arXiv subjects

Hui Wang

Publications and source records attributed to Hui Wang.

At least 127 records · Page 7Linked to original sources

arXiv2026

Causal-INSIGHT: Probing Temporal Models to Extract Causal Structure

Understanding directed temporal interactions in multivariate time series is essential for interpreting complex dynamical systems and the predictive models trained on them. We present Causal-INSIGHT, a model-agnostic, post-hoc interpretation framework for extracting model-implied (predictor-dependent), directed, time-lagged influence structure from trained temporal predictors. Rather than inferring causal structure at the level of the data-generating process, Causal-INSIGHT analyzes how a fixed, pre-trained predictor responds to systematic, intervention-inspired input clamping applied at inference time. From these responses, we construct directed temporal influence signals that reflect the dependencies the predictor relies on for prediction, and introduce Qbic, a sparsity-aware graph selection criterion that balances predictive fidelity and structural complexity without requiring ground-truth graph labels. Experiments across synthetic, simulated, and realistic benchmarks show that Causal-INSIGHT generalizes across diverse backbone architectures, maintains competitive structural accuracy, and yields significant improvements in temporal delay localization when applied to existing predictors.

cs.LG↗

arXiv2026

Realizing giant valley polarization effect based on monolayer altermagnets

Stable and remarkable valley polarization effect is the key to utilizing valley degree of freedom in valleytronic devices. According to first-principles calculations and symmetry analysis, we reveal that valley polarization effect in monolayer V2Se2O altermagnet is correlated with the net magnetic moment between magnetic V atoms under uniaxial strain, thereby proposing two strategies for achieving giant valley polarization effect. Firstly, substituting one V atom in V2Se2O with Cr to construct a ferrimagnetic monolayer VCrSe2O enhances the net magnetic moment between magnetic atoms, thereby realizing a giant valley polarization effect. Applying uniaxial strain along either the a-axis or b-axis significantly increases the value of valley polarization, which exhibits a nearly linear relationship with the net magnetic moments between the magnetic atoms. Secondly, constructing a van der Waals heterostructure composed of V2Se2O and α-SnO monolayers breaks mirror symmetry, thereby inducing a net magnetic moment, which in turn causes a remarkable valley polarization effect. Compressing the interlayer distance of the heterostructure can increase the net magnetic moment between V atoms, then enhancing the value of valley polarization to nearly 400 meV. This work reveals that valley polarization in monolayer altermagnet is correlated with the net magnetic moment between magnetic atoms. Finally, we propose two strategies to achieve giant valley polarization based on monolayer altermagnets, providing theoretical guidance for the potential applications of ferrimagnetic monolayers and altermagnet-based heterostructures in valleytronics.

cond-mat.mtrl-sci↗

arXiv2026

RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems

Recommender systems are inherently dynamic feedback loops where prolonged local interactions accumulate into macroscopic structural degradation such as information cocoons. Existing representation learning paradigms are universally constrained by the assumption of a single flat space, forcing topologically grounded user associations and semantically driven historical interactions to be fitted within the same vector space. This excessive coupling of heterogeneous information renders it impossible for researchers to mechanistically distinguish and identify the sources of systemic bias. To overcome this theoretical bottleneck, we introduce Fiber Bundle from modern differential geometry and propose a novel geometric analysis paradigm for recommender systems. This theory naturally decouples the system space into two hierarchical layers: the base manifold formed by user interaction networks, and the fibers attached to individual user nodes that carry their dynamic preferences. Building upon this, we construct RecBundle, a framework oriented toward next-generation recommender systems that formalizes user collaboration as geometric connection and parallel transport on the base manifold, while mapping content evolution to holonomy transformations on fibers. From this foundation, we identify future application directions encompassing quantitative mechanisms for information cocoons and evolutionary bias, geometric meta-theory for adaptive recommendation, and novel inference architectures integrating large language models (LLMs). Empirical analysis on real-world MovieLens and Amazon Beauty datasets validates the effectiveness of this geometric framework.

cs.IR↗

arXiv2026

Hybrid Tribo/piezoelectic Electrospun Nanofibers for Energy Harvesting Enhancement in Flexible Electronics

