arXiv subjects

Lin Zhang

Publications and source records attributed to Lin Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and A Fourier Kolmogorov-Arnold Framework

Although Coordinate-MLP-based implicit neural representations have excelled in representing radiance fields, 3D shapes, and images, their application to audio signals remains underexplored. To fill this gap, we investigate existing implicit neural representations, from which we extract 3 types of positional encoding and 16 commonly used activation functions. Through combinatorial design, we establish the first benchmark for Coordinate-MLPs in audio signal representations. Our benchmark reveals that Coordinate-MLPs require complex hyperparameter tuning and frequency-dependent initialization, limiting their robustness. To address these issues, we propose Fourier-ASR, a novel framework based on the Fourier series theorem and the Kolmogorov-Arnold representation theorem. Fourier-ASR introduces Fourier Kolmogorov-Arnold Networks (Fourier-KAN), which leverage periodicity and strong nonlinearity to represent audio signals, eliminating the need for additional positional encoding. Furthermore, a Frequency-adaptive Learning Strategy (FaLS) is proposed to enhance the convergence of Fourier-KAN by capturing high-frequency components and preventing overfitting of low-frequency signals. Extensive experiments conducted on natural speech and music datasets reveal that: (1) well-designed positional encoding and activation functions in Coordinate-MLPs can effectively improve audio representation quality; and (2) Fourier-ASR can robustly represent complex audio signals without extensive hyperparameter tuning. Looking ahead, the continuity and infinite resolution of implicit audio representations make our research highly promising for tasks such as audio compression, synthesis, and generation. The source code will be released publicly to ensure reproducibility. The code is available at https://github.com/lif314/Fourier-ASR.

cs.SD↗

arXiv2025

Hybrid A* Path Planning with Multi-Modal Motion Extension for Four-Wheel Steering Mobile Robots

Four-wheel independent steering (4WIS) systems provide mobile robots with a rich set of motion modes, such as Ackermann steering, lateral steering, and parallel movement, offering superior maneuverability in constrained environments. However, existing path planning methods generally assume a single kinematic model and thus fail to fully exploit the multi-modal capabilities of 4WIS platforms. To address this limitation, we propose an extended Hybrid A* framework that operates in a four-dimensional state space incorporating both spatial states and motion modes. Within this framework, we design multi-modal Reeds-Shepp curves tailored to the distinct kinematic constraints of each motion mode, develop an enhanced heuristic function that accounts for mode-switching costs, and introduce a terminal connection strategy with intelligent mode selection to ensure smooth transitions between different steering patterns. The proposed planner enables seamless integration of multiple motion modalities within a single path, significantly improving flexibility and adaptability in complex environments. Results demonstrate significantly improved planning performance for 4WIS robots in complex environments.

cs.RO↗

arXiv2025

DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environments

Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. Most existing approaches rely on single-frame observation and employ simple concatenation for multi-modal fusion, which limits their ability to capture temporal context and hinders dynamic adaptability. To address these challenges, we propose a DRL-based navigation framework, DRL-TH, which leverages temporal graph attention and hierarchical graph pooling to integrate historical observations and adaptively fuse multi-modal information. Specifically, we introduce a temporal-guided graph attention network (TG-GAT) that incorporates temporal weights into attention scores to capture correlations between consecutive frames, thereby enabling the implicit estimation of scene evolution. In addition, we design a graph hierarchical abstraction module (GHAM) that applies hierarchical pooling and learnable weighted fusion to dynamically integrate RGB and LiDAR features, achieving balanced representation across multiple scales. Extensive experiments demonstrate that our DRL-TH outperforms existing methods in various crowded environments. We also implemented DRL-TH control policy on a real UGV and showed that it performed well in real world scenarios.

cs.RO↗

arXiv2025

XTrace: A Non-Invasive Dynamic Tracing Framework for Android Applications in Production

As the complexity of mobile applications grows exponentially and the fragmentation of user device environments intensifies, ensuring online application stability faces unprecedented challenges. Traditional methods, such as static logging and post-crash analysis, lack real-time contextual information, rendering them ineffective against "ghost bugs" that only manifest in specific scenarios. This highlights an urgent need for dynamic runtime observability: intercepting and tracing arbitrary methods in production without requiring an app release. We propose XTrace, a novel dynamic tracing framework. XTrace introduces a new paradigm of non-invasive proxying, which avoids direct modification of the virtual machine's underlying data structures. It achieves high-performance method interception by leveraging and optimizing the highly stable, built-in instrumentation mechanism of the Android ART virtual machine. Evaluated in a ByteDance application with hundreds of millions of daily active users, XTrace demonstrated production-grade stability and performance. Large-scale online A/B experiments confirmed its stability, showing no statistically significant impact (p > 0.05) on Crash User Rate or ANR rate, while maintaining minimal overhead (<7 ms startup latency, <0.01 ms per-method call) and broad compatibility (Android 5.0-15+). Critically, XTrace diagnosed over 11 severe online crashes and multiple performance bottlenecks, improving root-cause localization efficiency by over 90%. This confirms XTrace provides a production-grade solution that reconciles the long-standing conflict between stability and comprehensive coverage in Android dynamic tracing.

