arXiv subjects

Yang Xiao

Publications and source records attributed to Yang Xiao.

At least 109 records · Page 6Linked to original sources

arXiv2026

MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System Evaluation

Recent advances in generative models have enabled modern Text-to-Audio (TTA) systems to synthesize audio with high perceptual quality. However, TTA systems often struggle to maintain semantic consistency with the input text, leading to mismatches in sound events, temporal tructures, or contextual relationships. Evaluating semantic fidelity in TTA remains a significant challenge. Traditional methods primarily rely on subjective human listening tests, which is time-consuming. To solve this, we propose an objective evaluator based on a Mixture of Experts (MoE) architecture with Sequential Cross-Attention (SeqCoAttn). Our model achieves the first rank in the XACLE Challenge, with an SRCC of 0.6402 (an improvement of 30.6% over the challenge baseline) on the test dataset. Code is available at: https://github.com/S-Orion/MOESCORE.

cs.SD↗

arXiv2025

Environmental Sound Deepfake Detection Challenge: An Overview

Recent progress in audio generation models has made it possible to create highly realistic and immersive soundscapes, which are now widely used in film and virtual-reality-related applications. However, these audio generators also raise concerns about potential misuse, such as producing deceptive audio for fabricated videos or spreading misleading information. Therefore, it is essential to develop effective methods for detecting fake environmental sounds. Existing datasets for environmental sound deepfake detection (ESDD) remain limited in both scale and the diversity of sound categories they cover. To address this gap, we introduced EnvSDD, the first large-scale curated dataset designed for ESDD. Based on EnvSDD, we launched the ESDD Challenge, recognized as one of the ICASSP 2026 Grand Challenges. This paper presents an overview of the ESDD Challenge, including a detailed analysis of the challenge results.

cs.SD↗

arXiv2025

ESDD 2026: Environmental Sound Deepfake Detection Challenge Evaluation Plan

Recent advances in audio generation systems have enabled the creation of highly realistic and immersive soundscapes, which are increasingly used in film and virtual reality. However, these audio generators also raise concerns about potential misuse, such as generating deceptive audio content for fake videos and spreading misleading information. Existing datasets for environmental sound deepfake detection (ESDD) are limited in scale and audio types. To address this gap, we have proposed EnvSDD, the first large-scale curated dataset designed for ESDD, consisting of 45.25 hours of real and 316.7 hours of fake sound. Based on EnvSDD, we are launching the Environmental Sound Deepfake Detection Challenge. Specifically, we present two different tracks: ESDD in Unseen Generators and Black-Box Low-Resource ESDD, covering various challenges encountered in real-life scenarios. The challenge will be held in conjunction with the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026).

cs.SD↗

arXiv2025

Worth the Effort? An Examination on the Effect of Higher Diligence Calculations of the Sound Shell Model

The gravitational wave spectrum arising from using the full velocity profile is well known to differ qualitatively from analytic fits to a broken power law. Former studies have shown that unlike the uncertainties arising from thermal field theory, more diligence in the hydrodynamics can sometimes have limited benefit. However, this was shown in the context of broken power law fits. We test the benefits of some recent calculations in modeling the spectrum, including new developments in adjustments of the low frequency tail to be consistent with causality, but we use the full velocity profile. We find the spectral shape information has a heightened sensitivity to the speed of sound which can be demonstrated analytically, however for our benchmark model this still results in a modest difference. The reason for a heightened sensitivity is because the velocity at the boundary is quite sensitive to the speed of sound, which in turn means a small change to the speed of sound can have a large change to the shape of the velocity profile. Furthermore, even modest changes in the product $ακ$ can make non-trivial changes to the shape around the peak. Finally, there are many points where adjusting the infrared behavior to be consistent with causality is affecting the spectrum near its peak. All this implies that the spectrum is sensitive to five thermal parameters rather than four which gives hope that an observation of a gravitational wave spectrum from a first order cosmological phase transition could eventually give even more information about the underlying microphysics responsible.

