arXiv subjects

Chen Yang

Publications and source records attributed to Chen Yang.

At least 163 records · Page 9Linked to original sources

arXiv2025

A Survey of Reinforcement Learning for Software Engineering

Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the rising demand for automation have motivated researchers to apply RL to a broad range of tasks, from software design and development to quality assurance and maintenance. Despite growing research in RL-for-SE, there remains a lack of a comprehensive and systematic survey of this evolving field. To address this gap, we reviewed 115 peer-reviewed studies published across 22 premier SE venues since the introduction of DRL. We conducted a comprehensive analysis of publication trends, categorized SE topics and RL algorithms, and examined key factors such as dataset usage, model design and optimization, and evaluation practices. Furthermore, we identified open challenges and proposed future research directions to guide and inspire ongoing work in this evolving area. To summarize, this survey offers the first systematic mapping of RL applications in software engineering, aiming to support both researchers and practitioners in navigating the current landscape and advancing the field. Our artifacts are publicly available: https://github.com/KaiWei-Lin-lanina/RL4SE.

cs.SE↗

arXiv2025

Miniaturized optically-generated Bessel beam ultrasound for volumetric transcranial brain stimulation

Non-invasive stimulation of small, variably shaped brain sub-regions is crucial for advancing our understanding of brain functions. Current ultrasound neuromodulation faces two significant trade-offs when targeting brain sub-regions: miniaturization versus volumetric control and spatial resolution versus transcranial capability. Here, we present an optically-generated Bessel beam ultrasound (OBUS) device designed to overcome these limitations. This 2.33 mm-diameter miniaturized device delivers a column-shaped field achieving a lateral resolution of 152 um and an axial resolution of 1.93 mm, targeting brain sub-regions with an elongated volume of tissue activation. Immunofluorescence imaging of mouse brain slices confirms its ability to stimulate cells at a depth of 2.2 mm. Additionally, OBUS outperforms conventional Gaussian ultrasound in transcranial transmission efficiency and beam shape preservation. Electrophysiological recordings and functional MRI captured rodent brain responses evoked by OBUS, demonstrating OBUS's ability to non-invasively activate neural circuits in intact brains. This technology offers new possibilities for studying brain functions with precision and volumetric control.

q-bio.NC↗

arXiv2025

Normalized solutions for the NLS equation with mixed fractional Laplacians and combined nonlinearities

We look for normalized solutions to the nonlinear Schrödinger equation with mixed fractional Laplacians and combined nonlinearities $$ \left\{\begin{array}{ll} (-Δ)^{s_{1}} u+(-Δ)^{s_{2}} u=λu+μ|u|^{q-2}u+|u|^{p-2}u \ \text{in}\;{\mathbb{R}^{N}}, \\[0.1cm] \int_{\mathbb{R}^{N}}|u|^2\mathrm dx=a^2, \end{array} \right. $$ where $N\geq 2,\;0 0$ and $λ\in\mathbb R$ appears as an unknown Lagrange multiplier. We mainly focus on some special cases, including fractional Sobolev subcritical or critical exponent. More precisely, for $2<q<2+\frac{4s_2}{N}<2+\frac{4s_1}{N}<p<2_{s_1}^{\ast}:=\frac{2N}{N-2s_1}$, we prove that the above problem has at least two solutions: a ground state with negative energy and a solution of mountain pass type with positive energy. For $2<q<2+\frac{4s_2}{N}$ and $p=2_{s_1}^{\ast}$, we also obtain the existence of ground states. Our results extend some previous ones of Chergui et al. (Calc. Var. Partial Differ. Equ., 2023) and Luo et al. (Adv. Nonlinear Stud., 2022).

math.AP↗

arXiv2025

Performance of diverse evaluation metrics in NLP-based assessment and text generation of consumer complaints

Machine learning (ML) has significantly advanced text classification by enabling automated understanding and categorization of complex, unstructured textual data. However, accurately capturing nuanced linguistic patterns and contextual variations inherent in natural language, particularly within consumer complaints, remains a challenge. This study addresses these issues by incorporating human-experience-trained algorithms that effectively recognize subtle semantic differences crucial for assessing consumer relief eligibility. Furthermore, we propose integrating synthetic data generation methods that utilize expert evaluations of generative adversarial networks and are refined through expert annotations. By combining expert-trained classifiers with high-quality synthetic data, our research seeks to significantly enhance machine learning classifier performance, reduce dataset acquisition costs, and improve overall evaluation metrics and robustness in text classification tasks.