Triboelectric nanogenerators or TENGs and piezoelectric nanogenerators or PENGs have emerged as promising platforms for harvesting mechanical energy and converting it into electrical energy for powering flexible electronic devices. However, the material selection and structure design of such hybrid nanogenerator, and mechanisms of energy output still remain challenges. In this work, electrospinning is employed for the fabrication of nanofibers, particularly polyvinylidene fluoride or PVDF based nanofibers, due to its capability to generate high beta phase contents that effectively increase the piezoelectric performance of the PVDF friction layer, thereby enhancing the overall electrical performance for flexible electronics by merging tribo-piezoelectric power. Furthermore, various concentrations carbon nanotubes or CNT or graphene nanosheets or GNS are individually incorporated into the PVDF solution as nanofillers or NF to enhance the piezoelectric responses of the PVDF based nanofibers. The introduction of nanofillers is found to not only alter the fiber diameter but also modify the surface roughness of the electrospun nanofibers, and thus, enhancing the triboelectric effect. In addition, the output performance of the fabricated nanogenerator is predominantly governed by the piezoelectric effect rather than triboelectric effect, as the electrical output shows a strong positive correlation with the beta phase content of PVDF based nanofibers: the highest beta phase content reached to 85.3 percent and consistently resulted in the optimal energy output of 1.133 watt per meter square. Notably, the power density achieved by the prototype device reaches to the level of watt/m2, representing a substantial improvement compared with that of the conventional TENGs or PENGs reported to date, providing expanded opportunities for flexible electronic devices

cond-mat.mtrl-sci↗

arXiv2026

Code Fingerprints: Disentangled Attribution of LLM-Generated Code

The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While these systems improve productivity, they introduce new challenges for software governance, accountability, and compliance. Existing research primarily focuses on distinguishing machine-generated code from human-written code; however, many practical scenarios--such as vulnerability triage, incident investigation, and licensing audits--require identifying which LLM produced a given code snippet. In this paper, we study the problem of model-level code attribution, which aims to determine the source LLM responsible for generated code. Although attribution is challenging, differences in training data, architectures, alignment strategies, and decoding mechanisms introduce model-dependent stylistic and structural variations that serve as generative fingerprints. Leveraging this observation, we propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations. Through a contrastive learning objective, DCAN isolates discriminative model-dependent signals while preserving task semantics, enabling multi-class attribution across models and programming languages. To support systematic evaluation, we construct the first large-scale benchmark dataset comprising code generated by four widely used LLMs (DeepSeek, Claude, Qwen, and ChatGPT) across four programming languages (Python, Java, C, and Go). Experimental results demonstrate that DCAN achieves reliable attribution performance across diverse settings, highlighting the feasibility of model-level provenance analysis in software engineering contexts. The dataset and implementation are publicly available at https://github.com/mtt500/DCAN.

cs.SE↗

arXiv2026

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data caused by stringent privacy requirements. Secure Multi-party Computation (MPC)-based privacy-preserving machine learning provides theoretical guarantees for the privacy of model parameters and data. However, its application to LLMs has been predominantly limited to inference, as fine-tuning introduces significant efficiency challenges, particularly in backward propagation, optimizer, and self-attention operations. To address these challenges, we propose SecP-Tuning, the first MPC-based framework designed for efficient, privacy-preserving prompt tuning of LLMs. SecP-Tuning innovatively integrates Forward-only Tuning (FoT) through the ``data owner-server interaction" paradigm, effectively removing the need for privacy-preserving computations in backward propagation and optimization processes. Furthermore, it devises an efficient privacy-preserving Random Feature Attention (RFA), effectively mitigating the computational complexity of softmax-based self-attention and circumventing MPC-incompatible nonlinear operations. Experimental results demonstrate that, compared to full-Parameter Supervised Fine-Tuning (SFT) and gradient-based prompt tuning, SecP-Tuning achieves approximately 12x and 16x end-to-end acceleration, as well as 17x and 20x reductions in communication overhead, respectively. Moreover, it delivers performance comparable to gradient-based methods across multiple few-shot tasks.