hep-ph↗

arXiv2025

SPVR: syntax-to-prompt vulnerability repair based on large language models

Purpose: In the field of vulnerability repair, previous research has leveraged pretrained models and LLM-based prompt engineering, among which LLM-based approaches show better generalizability and achieve the best performance. However, the LLM-based approaches generally regard vulnerability repair as a sequence-to-sequence task, and do not explicitly capture the syntax patterns for different vulnerability types, leading to limited accuracy. We aim to create a method that ensures the specificity of prompts targeting vulnerable code while also leveraging the generative capabilities of Large Language Models. Methods: We propose SPVR (Syntax-to-Prompt Vulnerability Repair), a novel framework that collects information from syntax trees, and generates corresponding prompts. Our method consists of three steps: rule design, prompt generation, and patch generation. In the rule design step, our method parses code patches and designs rules to extract relevant contextual information. These rules aid in identifying vulnerability-related issues. In the prompt generation step, our method extracts information from vulnerable code with pre-defined rules, automatically converting them into prompts. We also incorporate the description of CWE (Common Weakness Enumeration) as known information into the prompts. Finally, in the patch generation step, this prompt will serve as input to any conversational LLM to obtain code patches. Results: Extensive experiments validate that our method achieves excellent results in assisting LLMs to fix vulnerabilities accurately. We utilize multiple Large Language Models to validate the effectiveness of our work, repairing 143 of 547 vulnerable code using ChatGPT-4. We conducted a comparison of our approach against several existing vulnerability repair approaches (including fine-tuning-based and prompt-based), across multiple metrics.

cs.SE↗

arXiv2025

Continual Learning for Acoustic Event Classification

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resources (e.g., model size, running memory). To alleviate such an issue, we propose two novel diversity-aware incremental learning method for Spoken Keyword Spotting and Environmental Sound Classification. Our method selects the historical data for the training by measuring the per-sample classification uncertainty. For the Spoken Keyword Spotting application, the proposed RK approach introduces a diversity-aware sampler to select a diverse set from historical and incoming keywords by calculating classification uncertainty. As a result, the RK approach can incrementally learn new tasks without forgetting prior knowledge. Besides, the RK approach also proposes data augmentation and knowledge distillation loss function for efficient memory management on the edge device. For the Environmental Sound Classification application, we measure the uncertainty by observing how the classification probability of data fluctuates against the parallel perturbations added to the classifier embedding. In this way, the computation cost can be significantly reduced compared with adding perturbation to the raw data. Experimental results show that the proposed RK approach achieves 4.2% absolute improvement in terms of average accuracy over the best baseline on Google Speech Command dataset with less required memory. Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification

eess.AS↗

arXiv2025

Evaluating Hydro-Science and Engineering Knowledge of Large Language Models

Hydro-Science and Engineering (Hydro-SE) is a critical and irreplaceable domain that secures human water supply, generates clean hydropower energy, and mitigates flood and drought disasters. Featuring multiple engineering objectives, Hydro-SE is an inherently interdisciplinary domain that integrates scientific knowledge with engineering expertise. This integration necessitates extensive expert collaboration in decision-making, which poses difficulties for intelligence. With the rapid advancement of large language models (LLMs), their potential application in the Hydro-SE domain is being increasingly explored. However, the knowledge and application abilities of LLMs in Hydro-SE have not been sufficiently evaluated. To address this issue, we propose the Hydro-SE LLM evaluation benchmark (Hydro-SE Bench), which contains 4,000 multiple-choice questions. Hydro-SE Bench covers nine subfields and enables evaluation of LLMs in aspects of basic conceptual knowledge, engineering application ability, and reasoning and calculation ability. The evaluation results on Hydro-SE Bench show that the accuracy values vary among 0.74 to 0.80 for commercial LLMs, and among 0.41 to 0.68 for small-parameter LLMs. While LLMs perform well in subfields closely related to natural and physical sciences, they struggle with domain-specific knowledge such as industry standards and hydraulic structures. Model scaling mainly improves reasoning and calculation abilities, but there is still great potential for LLMs to better handle problems in practical engineering application. This study highlights the strengths and weaknesses of LLMs for Hydro-SE tasks, providing model developers with clear training targets and Hydro-SE researchers with practical guidance for applying LLMs.

