the fixed sub-surface to achieve dynamic beam reconfiguration with static phase shifts. This paper investigates an MRIS-assisted ISAC system under imperfect sensing estimation, where dedicated radar signals serve as artificial noise to enhance secure transmission against potential eavesdroppers (Eves). The transmit beamforming vectors, MRIS phase shifts, and relative positions of the two sub-surfaces are jointly optimized to maximize the minimum secrecy rate, ensuring robust secrecy performance for the weakest user under the uncertainty of the Eves' channels. To handle the non-convexity, a convex bound is derived for the Eve channel uncertainty, and the S-procedure is employed to reformulate semi-infinite constraints as linear matrix inequalities. An efficient alternating optimization and penalty dual decomposition-based algorithm is developed. Simulation results demonstrate that the proposed MRIS architecture substantially improves secrecy performance, especially when only a small number of elements are allocated to the movable sub-surface.

eess.SP↗

arXiv2025

From Essence to Defense: Adaptive Semantic-aware Watermarking for Embedding-as-a-Service Copyright Protection

Benefiting from the superior capabilities of large language models in natural language understanding and generation, Embeddings-as-a-Service (EaaS) has emerged as a successful commercial paradigm on the web platform. However, prior studies have revealed that EaaS is vulnerable to imitation attacks. Existing methods protect the intellectual property of EaaS through watermarking techniques, but they all ignore the most important properties of embedding: semantics, resulting in limited harmlessness and stealthiness. To this end, we propose SemMark, a novel semantic-based watermarking paradigm for EaaS copyright protection. SemMark employs locality-sensitive hashing to partition the semantic space and inject semantic-aware watermarks into specific regions, ensuring that the watermark signals remain imperceptible and diverse. In addition, we introduce the adaptive watermark weight mechanism based on the local outlier factor to preserve the original embedding distribution. Furthermore, we propose Detect-Sampling and Dimensionality-Reduction attacks and construct four scenarios to evaluate the watermarking method. Extensive experiments are conducted on four popular NLP datasets, and SemMark achieves superior verifiability, diversity, stealthiness, and harmlessness.

cs.CR↗

arXiv2025

Prefrontal scaling of reward prediction error readout gates reinforcement-derived adaptive behavior in primates

Reinforcement learning (RL) enables adaptive behavior across species via reward prediction errors (RPEs), but the neural origins of species-specific adaptability remain unknown. Integrating RL modeling, transcriptomics, and neuroimaging during reversal learning, we discovered convergent RPE signatures - shared monoaminergic/synaptic gene upregulation and neuroanatomical representations, yet humans outperformed macaques behaviorally. Single-trial decoding showed RPEs guided choices similarly in both species, but humans disproportionately recruited dorsal anterior cingulate (dACC) and dorsolateral prefrontal cortex (dlPFC). Cross-species alignment uncovered that macaque prefrontal circuits encode human-like optimal RPEs yet fail to translate them into action. Adaptability scaled not with RPE encoding fidelity, but with the areal extent of dACC/dlPFC recruitment governing RPE-to-action transformation. These findings resolve an evolutionary puzzle: behavioral performance gaps arise from executive cortical readout efficiency, not encoding capacity.

q-bio.NC↗

arXiv2025

A Note on the Conditions for COS Convergence

We study the truncation error of the COS method and give simple, verifiable conditions that guarantee convergence. In one dimension, COS is admissible when the density belongs to both L1 and L2 and has a finite weighted L2 moment of order strictly greater than one. We extend the result to multiple dimensions by requiring the moment order to exceed the dimension. These conditions enlarge the class of densities covered by previous analyses and include heavy-tailed distributions such as Student t with small degrees of freedom.

q-fin.CP↗

arXiv2025

Probing critical phenomena in open quantum systems using atom arrays

At continuous phase transitions, quantum many-body systems exhibit scale-invariance and complex, emergent universal behavior. Most strikingly, at a quantum critical point, correlations decay as a power law, with exponents determined by a set of universal scaling dimensions. Experimentally probing such power-law correlations is extremely challenging, owing to the complex interplay between decoherence, the vanishing energy gap, and boundary effects. Here, we employ a Rydberg quantum simulator to adiabatically prepare critical ground states of both a one-dimensional ring and a two-dimensional square lattice. By accounting for and tuning the openness of our quantum system, which is well-captured by the introduction of a single phenomenological length scale, we are able to directly observe power-law correlations and extract the corresponding scaling dimensions. Moreover, in two dimensions, we observe a decoupling between phase transitions in the bulk and on the boundary, allowing us to identify two distinct boundary universality classes. Our work demonstrates that direct adiabatic preparation of critical states in quantum simulators can complement recent approaches to studying quantum criticality using the Kibble-Zurek mechanism or digital quantum circuits.

quant-ph↗

arXiv2025

MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization

Large Language Models demonstrate strong reasoning capabilities, which can be effectively compressed into smaller models. However, existing datasets and fine-tuning approaches still face challenges that lead to catastrophic forgetting, particularly for models smaller than 8B. First, most datasets typically ignore the relationship between training data knowledge and the model's inherent abilities, making it difficult to preserve prior knowledge. Second, conventional training objectives often fail to constrain inherent knowledge preservation, which can result in forgetting of previously learned skills. To address these issues, we propose a comprehensive solution that alleviates catastrophic forgetting from both the data and fine-tuning approach perspectives. On the data side, we construct a dataset of 5K instances that covers multiple reasoning tasks and incorporates metacognitive knowledge, making it more tolerant and effective for distillation into smaller models. We annotate the metacognitive knowledge required to solve each question and filter the data based on task knowledge and the model's inherent skills. On the training side, we introduce GDPO (Group Direction Preference Optimization), which is better suited for resource-limited scenarios and can efficiently approximate the performance of GRPO. Guided by the large model and by implicitly constraining the optimization path through a reference model, GDPO enables more effective knowledge transfer from the large model and constrains excessive parameter drift. Extensive experiments demonstrate that our approach significantly alleviates catastrophic forgetting and improves reasoning performance on smaller models.

cs.AI↗

arXiv2025

Average AoI in Pinching Antenna-assisted WPCNs with Probabilistic LoS Blockage

This paper analyzes the age of information (AoI) for a pinching antenna (PA)-assisted wireless powered communication network (WPCN) with probabilistic line-of-sight (LoS) blockage. AoI is a key metric for evaluating the freshness of status updates in IoT networks, and its optimization is crucial for ensuring the performance of time-critical applications. To facilitate analysis and gain useful insights, we consider a representative scenario, where an IoT device harvests energy from a base station (BS) equipped with a PA and transmits data packets to it. The IoT device harvests energy via the PA until its capacitor is fully charged, then transmits status updates using all stored energy. We derive closed-form expressions for the average AoI by analyzing the capacitor charging time, transmission success probability, and inter-arrival time of successful updates. To minimize the average AoI, we formulate an optimization problem of PA position, and propose a one-dimensional search to solve it. The simulation results show that the optimal PA position is the one closest to the IoT device, and this conclusion can be extended to the multi-IoT devices frequency division multiple access (FDMA) scenario. The PA-based systems significantly outperform the conventional fixed-antenna systems.

cs.IT↗