arXiv subjects

Yifei Duan

Publications and source records attributed to Yifei Duan.

At least 19 recordsLinked to original sources

arXiv2025

Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families

A significant connection exists between the controllability of dynamical systems and the approximation capabilities of neural networks, where residual networks and vanilla feedforward neural networks can both be regarded as numerical discretizations of the flow maps of dynamical systems. Leveraging the expressive power of neural networks, prior works have explored various control families $\mathcal{F}$ that enable the flow maps of dynamical systems to achieve either the universal approximation property (UAP) or the universal interpolation property (UIP). For example, the control family $\mathcal{F}_\text{ass}({\mathrm{ReLU}})$, consisting of affine maps together with a specific nonlinear function ReLU, achieves UAP; while the affine-invariant nonlinear control family $\mathcal{F}_{\mathrm{aff}}(f)$ containing a nonlinear function $f$ achieves UIP. However, UAP and UIP are generally not equivalent, and thus typically need to be studied separately with different techniques. In this paper, we investigate more general control families, including $\mathcal{F}_\text{ass}(f)$ with nonlinear functions $f$ beyond ReLU, the diagonal affine-invariant family $\mathcal{F}_{\mathrm{diag}}(f)$, and UAP for orientation-preserving diffeomorphisms under the uniform norm. We show that in certain special cases, UAP and UIP are indeed equivalent, whereas in the general case, we introduce the notion of local UIP (a substantially weaker version of UIP) and prove that the combination of UAP and local UIP implies UIP. In particular, the control family $\mathcal{F}_\text{ass}({\mathrm{ReLU}})$ achieves the UIP.

math.OC↗

arXiv2025

DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning

The synthesis of crystalline materials, such as zeolites, remains a significant challenge due to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Considering the one-to-many relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes spanning 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn achieves state-of-the-art performance by capturing the multi-modal nature of structure-synthesis relationships. We apply DiffSyn to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/Al$_{\text{ICP}}$ of 19.0, which is expected to improve thermal stability and is higher than that of any previously recorded.

cond-mat.mtrl-sci↗

arXiv2025

Granular segregation across flow geometries: a closure model for the particle segregation velocity

Predicting particle segregation has remained challenging due to the lack of a general model for the segregation velocity that is applicable across a range of granular flow geometries. Here, a segregation velocity model for dense granular flows is developed by exploiting momentum balance and recent advances in particle-scale modelling of the segregation driving and drag forces over a wide range of particle concentrations, size and density ratios, and flow conditions. This model is shown to correctly predict particle segregation velocity in a diverse set of idealized and natural granular flow geometries simulated using the discrete element method. When incorporated in the well-established advection-diffusion-segregation formulation, the model has the potential to accurately capture segregation phenomena in many relevant industrial application and geophysical settings.

cond-mat.soft↗

arXiv2025

Intelligent Task Scheduling for Microservices via A3C-Based Reinforcement Learning

To address the challenges of high resource dynamism and intensive task concurrency in microservice systems, this paper proposes an adaptive resource scheduling method based on the A3C reinforcement learning algorithm. The scheduling problem is modeled as a Markov Decision Process, where policy and value networks are jointly optimized to enable fine-grained resource allocation under varying load conditions. The method incorporates an asynchronous multi-threaded learning mechanism, allowing multiple agents to perform parallel sampling and synchronize updates to the global network parameters. This design improves both policy convergence efficiency and model stability. In the experimental section, a real-world dataset is used to construct a scheduling scenario. The proposed method is compared with several typical approaches across multiple evaluation metrics, including task delay, scheduling success rate, resource utilization, and convergence speed. The results show that the proposed method delivers high scheduling performance and system stability in multi-task concurrent environments. It effectively alleviates the resource allocation bottlenecks faced by traditional methods under heavy load, demonstrating its practical value for intelligent scheduling in microservice systems.

cs.DC↗

arXiv2025

A Minimal Control Family of Dynamical Systems for Universal Approximation

The universal approximation property (UAP) holds a fundamental position in deep learning, as it provides a theoretical foundation for the expressive power of neural networks. It is widely recognized that a composition of linear and nonlinear functions, such as the rectified linear unit (ReLU) activation function, can approximate continuous functions on compact domains. In this paper, we extend this efficacy to a scenario containing dynamical systems with controls. We prove that the control family $\mathcal{F}_1$ containing all affine maps and the nonlinear ReLU map is sufficient for generating flow maps that can approximate orientation-preserving (OP) diffeomorphisms on any compact domain. Since $\mathcal{F}_1$ contains only one nonlinear function and the UAP does not hold if we remove the nonlinear function, we call $\mathcal{F}_1$ a minimal control family for the UAP. On this basis, several mild sufficient conditions, such as affine invariance, are established for the control family and discussed. Our results reveal an underlying connection between the approximation power of neural networks and control systems and could provide theoretical guidance for examining the approximation power of flow-based models.