cs.CL↗

arXiv2025

The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models

Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been well studied. In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model. Motivated by the observation and the right to be forgotten, we define a new terminology ``un-pruning" to eliminate the impact of deleted data on model pruning. Then we propose an un-pruning algorithm to approximate the pruned topology driven by retained data. We remark that any existing unlearning algorithm can be integrated with the proposed un-pruning workflow and the error of un-pruning is upper-bounded in theory. Also, our un-pruning algorithm can be applied to both structured sparse models and unstructured sparse models. In the experiment, we further find that Membership Inference Attack (MIA) accuracy is unreliable for assessing whether a model has forgotten deleted data, as a small change in the amount of deleted data can produce arbitrary MIA results. Accordingly, we devise new performance metrics for sparse models to evaluate the success of un-pruning. Lastly, we conduct extensive experiments to verify the efficacy of un-pruning with various pruning methods and unlearning algorithms. Our code is released at https://github.com/NKUShaw/SparseModels .

cs.LG↗

arXiv2025

Spontaneous emission in Casimir-Rabi oscillations through a weak optomechanical coupling

The dynamical Casimir effect (DCE) describes the energy conversion from a mechanical motion to the electromagnetic fields. When the mechanical oscillator is in a mechanically excited state, the free evolution due to the DCE produces radiation in the vacuum, in analogy with the spontaneous emission from an excited atom. In this manuscript, we investigate such a spontaneous radiation process by employing the quantum trajectory approach. When the dissipation rate of the system is very low, there can be a reversible energy exchange between the mirror in the excited state and the vacuum field, and this reversible exchange is called vacuum Casimir-Rabi oscillations. Multiple quantum trajectory simulations of this process show that the number of trajectories responsible for the generation of radiation can reach a significant value when the mechanical dissipation rate is less than the photon dissipation rate. We also find that two-photon (two/three-phonon) bundle emission occurs in photon (phonon) emission. In comparison to pure two-photon and three-phonon free dissipation, the probability of two-photon bundle emission and two-phonon bundle emission are observed to be marginally elevated as a consequence of the presence of the DCE. This pattern may assist in developing a deeper comprehension of the physical characteristics of photon and phonon emission in the DCE.

quant-ph↗

arXiv2025

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling

Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform resource distribution across all reasoning sub-problems, creating fundamental bottlenecks where challenging sub-problems receive insufficient attention while routine operations consume disproportionate resources. This uniform allocation creates performance bottlenecks where additional computational resources yield diminishing returns. Inspired by dual-process theory, we propose \textbf{SCALE} (Selective Resource Allocation), a framework that selectively allocates computational resources based on sub-problem difficulty. SCALE operates through four stages: (1) problem decomposition into sequential reasoning sub-problems, (2) difficulty assessment of each sub-problem to distinguish between routine operations and computationally challenging sub-problems, (3) selective processing mode assignment between System 1 for simple sub-problems and System 2 for complex ones, and (4) sequential execution with context propagation. By concentrating resources on challenging sub-problems while processing routine operations efficiently, SCALE achieves substantial performance improvements with superior resource utilization. Extensive experiments demonstrate that SCALE significantly outperforms uniform scaling baselines, achieving accuracy improvements of up to 13.75 percentage points (57.50% to 71.25% on AIME25) while reducing computational costs by 33%-53%, representing a major advance in test-time scaling that addresses fundamental limitations of current approaches.

cs.CL↗

arXiv2025

Device-Scale Atomistic Simulations of Heat Transport in Advanced Field-Effect Transistors

