arXiv subjects

Fang Fang

Publications and source records attributed to Fang Fang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Pinching Antennas Meet AI in Next-Generation Wireless Networks

Next-generation (NG) wireless networks must embrace innate intelligence in support of demanding emerging applications, such as extended reality and autonomous systems, under ultra-reliable and low-latency requirements. Pinching antennas (PAs), a new flexible low-cost technology, can create line-of-sight links by dynamically activating small dielectric pinches along a waveguide on demand. As a compelling complement, artificial intelligence (AI) offers the intelligence needed to manage the complex control of PA activation positions and resource allocation in these dynamic environments. This article explores the "win-win" cooperation between AI and PAs: AI facilitates the adaptive optimization of PA activation positions along the waveguide, while PAs support edge AI tasks such as federated learning and over-the-air aggregation. We also discuss promising research directions including large language model-driven PA control frameworks, and how PA-AI integration can advance semantic communications, and integrated sensing and communication. This synergy paves the way for adaptive, resilient, and self-optimizing NG networks.

cs.NI↗

arXiv2025

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs

The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, law, and education. Existing evaluation methods for short texts often fail on long-form content due to complex reasoning chains, intertwined perspectives, and cumulative information. To address this, we propose a systematic approach integrating large-scale long-form datasets, multi-agent verification mechanisms, and weighted evaluation metrics. We construct LongHalluQA, a Chinese long-form factuality dataset; and develop MAD-Fact, a debate-based multi-agent verification system. We introduce a fact importance hierarchy to capture the varying significance of claims in long-form texts. Experiments on two benchmarks show that larger LLMs generally maintain higher factual consistency, while domestic models excel on Chinese content. Our work provides a structured framework for evaluating and enhancing factual reliability in long-form LLM outputs, guiding their safe deployment in sensitive domains.

cs.CL↗

arXiv2025

Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

Large Language Models (LLMs) demonstrate human-level or even superior language abilities, effectively modeling syntactic structures, yet the specific computational modules responsible remain unclear. A key question is whether LLM behavioral capabilities stem from mechanisms akin to those in the human brain. To address these questions, we introduce the Hierarchical Frequency Tagging Probe (HFTP), a tool that utilizes frequency-domain analysis to identify neuron-wise components of LLMs (e.g., individual Multilayer Perceptron (MLP) neurons) and cortical regions (via intracranial recordings) encoding syntactic structures. Our results show that models such as GPT-2, Gemma, Gemma 2, Llama 2, Llama 3.1, and GLM-4 process syntax in analogous layers, while the human brain relies on distinct cortical regions for different syntactic levels. Representational similarity analysis reveals a stronger alignment between LLM representations and the left hemisphere of the brain (dominant in language processing). Notably, upgraded models exhibit divergent trends: Gemma 2 shows greater brain similarity than Gemma, while Llama 3.1 shows less alignment with the brain compared to Llama 2. These findings offer new insights into the interpretability of LLM behavioral improvements, raising questions about whether these advancements are driven by human-like or non-human-like mechanisms, and establish HFTP as a valuable tool bridging computational linguistics and cognitive neuroscience. This project is available at https://github.com/LilTiger/HFTP.

cs.CL↗

arXiv2025

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring classification boundaries and making accurate detection increasingly challenging. To address the above challenges, we propose a DNA-inspired perspective, leveraging a repair-based process to directly and interpretably capture the intrinsic differences between human-written and AI-generated text. Building on this perspective, we introduce DNA-DetectLLM, a zero-shot detection method for distinguishing AI-generated and human-written text. The method constructs an ideal AI-generated sequence for each input, iteratively repairs non-optimal tokens, and quantifies the cumulative repair effort as an interpretable detection signal. Empirical evaluations demonstrate that our method achieves state-of-the-art detection performance and exhibits strong robustness against various adversarial attacks and input lengths. Specifically, DNA-DetectLLM achieves relative improvements of 5.55% in AUROC and 2.08% in F1 score across multiple public benchmark datasets. Code and data are available at https://github.com/Xiaoweizhu57/DNA-DetectLLM.