cs.LG↗

arXiv2026

Control the qubit-qubit coupling with double superconducting resonators

We experimentally studied the switching off processes in the double-resonator coupler superconducting quantum circuit. In both frequency and time-domain, we observed the variation of qubit-qubit effective coupling by tuning the frequency differences between qubits and the double-resonator coupler. According to the measurement results, by just shifting about 50 MHz of qubits' frequencies, we can tune the effective qubit-qubit coupling strength from switching off point to two qubit gate point (effective coupling larger than 5 MHz) in double-resonator superconducting quantum circuit.The double-resonator (coupler) superconducting quantum circuit has the advantage of simple fabrications, introducing less flux noises, reducing occupancy of dilution refrigerator cables,which might supply a promising platform for future large-scale superconducting quantum processors.

quant-ph↗

arXiv2026

A Cognitive Distribution and Behavior-Consistent Framework for Black-Box Attacks on Recommender Systems

With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing black-box extraction attacks primarily rely on hard labels or pairwise learning, often ignoring the importance of ranking positions, which results in incomplete knowledge transfer. Moreover, adversarial sequences generated via pure gradient methods lack semantic consistency with real user behavior, making them easily detectable. To overcome these limitations, this paper proposes a dual-enhanced attack framework. First, drawing on primacy effects and position bias, we introduce a cognitive distribution-driven extraction mechanism that maps discrete rankings into continuous value distributions with position-aware decay, thereby advancing from order alignment to cognitive distribution alignment. Second, we design a behavior-aware noisy item generation strategy that jointly optimizes collaborative signals and gradient signals. This ensures both semantic coherence and statistical stealth while effectively promoting target item rankings. Extensive experiments on multiple datasets demonstrate that our approach significantly outperforms existing methods in both attack success rate and evasion rate, validating the value of integrating cognitive modeling and behavioral consistency for secure recommender systems.

cs.IR↗

arXiv2026

Nimbus: A Unified Embodied Synthetic Data Generation Framework

Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to expensive physical data acquisition, existing pipelines remain fragmented and task-specific. This isolation leads to significant engineering inefficiency and system instability, failing to support the sustained, high-throughput data generation required for foundation model training. To address these challenges, we present Nimbus, a unified synthetic data generation framework designed to integrate heterogeneous navigation and manipulation pipelines. Nimbus introduces a modular four-layer architecture featuring a decoupled execution model that separates trajectory planning, rendering, and storage into asynchronous stages. By implementing dynamic pipeline scheduling, global load balancing, distributed fault tolerance, and backend-specific rendering optimizations, the system maximizes resource utilization across CPU, GPU, and I/O resources. Our evaluation demonstrates that Nimbus achieves a 2-3X improvement in end-to-end throughput compared to unoptimized baselines and ensuring robust, long-term operation in large-scale distributed environments. This framework serves as the production backbone for the InternData suite, enabling seamless cross-domain data synthesis.

cs.RO↗

arXiv2026

Towards Automatic Evaluation and High-Quality Pseudo-Parallel Dataset Construction for Audio Editing: A Human-in-the-Loop Method

Audio editing aims to manipulate audio content based on textual descriptions, supporting tasks such as adding, removing, or replacing audio events. Despite recent progress, the lack of high-quality benchmark datasets and comprehensive evaluation metrics remains a major challenge for both assessing audio editing quality and improving the task itself. In this work, we propose a novel approach for audio editing task by incorporating expert knowledge into both the evaluation and dataset construction processes: 1) First, we establish AuditScore, the first comprehensive dataset for subjective evaluation of audio editing, consisting of over 6,300 edited samples generated from 7 representative audio editing frameworks and 23 system configurations. Each sample is annotated by professional raters on three key aspects of audio editing quality: overall Quality, Relevance to editing intent, and Faithfulness to original features. 2) Based on this dataset, we systematically propose AuditEval, a family of automatic MOS-style evaluators tailored for audio editing, covering both SSL-based and LLM-based approaches. It addresses the lack of effective objective metrics and the prohibitive cost of subjective evaluation in this field. 3) We further leverage AuditEval to evaluate and filter a large amount of synthetically mixed editing pairs, mining a high-quality pseudo-parallel subset by selecting the most plausible samples. Comprehensive experiments validate that our expert-informed filtering strategy effectively yields higher-quality data, while also exposing the limitations of traditional objective metrics and the advantages of AuditEval. The dataset, codes and tools can be found at: https://github.com/NKU-HLT/AuditEval.