Self-heating in next-generation, high-power-density field-effect transistor limits performance and complicates fabrication. Here, we introduce NEP-FET, a machine-learned framework for device-scale heat transport simulations of field-effect transistors. Built upon the neuroevolution potential, the model extends a subset of the OMat24 dataset through an active-learning workflow to generate a chemically diverse, interface-rich reference set. Coupled with the FETMOD structure generator module, NEP-FET can simulate realistic field-effect transistor geometries at sub-micrometer scales containing millions of atoms, and delivers atomistic predictions of temperature fields, per-atom heat flux, and thermal stress in device structures with high fidelity. This framework enables rapid estimation of device-level metrics, including heat-flux density and effective thermal conductivity. Our results reveal pronounced differences in temperature distribution between fin-type and gate-all-around transistor architectures. The framework closes a key gap in multiscale device modeling by combining near-quantum-mechanical accuracy with device-scale throughput, providing a systematic route to explore heat transport and thermo-mechanical coupling in advanced transistors.

cond-mat.mtrl-sci↗

arXiv2025

DEXO: A Secure and Fair Exchange Mechanism for Decentralized IoT Data Markets

Opening up data produced by the Internet of Things (IoT) and mobile devices for public utilization can maximize their economic value. Challenges remain in the trustworthiness of the data sources and the security of the trading process, particularly when there is no trust between the data providers and consumers. In this paper, we propose DEXO, a decentralized data exchange mechanism that facilitates secure and fair data exchange between data consumers and distributed IoT/mobile data providers at scale, allowing the consumer to verify the data generation process and the providers to be compensated for providing authentic data, with correctness guarantees from the exchange platform. To realize this, DEXO extends the decentralized oracle network model that has been successful in the blockchain applications domain to incorporate novel hardware-cryptographic co-design that harmonizes trusted execution environment, secret sharing, and smart contract-assisted fair exchange. For the first time, DEXO ensures end-to-end data confidentiality, source verifiability, and fairness of the exchange process with strong resilience against participant collusion. We implemented a prototype of the DEXO system to demonstrate feasibility. The evaluation shows a moderate deployment cost and significantly improved blockchain operation efficiency compared to a popular data exchange mechanism.

cs.CR↗

arXiv2025

RAID: In-Network RA Signaling Storm Detection for 5G Open RAN

The disaggregation and virtualization of 5G Open RAN (O-RAN) introduces new vulnerabilities in the control plane that can greatly impact the quality of service (QoS) of latency-sensitive 5G applications and services. One critical issue is Random Access (RA) signaling storms where, a burst of illegitimate or misbehaving user equipments (UEs) send Radio Resource Control (RRC) connection requests that rapidly saturate a Central Unit's (CU) processing pipeline. Such storms trigger widespread connection failures within the short contention resolution window defined by 3GPP. Existing detection and mitigation approaches based on near-real-time RAN Intelligent Controller (n-RT RIC) applications cannot guarantee a timely reaction to such attacks as RIC control loops incur tens to hundreds of milliseconds of latency due to the non-deterministic nature of their general purpose processor (GPP) based architectures. This paper presents RAID, an in-network RA signaling storm detection and mitigation system that leverages P4-programmable switch ASICs to enable real-time protection from malicious attacks. RAID embeds a lightweight Random Forest (RF) classifier into a programmable Tofino switch, enabling line-rate flow classification with deterministic microsecond-scale inference delay. By performing ML-based detection directly in the data plane, RAID catches and filters malicious RA requests before they reach and overwhelm the RRC. RAID achieves above 94% detection accuracy with a fixed per-flow inference delay on the order of 3.4 microseconds, effectively meeting strict O-RAN control-plane deadlines. These improvements are sustained across multiple traffic loads, making RAID a fast and scalable solution for the detection and mitigation of signaling storms in 5G O-RAN.

cs.NI↗

arXiv2025

Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids

Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks, such as dispensing, aspiration, and mixing, must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks. The dataset and code are available at https://dualtransparency.github.io/Phys-Liquid/.