cs.CL↗

arXiv2025

Non-Concave Utility Maximization with Transaction Costs

This paper studies a finite-horizon portfolio selection problem with non-concave terminal utility and proportional transaction costs, in which the commonly used concavification principle for terminal value is no longer applicable. We establish a proper theoretical characterization of this problem via a two-step procedure. First, we examine the asymptotic terminal behavior of the value function, which implies that any transaction close to maturity only provides a marginal contribution to the utility. Second, we establish the theoretical foundation in terms of the discontinuous viscosity solution, incorporating the proper characterization of the terminal condition. Via extensive numerical analyses involving several types of utility functions, we find that the introduction of transaction costs into non-concave utility maximization problems can make it optimal for investors to hold on to a larger long position in the risky asset compared to the frictionless case, or hold on to a large short position in the risky asset despite a positive risk premium.

q-fin.MF↗

arXiv2025

Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing

De novo peptide sequencing is a fundamental computational technique for ascertaining amino acid sequences of peptides directly from tandem mass spectrometry data, eliminating the need for reference databases. Cutting-edge models usually encode the observed mass spectra into latent representations from which peptides are predicted autoregressively. However, the issue of missing fragmentation, attributable to factors such as suboptimal fragmentation efficiency and instrumental constraints, presents a formidable challenge in practical applications. To tackle this obstacle, we propose a novel computational paradigm called \underline{\textbf{L}}atent \underline{\textbf{I}}mputation before \underline{\textbf{P}}rediction (LIPNovo). LIPNovo is devised to compensate for missing fragmentation information within observed spectra before executing the final peptide prediction. Rather than generating raw missing data, LIPNovo performs imputation in the latent space, guided by the theoretical peak profile of the target peptide sequence. The imputation process is conceptualized as a set-prediction problem, utilizing a set of learnable peak queries to reason about the relationships among observed peaks and directly generate the latent representations of theoretical peaks through optimal bipartite matching. In this way, LIPNovo manages to supplement missing information during inference and thus boosts performance. Despite its simplicity, experiments on three benchmark datasets demonstrate that LIPNovo outperforms state-of-the-art methods by large margins. Code is available at \href{https://github.com/usr922/LIPNovo}{https://github.com/usr922/LIPNovo}.

cs.CE↗

arXiv2025

BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling

In recent years, foundational models have revolutionized the fields of language and vision, demonstrating remarkable abilities in understanding and generating complex data; however, similar advances in user behavior modeling have been limited, largely due to the complexity of behavioral data and the challenges involved in capturing intricate temporal and contextual relationships in user activities. To address this, we propose BehaveGPT, a foundational model designed specifically for large-scale user behavior prediction. Leveraging transformer-based architecture and a novel pretraining paradigm, BehaveGPT is trained on vast user behavior datasets, allowing it to learn complex behavior patterns and support a range of downstream tasks, including next behavior prediction, long-term generation, and cross-domain adaptation. Our approach introduces the DRO-based pretraining paradigm tailored for user behavior data, which improves model generalization and transferability by equitably modeling both head and tail behaviors. Extensive experiments on real-world datasets demonstrate that BehaveGPT outperforms state-of-the-art baselines, achieving more than a 10% improvement in macro and weighted recall, showcasing its ability to effectively capture and predict user behavior. Furthermore, we measure the scaling law in the user behavior domain for the first time on the Honor dataset, providing insights into how model performance scales with increased data and parameter sizes.

cs.IR↗

arXiv2025

Pricing Model for Data Assets in Investment-Consumption Framework with Ambiguity

Data assets are data commodities that have been processed, produced, priced, and traded based on actual demand. Reasonable pricing mechanism for data assets is essential for developing the data market and realizing their value. Most existing literature approaches data asset pricing from the seller's perspective, focusing on data properties and collection costs, however, research from the buyer's perspective remains scarce. This gap stems from the nature of data assets: their value lies not in direct revenue generation but in providing informational advantages that enable enhanced decision-making and excess returns. This paper addresses this gap by developing a pricing model based on the informational value of data assets from the buyer's perspective. We determine data asset prices through an implicit function derived from the value functions in two robust investment-consumption problems under ambiguity markets via the indifference pricing principle. By the existing research results, we simplify the value function, using mathematical analysis and differential equation theory, we derive general expressions for data assets price and explore their properties under various conditions. Furthermore, we derive the explicit pricing formulas for specific scenarios and provide numerical illustration to describe how to use our pricing model.