cs.CL↗

arXiv2025

Enhancing ML Models Interpretability for Credit Scoring

Predicting default is essential for banks to ensure profitability and financial stability. While modern machine learning methods often outperform traditional regression techniques, their lack of transparency limits their use in regulated environments. Explainable artificial intelligence (XAI) has emerged as a solution in domains like credit scoring. However, most XAI research focuses on post-hoc interpretation of black-box models, which does not produce models lightweight or transparent enough to meet regulatory requirements, such as those for Internal Ratings-Based (IRB) models. This paper proposes a hybrid approach: post-hoc interpretations of black-box models guide feature selection, followed by training glass-box models that maintain both predictive power and transparency. Using the Lending Club dataset, we demonstrate that this approach achieves performance comparable to a benchmark black-box model while using only 10 features - an 88.5% reduction. In our example, SHapley Additive exPlanations (SHAP) is used for feature selection, eXtreme Gradient Boosting (XGBoost) serves as the benchmark and the base black-box model, and Explainable Boosting Machine (EBM) and Penalized Logistic Tree Regression (PLTR) are the investigated glass-box models. We also show that model refinement using feature interaction analysis, correlation checks, and expert input can further enhance model interpretability and robustness.

cs.LG↗

arXiv2025

Spatial weights matrix selection and model averaging for multivariate spatial autoregressive models

In this paper, we focus on the model specification problem in multivariate spatial econometric models when a candidate set for the spatial weights matrix is available. We propose a model selection method for the multivariate spatial autoregressive model, when the true spatial weights matrix may not be in the candidates. We show that the selected estimator is asymptotically optimal in the sense of minimizing the squared loss. If the candidate set contains the true spatial weights matrix, the method has selection consistency. We further propose a model averaging estimator that combines a set of candidate models and show its asymptotic optimality. Monte Carlo simulation results indicate that the proposed model selection and model averaging estimators perform quite well in finite samples. The proposed methods are applied to a Sina Weibo data to reveal how the user's posting behavior is influenced by the users that he follows. The analysis results indicate that the influence tends to be uniformly distributed among the user's followee, or linearly correlated with the number of followers of the followee.

stat.ME↗

arXiv2025

Emergent disorder and sub-ballistic dynamics in quantum simulations of the Ising model using Rydberg atom arrays

Rydberg atom arrays with Van der Waals interactions provide a controllable path to simulate the locally connected transverse-field Ising model (TFIM), a prototypical model in statistical mechanics. Remotely operating the publicly accessible Aquila Rydberg atom array, we experimentally investigate the physics of TFIM far from equilibrium and uncover significant deviations from the theoretical predictions. Rather than the expected ballistic spread of correlations, the Rydberg simulator exhibits a subballistic spread, along with a logarithmic scaling of entanglement entropy in time - all while the system mostly retains its initial magnetization. By modeling the atom motion, we trace these effects to an emergent disorder in Rydberg atom arrays, which we characterize with a minimal random spin model. We further experimentally explore the different dynamical regimes hosted in the system by varying the lattice spacing and the Rabi frequency. Our findings highlight the crucial role of atom motion in the many-body dynamics of Rydberg atom arrays at the TFIM limit, and propose simple benchmark measurements to test for its presence in future experiments.

quant-ph↗

arXiv2025

Straggler-Resilient Federated Learning over A Hybrid Conventional and Pinching Antenna Network

Leveraging pinching antennas in wireless network enabled federated learning (FL) can effectively mitigate the common "straggler" issue in FL by dynamically establishing strong line-of-sight (LoS) links on demand. This letter proposes a hybrid conventional and pinching antenna network (HCPAN) to significantly improve communication efficiency in the non-orthogonal multiple access (NOMA)-enabled FL system. Within this framework, a fuzzy logic-based client classification scheme is first proposed to effectively balance clients' data contributions and communication conditions. Given this classification, we formulate a total time minimization problem to jointly optimize pinching antenna placement and resource allocation. Due to the complexity of variable coupling and non-convexity, a deep reinforcement learning (DRL)-based algorithm is developed to effectively address this problem. Simulation results validate the superiority of the proposed scheme in enhancing FL performance via the optimized deployment of pinching antenna.