cs.SE↗

arXiv2025

SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images

Recent advances in generative AI have accelerated the production of ultra-high-resolution visual content, posing significant challenges for efficient compression and real-time decoding on end-user devices. Inspired by 3D Gaussian Splatting, recent 2D Gaussian image models improve representation efficiency, yet existing methods struggle to balance compression ratio and reconstruction fidelity in ultra-high-resolution scenarios. To address this issue, we propose SmartSplat, a highly adaptive and feature-aware GS-based image compression framework that supports arbitrary image resolutions and compression ratios. SmartSplat leverages image-aware features such as gradients and color variances, introducing a Gradient-Color Guided Variational Sampling strategy together with an Exclusion-based Uniform Sampling scheme to improve the non-overlapping coverage of Gaussian primitives in pixel space. In addition, we propose a Scale-Adaptive Gaussian Color Sampling method to enhance color initialization across scales. Through joint optimization of spatial layout, scale, and color initialization, SmartSplat efficiently captures both local structures and global textures using a limited number of Gaussians, achieving high reconstruction quality under strong compression. Extensive experiments on DIV8K and a newly constructed 16K dataset demonstrate that SmartSplat consistently outperforms state-of-the-art methods at comparable compression ratios and exceeds their compression limits, showing strong scalability and practical applicability. The code is publicly available at https://github.com/lif314/SmartSplat.

cs.CV↗

arXiv2025

Beyond openness: Inclusiveness and usability of Chinese scholarly data in OpenAlex

OpenAlex, launched in 2022 as a fully open scholarly data source, promises greater inclusiveness compared to traditional proprietary databases. This study evaluates whether OpenAlex delivers on that promise by examining its coverage and metadata quality for Chinese-language journals and their articles. Using the 2023 edition of A Guide to the Core Journals of China (GCJC) and Wanfang Data as a benchmark, we analyze three aspects: (1) journal-level coverage, (2) article-level coverage, and (3) completeness and accuracy of metadata fields. Results show that OpenAlex indexes only 37% of GCJC journals and 24% of their articles, with substantial disciplinary and temporal variation. Metadata quality is uneven: while basic fields such as title and publication year are complete, bibliographic details, author affiliations, and cited references are frequently missing or inaccurate. DOI coverage is limited, and language information is often incorrect, with most Chinese-language articles labeled as English. These findings highlight significant challenges for achieving full inclusiveness and usability in research evaluation and related activities. We conclude with recommendations for improving data aggregation strategies, DOI registration practices, and metadata standardization to enhance the integration of local scholarly outputs into global open infrastructures.

cs.DL↗

arXiv2025

BUT Systems for WildSpoof Challenge: SASV in the Wild

This paper presents the BUT submission to the WildSpoof Challenge, focusing on the Spoofing-robust Automatic Speaker Verification (SASV) track. We propose a SASV framework designed to bridge the gap between general audio understanding and specialized speech analysis. Our subsystem integrates diverse Self-Supervised Learning front-ends ranging from general audio models (e.g., Dasheng) to speech-specific encoders (e.g., WavLM). These representations are aggregated via a lightweight Multi-Head Factorized Attention back-end for corresponding subtasks. Furthermore, we introduce a feature domain augmentation strategy based on Distribution Uncertainty to explicitly model and mitigate the domain shift caused by unseen neural vocoders and recording environments. By fusing these robust CM scores with state-of-the-art ASV systems, our approach achieves superior minimization of the a-DCFs and EERs.

eess.AS↗

arXiv2025

BUT Systems for Environmental Sound Deepfake Detection in the ESDD 2026 Challenge