q-fin.MF↗

arXiv2025

Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of CTRL remains limited, especially in settings with general function approximation. In this work, we propose a model-based CTRL algorithm that achieves both sample and computational efficiency. Our approach leverages optimism-based confidence sets to establish the first sample complexity guarantee for CTRL with general function approximation, showing that a near-optimal policy can be learned with a suboptimality gap of $\tilde{O}(\sqrt{d_{\mathcal{R}} + d_{\mathcal{F}}}N^{-1/2})$ using $N$ measurements, where $d_{\mathcal{R}}$ and $d_{\mathcal{F}}$ denote the distributional Eluder dimensions of the reward and dynamic functions, respectively, capturing the complexity of general function approximation in reinforcement learning. Moreover, we introduce structured policy updates and an alternative measurement strategy that significantly reduce the number of policy updates and rollouts while maintaining competitive sample efficiency. We implemented experiments to backup our proposed algorithms on continuous control tasks and diffusion model fine-tuning, demonstrating comparable performance with significantly fewer policy updates and rollouts.

cs.LG↗

arXiv2025

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each question in MMAR is hierarchically categorized across four reasoning layers: Signal, Perception, Semantic, and Cultural, with additional sub-categories within each layer to reflect task diversity and complexity. To further foster research in this area, we annotate every question with a Chain-of-Thought (CoT) rationale to promote future advancements in audio reasoning. Each item in the benchmark demands multi-step deep reasoning beyond surface-level understanding. Moreover, a part of the questions requires graduate-level perceptual and domain-specific knowledge, elevating the benchmark's difficulty and depth. We evaluate MMAR using a broad set of models, including Large Audio-Language Models (LALMs), Large Audio Reasoning Models (LARMs), Omni Language Models (OLMs), Large Language Models (LLMs), and Large Reasoning Models (LRMs), with audio caption inputs. The performance of these models on MMAR highlights the benchmark's challenging nature, and our analysis further reveals critical limitations of understanding and reasoning capabilities among current models. We hope MMAR will serve as a catalyst for future advances in this important but little-explored area.

cs.SD↗

arXiv2025

Physics-informed Deep Diffusion MRI Reconstruction with Synthetic Data: Break Training Data Bottleneck in Artificial Intelligence

Diffusion magnetic resonance imaging (MRI) is the only imaging modality for non-invasive movement detection of in vivo water molecules, with significant clinical and research applications. Diffusion weighted imaging (DWI) MRI acquired by multi-shot techniques can achieve higher resolution, better signal-to-noise ratio, and lower geometric distortion than single-shot, but suffers from inter-shot motion-induced artifacts. These artifacts cannot be removed prospectively, leading to the absence of artifact-free training labels. Thus, the potential of deep learning in multi-shot DWI reconstruction remains largely untapped. To break the training data bottleneck, here, we propose a Physics-Informed Deep DWI reconstruction method (PIDD) to synthesize high-quality paired training data by leveraging the physical diffusion model (magnitude synthesis) and inter-shot motion-induced phase model (motion phase synthesis). The network is trained only once with 100,000 synthetic samples, achieving encouraging results on multiple realistic in vivo data reconstructions. Advantages over conventional methods include: (a) Better motion artifact suppression and reconstruction stability; (b) Outstanding generalization to multi-scenario reconstructions, including multi-resolution, multi-b-value, multi-under-sampling, multi-vendor, and multi-center; (c) Excellent clinical adaptability to patients with verifications by seven experienced doctors (p<0.001). In conclusion, PIDD presents a novel deep learning framework by exploiting the power of MRI physics, providing a cost-effective and explainable way to break the data bottleneck in deep learning medical imaging.

eess.IV↗

arXiv2025

Intra-Class Correlation Coefficient Ignorable Clustered Randomized Trials for Detecting Treatment Effect Heterogeneity

Accurately estimating the intra-class correlation coefficient (ICC) is crucial for adequately powering clustered randomized trials (CRTs). Challenges arise due to limited prior data on the specific outcome within the target population, making accurate ICC estimation difficult. Furthermore, ICC can vary significantly across studies, even for the same outcome, influenced by factors like study design, participant characteristics, and the specific intervention. Power calculations are extremely sensitive to ICC assumptions. Minor variation in the assumed ICC can lead to large differences in the number of clusters needed, potentially impacting trial feasibility and cost. This paper identifies a special class of CRTs aiming to detect the treatment effect heterogeneity, wherein the ICC can be completely disregarded in calculation of power and sample size. This result offers a solution for research projects lacking preliminary estimates of the ICC or facing challenges in their estimate. Moreover, this design facilitates power improvement through increasing the cluster sizes rather than the number of clusters, making it particular advantageous in the situations where expanding the number of clusters is difficult or costly. This paper provides a rigorous theoretical foundation for this class of ICC-ignorable CRTs, including mathematical proofs and practical guidance for implementation. We also present illustrative examples to demonstrate the practical implications of this approach in various research contexts in healthcare delivery.