cs.IT↗

arXiv2025

Power-Efficient Optimization for Coexisting Semantic and Bit-Based Users in NOMA Networks

Semantic communications, which focus on transmitting the semantic meaning of data, have been proposed as a novel paradigm for achieving efficient and relevant communication. Meanwhile, non-orthogonal multiple access (NOMA) enhances spectral efficiency by allowing multiple users to share the same spectrum. However, semantic communications are unlikely to fully replace conventional bit-level communications in the near future, as the latter remain dominant. Therefore, integrating semantic users into a NOMA network alongside conventional bit-based users becomes a meaningful approach to improve both transmission and spectrum efficiency. Nonetheless, due to the lack of a mathematical model that accurately characterizes the relationship between the performance of semantic transceivers and wireless resource allocation, enhancing performance through resource optimization remains a challenge. Moreover, successive interference cancellation (SIC), a key technique in NOMA, introduces additional complexity in system design and implementation. To address these challenges, this paper first improves the deep semantic communication (DeepSC) transceiver to make it adaptive to varying wireless transmission conditions. Subsequently, a data-driven regression approach is employed to develop a mathematical model that captures the impact of wireless resources on semantic transceiver performance. In parallel, a multi-cluster hybrid NOMA (H-NOMA) framework is proposed, where each cluster consists of one semantic user and one bit-based user, to mitigate the complexity introduced by SIC. A total transmit power minimization problem is then formulated by jointly optimizing the beamforming design, bandwidth allocation, and semantic symbol factor.

eess.SP↗

arXiv2025

High-Dimensional Model Averaging via Cross-Validation

Model averaging is an important alternative to model selection with attractive prediction accuracy. However, its application to high-dimensional data remains under-explored. We propose a high-dimensional model averaging method via cross-validation under a general framework and systematically establish its theoretical properties. Each candidate model is fitted using a flexible loss function paired with a general regularizer, and the optimal weights are determined by minimizing a cross-validation criterion. When all candidate models are misspecified, we establish a non-asymptotic upper bound and a minimax lower bound for our weight estimator. The asymptotic optimality is also derived, showing that the proposed weight estimator achieves the lowest possible prediction risk asymptotically. When the correct models are included in the candidate model set, the proposed method asymptotically assigns all weights to the correct models, and the model averaging estimator achieves a nearly-oracle convergence rate. Further, we introduce a post-averaging debiased estimator and establish Gaussian and bootstrap approximation to construct simultaneous confidence intervals. A fast greedy model averaging (FGMA) algorithm is proposed to solve the simplex-constrained optimization problem, which has a descent property empirically and a faster convergence rate, compared to the original greedy model averaging algorithm. Empirical results demonstrate the strong competitiveness of the proposed method in prediction and inference, compared to other existing model averaging and selection methods.

math.ST↗

arXiv2025

Energy-Efficient Design for Downlink Pinching-Antenna Systems with QoS Guarantee

Pinching antennas have recently garnered significant attention due to their ability to dynamically reconfigure wireless propagation environments. Despite notable advancements in this area, the exploration of energy efficiency (EE) maximization in pinching-antenna systems remains relatively underdeveloped. In this paper, we address the EE maximization problem in a downlink time-division multiple access (TDMA)-based multi-user system employing one waveguide and multiple pinching antennas, where each user is subject to a minimum rate constraint to ensure quality-of-service. The formulated optimization problem jointly considers transmit power and time allocations as well as the positioning of pinching antennas, resulting in a non-convex problem. To tackle this challenge, we first obtain the optimal positions of the pinching antennas. Based on this, we establish a feasibility condition for the system. Subsequently, the joint power and time allocation problem is decomposed into two subproblems, which are solved iteratively until convergence. Specifically, the power allocation subproblem is addressed through an iterative approach, where a semi-analytical solution is obtained in each iteration. Likewise, a semi-analytical solution is derived for the time allocation subproblem. Numerical simulations demonstrate that the proposed pinching-antenna-based strategy significantly outperforms both conventional fixed-antenna systems and other benchmark pinching-antenna schemes in terms of EE.