This paper describes the BUT submission to the ESDD 2026 Challenge, specifically focusing on Track 1: Environmental Sound Deepfake Detection with Unseen Generators. To address the critical challenge of generalizing to audio generated by unseen synthesis algorithms, we propose a robust ensemble framework leveraging diverse Self-Supervised Learning (SSL) models. We conduct a comprehensive analysis of general audio SSL models (including BEATs, EAT, and Dasheng) and speech-specific SSLs. These front-ends are coupled with a lightweight Multi-Head Factorized Attention (MHFA) back-end to capture discriminative representations. Furthermore, we introduce a feature domain augmentation strategy based on distribution uncertainty modeling to enhance model robustness against unseen spectral distortions. All models are trained exclusively on the official EnvSDD data, without using any external resources. Experimental results demonstrate the effectiveness of our approach: our best single system achieved Equal Error Rates (EER) of 0.00\%, 4.60\%, and 4.80\% on the Development, Progress (Track 1), and Final Evaluation sets, respectively. The fusion system further improved generalization, yielding EERs of 0.00\%, 3.52\%, and 4.38\% across the same partitions.

eess.AS↗

arXiv2025

Probing Anharmonic Lattice Dynamics and Thermal Transport in Layered Perovskite LiYTiO4 Anode

Layered perovskite lithium yttrium titanate ($\rm LiYTiO_4$) has recently emerged as a promising low-potential, ultrahigh-rate intercalation-type anode material for lithium-ion batteries; however, its lattice dynamics and thermal transport properties remain poorly understood, limiting a complete evaluation of its practical potential. Here, we combine experimental measurements with theoretical modeling to systematically investigate the anharmonic lattice dynamics and heat transport in $\rm LiYTiO_4$. We employ a neural evolution potential (NEP)-based framework that integrates the temperature-dependent effective potential method with the Wigner thermal transport (WTT) formalism, explicitly including both diagonal and off-diagonal terms of the heat-flux operator. Zero-temperature phonon calculations reveal dynamical instabilities associated with $\rm TiO_6$ octahedral rotation, which are stabilized at finite temperatures through anharmonic renormalization. Using the WTT approach with contributions from phonon propagation and coherence contributions, we predict a room-temperature lattice thermal conductivity ($κ_{\rm L}$) of 3.8 $\rm Wm^{-1}K^{-1}$ averaged over all crystal orientations, in close agreement with the measured value of 3.2 \pm 0.08 $\rm Wm^{-1}K^{-1}$ for polycrystalline samples. To further examine the possible influence of ionic motion on high-temperature thermal transport, we compute $κ_{\rm L}$ using a Green-Kubo equilibrium molecular dynamics approach based on the same NEP, which yields consistent results with both experiment and WTT predictions, confirming the negligible role of Li-ion mobility in heat conduction. Our study not only identifies the ultralow thermal conductivity of $\rm LiYTiO_4$ as a key limitation for its practical application but also establishes a reliable computational framework for studying thermal properties in battery materials.

cond-mat.mtrl-sci↗

arXiv2025

Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization

Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generated text conflicts with the visual input. Prior work links this partly to insufficient visual attention, but existing attention-based detectors and mitigation typically apply uniform adjustments across layers and heads, obscuring where errors originate. In this paper, we first show these methods fail to accurately localize problematic layers. Then, we introduce two diagnostics: Layer Image Attention Entropy (LIAE) which flags anomalous layers, and Image Attention Focus (IAF) which scores attention heads within those layers. Analysis shows that LIAE pinpoints faulty layers and IAF reliably ranks heads that warrant correction. Guided by these signals, we propose Dynamic Layer-wise Entropy and Attention Fusion (D-LEAF), a task-agnostic, attention-guided method that dynamically localizes and corrects errors during inference with negligible overhead. Furthermore, by establishing a connection between D-LEAF and DPO, we provide theoretical justification for the effectiveness of D-LEAF. Results show our D-LEAF delivers a 53\% relative improvement on standard captioning benchmarks, and on VQA both accuracy and F1-score improve by approximately 4\%, substantially suppressing hallucinations while preserving efficiency.

cs.CV↗

arXiv2025

Lane Departure Accident Prevention in Foggy Conditions: A Prior-Guided Dynamic Feature Fusion Transformer Framework for Real-Time Lane Detection