cs.SD↗

arXiv2026

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized distributed training due to the tight coupling between parameter learning and rollout sampling. For this, we propose HeteroRL, a heterogeneous RL architecture that decouples these processes, enabling stable training across geographically distributed nodes connected via the Internet. The core component is Group Expectation Policy Optimization (GEPO), an asynchronous RL algorithm robust to latency caused by network delays or heterogeneity in computational resources. Our study reveals that high latency significantly increases KL divergence, leading to higher variance of importance weights and training instability. GEPO mitigates this issue by using group expectation weighting to exponentially reduce the variance of importance weights, with theoretical guarantees. Experiments show GEPO achieves superior stability - only a 3% performance drop from online to 1800s latency-and reduces the best-to-last gap by 85% versus GSPO (1.8 vs. 12.0) while attaining the highest scores, highlighting its effectiveness in decentralized, resource-heterogeneous environments.

cs.LG↗

arXiv2026

AudioEval: Automatic Dual-Perspective and Multi-Dimensional Evaluation of Text-to-Audio-Generation

Text-to-audio (TTA) generation is advancing rapidly, but evaluation remains challenging because human listening studies are expensive and existing automatic metrics capture only limited aspects of perceptual quality. We introduce AudioEval, a large-scale TTA evaluation dataset with 4,200 generated audio samples (11.7 hours) from 24 systems and 126,000 ratings collected from both experts and non-experts across five dimensions: enjoyment, usefulness, complexity, quality, and text alignment. Using AudioEval, we benchmark diverse automatic evaluators to compare perspective- and dimension-level differences across model families. We also propose Qwen-DisQA as a strong reference baseline: it jointly processes prompts and generated audio to predict multi-dimensional ratings for both annotator groups, modeling rater disagreement via distributional prediction and achieving strong performance. We will release AudioEval to support future research in TTA evaluation.

cs.SD↗

arXiv2026

Macroscopic dynamics of quadratic integrate-and-fire neurons subject to correlated noise

The presence of correlated noise, arising from a mixture of independent fluctuations and a common noisy input shared across the neural population, is a ubiquitous feature of neural circuits, yet its impact on collective network dynamics remains poorly understood. We analyze a network of quadratic integrate-and-fire neurons driven by Gaussian noise with a tunable degree of correlation. Using the cumulant expansion method, we derive a reduced set of effective mean-field equations that accurately describe the evolution of the population's mean firing rate and membrane potential. Our analysis reveals a counterintuitive phenomenon: increasing the noise correlation strength suppresses the mean network activity, an effect we term correlated-noise-inhibited spiking. Furthermore, within a specific parameter regime, the network exhibits metastability, manifesting itself as spontaneous, noise-driven transitions between distinct high- and low-activity states. These results provide a theoretical framework for reducing the dynamics of complex stochastic networks and demonstrate how correlated noise can fundamentally regulate macroscopic neural activity, with implications for understanding state transitions in biological systems.

q-bio.NC↗

arXiv2026

LightFormer: A lightweight and efficient decoder for remote sensing image segmentation

Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder complexity. Herein, we introduce LightFormer, a lightweight decoder for time-critical tasks that involve unstructured targets, such as disaster assessment, unmanned aerial vehicle search-and-rescue, and cultural heritage monitoring. LightFormer employs a feature-fusion and refinement module built on channel processing and a learnable gating mechanism to aggregate multi-scale, multi-range information efficiently, which drastically curtails model complexity. Furthermore, we propose a spatial information selection module (SISM) that integrates long-range attention with a detail preservation branch to capture spatial dependencies across multiple scales, thereby substantially improving the recognition of unstructured targets in complex scenes. On the ISPRS Vaihingen benchmark, LightFormer attains 99.9% of GLFFNet's mIoU (83.9% vs. 84.0%) while requiring only 14.7% of its FLOPs and 15.9% of its parameters, thus achieving an excellent accuracy-efficiency trade-off. Consistent results on LoveDA, ISPRS Potsdam, RescueNet, and FloodNet further demonstrate its robustness and superior perception of unstructured objects. These findings highlight LightFormer as a practical solution for remote sensing applications where both computational economy and high-precision segmentation are imperative.