cs.IT↗

arXiv2025

Flow interactions and forward flight dynamics of tandem flapping wings

We examine theoretically the flow interactions and forward flight dynamics of tandem or in-line flapping wings. Two wings are driven vertically with prescribed heaving-and-plunging motions, and the horizontal propulsion speeds and positions are dynamically selected through aero- or hydro-dynamic interactions. Our simulations employ an improved vortex sheet method to solve for the locomotion of the pair within the collective flow field, and we identify 'schooling states' in which the wings travel together with nearly constant separation. Multiple terminal configurations are achieved by varying the initial conditions, and the emergent separations are approximately integer multiples of the wavelength traced out by each wing. We explain the stability of these states by perturbing the follower and mapping out an effective potential for its position in the leader's wake. Each equilibrium position is stabilized since smaller separations are associated with in-phase follower-wake motions that constructively reinforce the flow but lead to decreased thrust on the follower; larger separations are associated with antagonistic follower-wake motions, increased thrust, and a weakened collective wake. The equilibria and their stability are also corroborated by a linearized theory for the motion of the leader, the wake it produces, and its effect on the follower. We also consider a weakly-flapping follower driven with lower heaving amplitude than the leader. We identify 'keep-up' conditions for which the wings may still 'school' together despite their dissimilar kinematics, with the 'freeloading' follower passively assuming a favorable position within the wake that permits it to travel significantly faster than it would in isolation.

physics.flu-dyn↗

arXiv2025

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment models can easily block. Meanwhile, Jailbreak attacks bypass LLM safety mechanisms to generate harmful content, but their role in privacy scenarios remains underexplored. In this paper, we examine the effectiveness of jailbreak attacks in extracting sensitive information, bridging privacy leakage and jailbreak attacks in LLMs. Moreover, we propose PIG, a novel framework targeting Personally Identifiable Information (PII) and addressing the limitations of current jailbreak methods. Specifically, PIG identifies PII entities and their types in privacy queries, uses in-context learning to build a privacy context, and iteratively updates it with three gradient-based strategies to elicit target PII. We evaluate PIG and existing jailbreak methods using two privacy-related datasets. Experiments on four white-box and two black-box LLMs show that PIG outperforms baseline methods and achieves state-of-the-art (SoTA) results. The results underscore significant privacy risks in LLMs, emphasizing the need for stronger safeguards. Our code is availble at https://github.com/redwyd/PrivacyJailbreak.

cs.CR↗

arXiv2025

Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction

The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors. As a result, developing effective detectors to mitigate these risks has become a critical priority. However, most existing detection methods focus excessively on detection accuracy, often neglecting the societal risks posed by high false positive rates (FPRs). This paper addresses this issue by leveraging Conformal Prediction (CP), which effectively constrains the upper bound of FPRs. While directly applying CP constrains FPRs, it also leads to a significant reduction in detection performance. To overcome this trade-off, this paper proposes a Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction (MCP), which both enforces the FPR constraint and improves detection performance. This paper also introduces RealDet, a high-quality dataset that spans a wide range of domains, ensuring realistic calibration and enabling superior detection performance when combined with MCP. Empirical evaluations demonstrate that MCP effectively constrains FPRs, significantly enhances detection performance, and increases robustness against adversarial attacks across multiple detectors and datasets.