stat.ME↗

arXiv2025

DecETT: Accurate App Fingerprinting Under Encrypted Tunnels via Dual Decouple-based Semantic Enhancement

Due to the growing demand for privacy protection, encrypted tunnels have become increasingly popular among mobile app users, which brings new challenges to app fingerprinting (AF)-based network management. Existing methods primarily transfer traditional AF methods to encrypted tunnels directly, ignoring the core obfuscation and re-encapsulation mechanism of encrypted tunnels, thus resulting in unsatisfactory performance. In this paper, we propose DecETT, a dual decouple-based semantic enhancement method for accurate AF under encrypted tunnels. Specifically, DecETT improves AF under encrypted tunnels from two perspectives: app-specific feature enhancement and irrelevant tunnel feature decoupling.Considering the obfuscated app-specific information in encrypted tunnel traffic, DecETT introduces TLS traffic with stronger app-specific information as a semantic anchor to guide and enhance the fingerprint generation for tunnel traffic. Furthermore, to address the app-irrelevant tunnel feature introduced by the re-encapsulation mechanism, DecETT is designed with a dual decouple-based fingerprint enhancement module, which decouples the tunnel feature and app semantic feature from tunnel traffic separately, thereby minimizing the impact of tunnel features on accurate app fingerprint extraction. Evaluation under five prevalent encrypted tunnels indicates that DecETT outperforms state-of-the-art methods in accurate AF under encrypted tunnels, and further demonstrates its superiority under tunnels with more complicated obfuscation. \textit{Project page: \href{https://github.com/DecETT/DecETT}{https://github.com/DecETT/DecETT}}

cs.CR↗

arXiv2025

Symmetry breaking of large-amplitude parametric oscillations in few-layer graphene nanomechanical resonators

Graphene nanomechanical resonators are well suited for the study of parametric oscillations. Their large frequency tunability and their pronounced nonlinearities enable an efficient modulation of their resonant frequencies. Here, we present measurements of the response of few-layer graphene nanomechanical resonators, each driven by a large parametric pump at frequency $2ω$ and a weak external drive at $ω$, where $ω$ is set near the mechanical resonant frequency $ω_0$. The pump actuates the resonator beyond the threshold for large-amplitude parametric oscillations, while the drive breaks the symmetry between the parametric phase states. By increasing and decreasing a gate voltage to detune $ω_0$ in the presence of the pump and the drive, we observe a double hysteresis in the response. The double hysteresis reveals the existence of two possible large-amplitude vibrational states whose phase difference is nearly $π$ radians. We deterministically prepare the resonator in either one of these states by cycling the gate voltage. We measure the stationary occupation probabilities of the two states in the presence of a white Gaussian force noise, and find that they strongly depend on the amplitude and on the phase of the external drive. The phase states of parametric oscillations with broken amplitude symmetry can be mapped to biased bi-modal degrees of freedom, such as Ising spins in an external magnetic field. Therefore, they hold promise as units of binary information.

cond-mat.mes-hall↗

arXiv2025

SF-Speech: Straightened Flow for Zero-Shot Voice Clone

Recently, neural ordinary differential equations (ODE) models trained with flow matching have achieved impressive performance on the zero-shot voice clone task. Nevertheless, postulating standard Gaussian noise as the initial distribution of ODE gives rise to numerous intersections within the fitted targets of flow matching, which presents challenges to model training and enhances the curvature of the learned generated trajectories. These curved trajectories restrict the capacity of ODE models for generating desirable samples with a few steps. This paper proposes SF-Speech, a novel voice clone model based on ODE and in-context learning. Unlike the previous works, SF-Speech adopts a lightweight multi-stage module to generate a more deterministic initial distribution for ODE. Without introducing any additional loss function, we effectively straighten the curved reverse trajectories of the ODE model by jointly training it with the proposed module. Experiment results on datasets of various scales show that SF-Speech outperforms the state-of-the-art zero-shot TTS methods and requires only a quarter of the solver steps, resulting in a generation speed approximately 3.7 times that of Voicebox and E2 TTS. Audio samples are available at the demo page\footnote{[Online] Available: https://lixuyuan102.github.io/Demo/}.