cs.CV↗

arXiv2026

SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems. Existing SDR systems typically adopt a cascaded framework, combining multiple modules such as speaker diarization (SD) and automatic speech recognition (ASR). The cascaded systems suffer from several limitations, such as error propagation, difficulty in handling overlapping speech, and lack of joint optimization for exploring the synergy between SD and ASR tasks. To address these limitations, we introduce SpeakerLM, a unified multimodal large language model for SDR that jointly performs SD and ASR in an end-to-end manner. Moreover, to facilitate diverse real-world scenarios, we incorporate a flexible speaker registration mechanism into SpeakerLM, enabling SDR under different speaker registration settings. SpeakerLM is progressively developed with a multi-stage training strategy on large-scale real data. Extensive experiments show that SpeakerLM demonstrates strong data scaling capability and generalizability, outperforming state-of-the-art cascaded baselines on both in-domain and out-of-domain public SDR benchmarks. Furthermore, experimental results show that the proposed speaker registration mechanism effectively ensures robust SDR performance of SpeakerLM across diverse speaker registration conditions and varying numbers of registered speakers.

cs.SD↗

arXiv2025

DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations

Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing E2E approaches primarily fall into two categories: (1) Methods that generate discrete speech tokens independently without incorporating them into the LLM's autoregressive process, resulting in text generation being unaware of concurrent speech synthesis. (2) Models that generate interleaved or parallel speech-text tokens through joint autoregressive modeling, enabling mutual modality awareness during generation. This paper presents DrVoice, a parallel speech-text voice conversation model based on joint autoregressive modeling, featuring dual-resolution speech representations. Notably, while current methods utilize mainly 12.5Hz input audio representation, our proposed dual-resolution mechanism reduces the input frequency for the LLM to 5Hz, significantly reducing computational cost and alleviating the frequency discrepancy between speech and text tokens and in turn better exploiting LLMs' capabilities. Experimental results demonstrate that DrVoice-7B establishes new state-of-the-art (SOTA) on prominent speech benchmarks including OpenAudioBench, VoiceBench, UltraEval-Audio and Big Bench Audio, making it a leading open-source speech foundation model in ~7B models.

cs.CL↗

arXiv2025

GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing

Shape deviation modeling and compensation in additive manufacturing are pivotal for achieving high geometric accuracy and enabling industrial-scale production. Critical challenges persist, including generalizability across complex geometries and adaptability to position-dependent variations in batch production. Traditional methods of controlling geometric deviations often rely on complex parameterized models and repetitive metrology, which can be time-consuming yet not applicable for batch production. In this paper, we present a novel, process-agnostic approach to address the challenge of ensuring geometric precision and accuracy in position-dependent AM production. The proposed GraphCompNet presents a novel computational framework integrating graph-based neural networks with a GAN inspired training paradigm. The framework leverages point cloud representations and dynamic graph convolutional neural networks (DGCNNs) to model intricate geometries while incorporating position-specific thermal and mechanical variations. A two-stage adversarial training process iteratively refines compensated designs using a compensator-predictor architecture, enabling real-time feedback and optimization. Experimental validation across various shapes and positions demonstrates the framework's ability to predict deviations in freeform geometries and adapt to position-dependent batch production conditions, significantly improving compensation accuracy (35 to 65 percent) across the entire printing space, addressing position-dependent variabilities within the print chamber. The proposed method advances the development of a Digital Twin for AM, offering scalable, real-time monitoring and compensation capabilities.

cs.CV↗

arXiv2025

CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models

Automatic Heuristic Design (AHD) is an effective framework for solving complex optimization problems. The development of large language models (LLMs) enables the automated generation of heuristics. Existing LLM-based evolutionary methods rely on population strategies and are prone to local optima. Integrating LLMs with Monte Carlo Tree Search (MCTS) improves the trade-off between exploration and exploitation, but multi-round cognitive integration remains limited and search diversity is constrained. To overcome these limitations, this paper proposes a novel cognitive-guided MCTS framework (CogMCTS). CogMCTS tightly integrates the cognitive guidance mechanism of LLMs with MCTS to achieve efficient automated heuristic optimization. The framework employs multi-round cognitive feedback to incorporate historical experience, node information, and negative outcomes, dynamically improving heuristic generation. Dual-track node expansion combined with elite heuristic management balances the exploration of diverse heuristics and the exploitation of high-quality experience. In addition, strategic mutation modifies the heuristic forms and parameters to further enhance the diversity of the solution and the overall optimization performance. The experimental results indicate that CogMCTS outperforms existing LLM-based AHD methods in stability, efficiency, and solution quality.

cs.AI↗