cs.CV↗

arXiv2025

Boundary Compactified Imaginary Liouville Theory

We generalize the construction of Compactified Imaginary Liouville Theory (CILT), a non-unitary logarithmic Conformal Field Theory (CFT) defined on closed surfaces, to surfaces with boundary. Starting from a compactified Gaussian Free Field (GFF) with Neumann boundary condition, we perturb it by adding in curvature terms and exponential potentials on both the bulk and the boundary. In physics, this theory is conjectured to describe the scaling limit of loop models such as the Potts and $O(n)$ models. To define it mathematically, the curvature terms require a detailed analysis of the topology, and the potential terms are defined using the imaginary Guassian Multiplicative Chaos (GMC). We prove that the resulting probabilistic path integral satisfies the axioms of CFT, including Segal's gluing axioms. This work provides the foundation for future studies of boundary CILT and will also help with the understanding of CILT.

math-ph↗

arXiv2025

InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research

AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. It comprises 20 tasks spanning Data Construction, Filtering, Augmentation, Loss Design, Reward Design, and Scaffold Construction, which require runnable artifacts and assessment of correctness, performance, output quality, and uncertainty. To support agent operation, we develop ResearchGym, a research environment offering rich action spaces, distributed and long-horizon execution, asynchronous monitoring, and snapshot saving. We also implement a lightweight ReAct agent that couples explicit reasoning with executable planning using frontier models such as Claude-4, GPT-5, GLM-4.5, and Kimi-K2. Our experiments demonstrate that while frontier models show promise in code-driven research tasks, they struggle with fragile algorithm-related tasks and long-horizon decision making, such as impatience, poor resource management, and overreliance on template-based reasoning. Furthermore, agents require over 11 hours to achieve their best performance on InnovatorBench, underscoring the benchmark's difficulty and showing the potential of InnovatorBench to be the next generation of code-based research benchmark.

cs.AI↗

arXiv2025

Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized tasks remains challenging. Current methods primarily fall into two categories. The first relies on dense human annotations through behavior cloning, which is prohibitively expensive for long-horizon tasks that can take days or months. The second depends on outcome-driven sampling, which often collapses due to the rarity of valid positive trajectories on domain-specialized tasks. We introduce Apollo, a sampling framework that integrates asynchronous human guidance with action-level data filtering. Instead of requiring annotators to shadow every step, Apollo allows them to intervene only when the agent drifts from a promising trajectory, by providing prior knowledge, strategic advice, etc. This lightweight design makes it possible to sustain interactions for over 30 hours and produces valuable trajectories at a lower cost. Apollo then applies supervision control to filter out sub-optimal actions and prevent error propagation. Together, these components enable reliable and effective data collection in long-horizon environments. To demonstrate the effectiveness of Apollo, we evaluate it using InnovatorBench. Our experiments show that when applied to train the GLM-4.5 model on InnovatorBench, Apollo achieves more than a 50% improvement over the untrained baseline and a 28% improvement over a variant trained without human interaction. These results highlight the critical role of human-in-the-loop sampling and the robustness of Apollo's design in handling long-horizon, domain-specialized tasks.

cs.AI↗

arXiv2025

A Large Scale Study of AI-based Binary Function Similarity Detection Techniques for Security Researchers and Practitioners

Binary Function Similarity Detection (BFSD) is a foundational technique in software security, underpinning a wide range of applications including vulnerability detection, malware analysis. Recent advances in AI-based BFSD tools have led to significant performance improvements. However, existing evaluations of these tools suffer from three key limitations: a lack of in-depth analysis of performance-influencing factors, an absence of realistic application analysis, and reliance on small-scale or low-quality datasets. In this paper, we present the first large-scale empirical study of AI-based BFSD tools to address these gaps. We construct two high-quality and diverse datasets: BinAtlas, comprising 12,453 binaries and over 7 million functions for capability evaluation; and BinAres, containing 12,291 binaries and 54 real-world 1-day vulnerabilities for evaluating vulnerability detection performance in practical IoT firmware settings. Using these datasets, we evaluate nine representative BFSD tools, analyze the challenges and limitations of existing BFSD tools, and investigate the consistency among BFSD tools. We also propose an actionable strategy for combining BFSD tools to enhance overall performance (an improvement of 13.4%). Our study not only advances the practical adoption of BFSD tools but also provides valuable resources and insights to guide future research in scalable and automated binary similarity detection.

cs.CR↗