cs.SD↗

arXiv2025

Mass concentration of minimizers for $L^2$-subcritical Kirchhoff energy functional in bounded domains

We are concerned with $L^2$-constraint minimizers for the Kirchhoff functional $$ E_b(u)=\int_Ω|\nabla u|^2\mathrm{d}x+\frac{b}{2}\left(\int_Ω|\nabla u|^2\mathrm{d}x\right)^2+\int_ΩV(x)u^2\mathrm{d}x-\fracβ{2}\int_Ω|u|^4\mathrm{d}x, $$ where $b>0$, $β>0$ and $V(x)$ is a trapping potential in a bounded domain $Ω$ of $\mathbb R^2$. As is well known that minimizers exist for any $b>0$ and $β>0$, while the minimizers do not exist for $b=0$ and $β\geqβ^*$, where $β^*=\int_{\mathbb R^2}|Q|^2\mathrm{d}x$ and $Q$ is the unique positive solution of $-Δu+u-u^3=0$ in $\mathbb R^2$. In this paper, we show that for $β=β^*$, the energy converges to 0, but for $β>β^*$, the minimal energy will diverge to $-\infty$ as $b\searrow0$. Further, we give the refined limit behaviors and energy estimates of minimizers as $b\searrow0$ for $β=β^*$ or $β>β^*$. For both cases, we obtain that the mass of minimizers concentrates either at an inner point or near the boundary of $Ω$, depending on whether $V(x)$ attains its flattest global minimum at an inner point of $Ω$ or not. Meanwhile, we find an interesting phenomenon that the blow-up rate when the minimizers concentrate near the boundary of $Ω$ is faster than concentration at an interior point if $β=β^*$, but the blow-up rates remain consistent if $β>β^*$.

math.AP↗

arXiv2025

A Brain-Computer Interface Data Persistence System for Multi-Scenario and Multi-Modal Data: NeuroStore

With the rapid advancement of brain-computer interface (BCI) technology, the volume of physiological data generated in related research and applications has grown significantly. Data is a critical resource in BCI research and a key factor in the development of BCI technology, making efficient storage and management of this data increasingly vital. In the realm of research, ample data can facilitate the development of novel algorithms, which can be more accurately validated. In terms of applications, well-organized data can foster the emergence of new business opportunities, thereby maximizing the commercial value of the data. Currently, there are two major challenges in the storage and management of BCI data: providing different classification storage modes for multi-modal data, and adapting to varying application scenarios while improving storage strategies. To address these challenges, this study has developed the NeuroStore BCI data persistence system, which provides a general and easily scalable data model and can effectively handle multiple types of data storage. The system has a flexible distributed framework and can be widely applied to various scenarios. It has been utilized as the core support platform for efficient data storage and management services in the "BCI Controlled Robot Contest in World Robot Contest."

cs.DB↗

arXiv2025

Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation

As requirements drift with rapid iterations, agile development becomes the dominant paradigm. Goal-driven Requirements Elicitation (RE) is a pivotal yet challenging task in agile project development due to its heavy tangling with adaptive planning and efficient collaboration. Recently, AI agents have shown promising ability in supporting requirements analysis by saving significant time and effort for stakeholders. However, current research mainly focuses on functional RE, and research works have not been reported bridging the long journey from goal to user stories. Moreover, considering the cost of LLM facilities and the need for data and idea protection, privately hosted small-sized LLM should be further utilized in RE. To address these challenges, we propose Goal2Story, a multi-agent fleet that adopts the Impact Mapping (IM) framework while merely using cost-effective sLLMs for goal-driven RE. Moreover, we introduce a StorySeek dataset that contains over 1,000 user stories (USs) with corresponding goals and project context information, as well as the semi-automatic dataset construction method. For evaluation, we proposed two metrics: Factuality Hit Rate (FHR) to measure consistency between the generated USs with the dataset and Quality And Consistency Evaluation (QuACE) to evaluate the quality of the generated USs. Experimental results demonstrate that Goal2Story outperforms the baseline performance of the Super-Agent adopting powerful LLMs, while also showcasing the performance improvements in key metrics brought by CoT and Agent Profile to Goal2Story, as well as its exploration in identifying latent needs.

cs.SE↗