cs.CL↗

arXiv2025

An Egocentric Vision-Language Model based Portable Real-time Smart Assistant

We present Vinci, a vision-language system designed to provide real-time, comprehensive AI assistance on portable devices. At its core, Vinci leverages EgoVideo-VL, a novel model that integrates an egocentric vision foundation model with a large language model (LLM), enabling advanced functionalities such as scene understanding, temporal grounding, video summarization, and future planning. To enhance its utility, Vinci incorporates a memory module for processing long video streams in real time while retaining contextual history, a generation module for producing visual action demonstrations, and a retrieval module that bridges egocentric and third-person perspectives to provide relevant how-to videos for skill acquisition. Unlike existing systems that often depend on specialized hardware, Vinci is hardware-agnostic, supporting deployment across a wide range of devices, including smartphones and wearable cameras. In our experiments, we first demonstrate the superior performance of EgoVideo-VL on multiple public benchmarks, showcasing its vision-language reasoning and contextual understanding capabilities. We then conduct a series of user studies to evaluate the real-world effectiveness of Vinci, highlighting its adaptability and usability in diverse scenarios. We hope Vinci can establish a new framework for portable, real-time egocentric AI systems, empowering users with contextual and actionable insights. Including the frontend, backend, and models, all codes of Vinci are available at https://github.com/OpenGVLab/vinci.

cs.CV↗

arXiv2025

A Low-Complexity Placement Design of Pinching-Antenna Systems

Pinching-antenna systems have recently been proposed as a new candidate for flexible-antenna systems, not only inheriting the reconfiguration capability but also offering a unique feature: establishing line-of-sight links to mitigate large-scale path loss. However, sophisticated optimization of the placement of pinching antennas has very high complexity, which is challenging for practical implementation. This paper proposes a low-complexity placement design, providing the closed-form expression of the placement of pinching antennas, to maximize the sum rate of multiple downlink users. Orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) are both investigated when the pinching-antenna system is only equipped with a single antenna and only the OMA case is studied when there are multiple antennas equipped by the pinching-antenna system. Simulation results indicate pinching-antenna systems can outperform conventional fixed-antenna systems and are more suitable for large service areas.

eess.SP↗

arXiv2025

Optimizing Value of Learning in Task-Oriented Federated Meta-Learning Systems

Federated Learning (FL) has gained significant attention in recent years due to its distributed nature and privacy preserving benefits. However, a key limitation of conventional FL is that it learns and distributes a common global model to all participants, which fails to provide customized solutions for diverse task requirements. Federated meta-learning (FML) offers a promising solution to this issue by enabling devices to finetune local models after receiving a shared meta-model from the server. In this paper, we propose a task-oriented FML framework over non-orthogonal multiple access (NOMA) networks. A novel metric, termed value of learning (VoL), is introduced to assess the individual training needs across devices. Moreover, a task-level weight (TLW) metric is defined based on task requirements and fairness considerations, guiding the prioritization of edge devices during FML training. The formulated problem, to maximize the sum of TLW-based VoL across devices, forms a non-convex mixed-integer non-linear programming (MINLP) challenge, addressed here using a parameterized deep Q-network (PDQN) algorithm to handle both discrete and continuous variables. Simulation results demonstrate that our approach significantly outperforms baseline schemes, underscoring the advantages of the proposed framework.

cs.LG↗

arXiv2025

Dynamic Authentication and Granularized Authorization with a Cross-Domain Zero Trust Architecture for Federated Learning in Large-Scale IoT Networks

With the increasing number of connected devices and complex networks involved, current domain-specific security techniques become inadequate for diverse large-scale Internet of Things (IoT) systems applications. While cross-domain authentication and authorization brings lots of security improvement, it creates new challenges of efficiency and security. Zero trust architecture (ZTA), an emerging network security architecture, offers a more granular and robust security environment for IoT systems. However, extensive cross-domain data exchange in ZTA can cause reduced authentication and authorization efficiency and data privacy concerns. Therefore, in this paper, we propose a dynamic authentication and granularized authorization scheme based on ZTA integrated with decentralized federated learning (DFL) for cross-domain IoT networks. Specifically, device requests in the cross-domain process are continuously monitored and evaluated, and only necessary access permissions are granted. To protect user data privacy and reduce latency, we integrate DFL with ZTA to securely and efficiently share device data across different domains. Particularly, the DFL model is compressed to reduce the network transmission load. Meanwhile, a dynamic adaptive weight adjustment mechanism is proposed to enable the DFL model to adapt to data characteristics from different domains. We analyze the performance of the proposed scheme in terms of security proof, including confidentiality, integrity and availability. Simulation results demonstrate the superior performance of the proposed scheme in terms of lower latency and higher throughput compared to other existing representative schemes.

cs.NI↗