Lane departure accident prevention plays a critical role in enhancing road safety, and lane detection is a core technology to achieve this goal, especially under complex weather conditions. While existing lane detection algorithms perform well under favorable weather conditions, their effectiveness significantly degrades in foggy environments, which increases the risk of traffic accidents. In response to this challenge, we propose PDT-Net, a robust Prior-Guided Dynamic Feature Fusion Transformer framework designed for real-time lane detection in foggy conditions. This framework integrates three key modules: a Global Feature Fusion Module (GFFM) to capture the relationship between local and global features in foggy images, a Dynamic Feature Fusion Module (DFFM) to model the structural and positional relationships of lane instances, and a Prior-Guided Edge Enhancement Module (PEM) to recover lost edge details in foggy environments. Furthermore, we introduce the FoggyLane dataset, a real-world dataset that specifically targets lane detection in foggy conditions, along with two synthesized datasets, FoggyCULane and FoggyTusimple, to address the lack of fog-specific data for lane detection. Extensive experiments show that PDT-Net achieves state-of-the-art performance with F1-scores of 95.04% on FoggyLane, 79.85% on FoggyCULane, and 96.95% on FoggyTusimple. Moreover, with TensorRT acceleration, our method achieves a processing speed of 38.4 FPS on the NVIDIA Jetson AGX Orin, confirming its real-time capability and robustness in challenging foggy environments. By improving the precision of lane detection, our framework can contribute to active safety warning systems, helping to prevent accidents in foggy conditions.

cs.CV↗

arXiv2025

Bargmann-invariant framework for local unitary equivalence and entanglement

Research on quantum states often focuses on the correlation between nonlocal effects and local unitary invariants, among which local unitary equivalence plays a significant role in quantum state classification and resource theories. This paper focuses on the local unitary equivalence of multipartite quantum states in quantum information theory, aiming to determine a complete set of invariants that identify their local unitary orbits; these invariants are crucial for deriving polynomial invariants and describing the physical properties preserved under local unitary transformations.The study deeply explores the characterization of local unitary equivalence and the method of detecting entanglement using local unitary Bargmann invariants. Taking two-qubit systems as an example, it verifies the measurability of invariants that determine equivalence and establishes a connection between Makhlin fundamental invariants (a complete set of 18 local unitary invariants for two-qubit states) and local unitary Bargmann invariants. These Bargmann invariants, related to the traces of products of density operators and marginal states, can be measured through cycle tests (an extended form of SWAP tests).

quant-ph↗

arXiv2025

Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a key technique for model compression, existing methods typically separate it from task-specific fine-tuning. This multi-stage approach struggles to create optimal architectures tailored for diverse downstream tasks. In this work, we introduce a unified framework that integrates structured pruning into the downstream fine-tuning process. Our framework unifies these steps, jointly optimizing for task performance and model sparsity in a single stage. This allows the model to learn a compressed architecture specifically for the end task, eliminating the need for complex multi-stage pipelines and knowledge distillation. Our pruned models achieve up to a 70\% parameter reduction with negligible performance degradation on large-scale datasets, achieving equal error rates of 0.7\%, 0.8\%, and 1.6\% on Vox1-O, -E, and -H, respectively. Furthermore, our approach demonstrates improved generalization in low-resource scenarios, reducing overfitting and achieving a state-of-the-art 3.7\% EER on ASVspoof5.

eess.AS↗

arXiv2025

A Dual Large Language Models Architecture with Herald Guided Prompts for Parallel Fine Grained Traffic Signal Control

Leveraging large language models (LLMs) in traffic signal control (TSC) improves optimization efficiency and interpretability compared to traditional reinforcement learning (RL) methods. However, existing LLM-based approaches are limited by fixed time signal durations and are prone to hallucination errors, while RL methods lack robustness in signal timing decisions and suffer from poor generalization. To address these challenges, this paper proposes HeraldLight, a dual LLMs architecture enhanced by Herald guided prompts. The Herald Module extracts contextual information and forecasts queue lengths for each traffic phase based on real-time conditions. The first LLM, LLM-Agent, uses these forecasts to make fine grained traffic signal control, while the second LLM, LLM-Critic, refines LLM-Agent's outputs, correcting errors and hallucinations. These refined outputs are used for score-based fine-tuning to improve accuracy and robustness. Simulation experiments using CityFlow on real world datasets covering 224 intersections in Jinan (12), Hangzhou (16), and New York (196) demonstrate that HeraldLight outperforms state of the art baselines, achieving a 20.03% reduction in average travel time across all scenarios and a 10.74% reduction in average queue length on the Jinan and Hangzhou scenarios. The source code is available on GitHub: https://github.com/BUPT-ANTlab/HeraldLight.

cs.LG↗

arXiv2025

Retrieval Augmented Generation-Enhanced Distributed LLM Agents for Generalizable Traffic Signal Control with Emergency Vehicles

With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to hallucinations in emergencies, leading to unreliable decisions that may cause substantial delays for emergency vehicles. Moreover, diverse intersection types present substantial challenges for traffic state encoding and cross-intersection training, limiting generalization across heterogeneous intersections. Therefore, this paper proposes Retrieval Augmented Generation (RAG)-enhanced distributed LLM agents with Emergency response for Generalizable TSC (REG-TSC). Firstly, this paper presents an emergency-aware reasoning framework, which dynamically adjusts reasoning depth based on the emergency scenario and is equipped with a novel Reviewer-based Emergency RAG (RERAG) to distill specific knowledge and guidance from historical cases, enhancing the reliability and rationality of agents' emergency decisions. Secondly, this paper designs a type-agnostic traffic representation and proposes a Reward-guided Reinforced Refinement (R3) for heterogeneous intersections. R3 adaptively samples training experience from diverse intersections with environment feedback-based priority and fine-tunes LLM agents with a designed reward-weighted likelihood loss, guiding REG-TSC toward high-reward policies across heterogeneous intersections. On three real-world road networks with 17 to 177 heterogeneous intersections, extensive experiments show that REG-TSC reduces travel time by 42.00%, queue length by 62.31%, and emergency vehicle waiting time by 83.16%, outperforming other state-of-the-art methods.

cs.AI↗

arXiv2025

Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning

The proliferation of harmful online content--e.g., toxicity, spam, and negative sentiment--demands robust and adaptable moderation systems. However, prevailing moderation systems are centralized and task-specific, offering limited transparency and neglecting diverse user preferences--an approach ill-suited for privacy-sensitive or decentralized environments. We propose a novel framework that leverages in-context learning (ICL) with foundation models to unify the detection of toxicity, spam, and negative sentiment across binary, multi-class, and multi-label settings. Crucially, our approach enables lightweight personalization, allowing users to easily block new categories, unblock existing ones, or extend detection to semantic variations through simple prompt-based interventions--all without model retraining. Extensive experiments on public benchmarks (TextDetox, UCI SMS, SST2) and a new, annotated Mastodon dataset reveal that: (i) foundation models achieve strong cross-task generalization, often matching or surpassing task-specific fine-tuned models; (ii) effective personalization is achievable with as few as one user-provided example or definition; and (iii) augmenting prompts with label definitions or rationales significantly enhances robustness to noisy, real-world data. Our work demonstrates a definitive shift beyond one-size-fits-all moderation, establishing ICL as a practical, privacy-preserving, and highly adaptable pathway for the next generation of user-centric content safety systems. To foster reproducibility and facilitate future research, we publicly release our code on GitHub and the annotated Mastodon dataset on Hugging Face.

cs.CL↗

arXiv2025

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization

Circuit discovery, which involves identifying sparse and task-relevant subnetworks in pre-trained language models, is a cornerstone of mechanistic interpretability. Automated Circuit Discovery (ACDC) has emerged as a pivotal methodology in circuit discovery, but its application to large language models is severely limited by computational inefficiency and prohibitively high memory requirements. Although several accelerated approaches have been proposed, they primarily rely on linear approximations to ACDC, which significantly compromises analytical faithfulness. Our proposed method for accelerating automated circuit discovery, Per Attention Head Quantization (PAHQ), takes a fundamentally different approach by optimizing the efficiency of each individual patching operation. PAHQ leverages a fundamental alignment between activation patching and mixed-precision quantization (MPQ): interpretability analysis through patching essentially performs targeted ablation studies. Therefore, we can maintain high precision exclusively for investigated components while safely reducing precision elsewhere in the network. PAHQ-accelerated ACDC reduces runtime by up to 80\% and memory consumption by up to 30\% compared to unaccelerated ACDC while maintaining faithfulness. Importantly, our method readily integrates with existing edge-based circuit discovery techniques by modifying the attention computation mechanism. This training-free approach provides a practical and novel pathway for accelerating mechanistic interpretability methods. Our code is available at https://github.com/626619403/PAHQ.

cs.LG↗

arXiv2025

Detection of quantum information masking via machine learning

Recently, machine learning has been widely applied in the field of quantum information, notably in tasks such as entanglement detection, steering characterization, and nonlocality verification. However, few studies have focused on utilizing machine learning to detect quantum information masking. In this work, we investigate supervised machine learning for detecting quantum information masking in both pure and mixed qubit states. For pure qubit states, we randomly generate the corresponding density matrices and train an XGBoost model to detect quantum information masking. For mixed qubit states, we improve the XGBoost method by optimizing the selection of training samples. The experimental results demonstrate that our approach achieves higher classification accuracy. Furthermore, we analyze the area under the curve (AUC) of the receiver operating characteristic curve for this method, which further confirms its classification performance.

quant-ph↗