eess.SY↗

arXiv2025

Dynamic Operating System Scheduling Using Double DQN: A Reinforcement Learning Approach to Task Optimization

In this paper, an operating system scheduling algorithm based on Double DQN (Double Deep Q network) is proposed, and its performance under different task types and system loads is verified by experiments. Compared with the traditional scheduling algorithm, the algorithm based on Double DQN can dynamically adjust the task priority and resource allocation strategy, thus improving the task completion efficiency, system throughput, and response speed. The experimental results show that the Double DQN algorithm has high scheduling performance under light load, medium load and heavy load scenarios, especially when dealing with I/O intensive tasks, and can effectively reduce task completion time and system response time. In addition, the algorithm also shows high optimization ability in resource utilization and can intelligently adjust resource allocation according to the system state, avoiding resource waste and excessive load. Future studies will further explore the application of the algorithm in more complex systems, especially scheduling optimization in cloud computing and large-scale distributed environments, combining factors such as network latency and energy efficiency to improve the overall performance and adaptability of the algorithm.

cs.LG↗

arXiv2025

Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper focuses on improving the performance of pre-trained language models in zero-shot settings through a simple and easily implementable method. We propose a novel backward attention mechanism to enhance contextual information encoding. Evaluated on the Chinese Massive Text Embedding Benchmark (C-MTEB), our approach achieves significant improvements across multiple tasks, providing valuable insights for advancing zero-shot learning capabilities.

cs.CL↗

arXiv2025

Automated UI Interface Generation via Diffusion Models: Enhancing Personalization and Efficiency

This study proposes a UI interface generation method based on a diffusion model, aiming to achieve high-quality, diversified, and personalized interface design through generative artificial intelligence technology. The diffusion model is based on its step-by-step denoising generation process. By combining the conditional generation mechanism, design optimization module, and user feedback mechanism, the model can generate a UI interface that meets the requirements based on multimodal inputs such as text descriptions and sketches provided by users. In the study, a complete experimental evaluation framework was designed, and mainstream generation models (such as GAN, VAE, DALL E, etc.) were selected for comparative experiments. The generation results were quantitatively analyzed from indicators such as PSNR, SSIM, and FID. The results show that the model proposed in this study is superior to other models in terms of generation quality and user satisfaction, especially in terms of logical clarity of information transmission and visual aesthetics. The ablation experiment further verifies the key role of conditional generation and design optimization modules in improving interface quality. This study provides a new technical path for UI design automation and lays the foundation for the intelligent and personalized development of human-computer interaction interfaces. In the future, the application potential of the model in virtual reality, game design, and other fields will be further explored.

cs.HC↗

arXiv2025

Unsupervised Detection of Fraudulent Transactions in E-commerce Using Contrastive Learning

With the rapid development of e-commerce, e-commerce platforms are facing an increasing number of fraud threats. Effectively identifying and preventing these fraudulent activities has become a critical research problem. Traditional fraud detection methods typically rely on supervised learning, which requires large amounts of labeled data. However, such data is often difficult to obtain, and the continuous evolution of fraudulent activities further reduces the adaptability and effectiveness of traditional methods. To address this issue, this study proposes an unsupervised e-commerce fraud detection algorithm based on SimCLR. The algorithm leverages the contrastive learning framework to effectively detect fraud by learning the underlying representations of transaction data in an unlabeled setting. Experimental results on the eBay platform dataset show that the proposed algorithm outperforms traditional unsupervised methods such as K-means, Isolation Forest, and Autoencoders in terms of accuracy, precision, recall, and F1 score, demonstrating strong fraud detection capabilities. The results confirm that the SimCLR-based unsupervised fraud detection method has broad application prospects in e-commerce platform security, improving both detection accuracy and robustness. In the future, with the increasing scale and diversity of datasets, the model's performance will continue to improve, and it could be integrated with real-time monitoring systems to provide more efficient security for e-commerce platforms.

cs.LG↗

arXiv2025

Baichuan-M1: Pushing the Medical Capability of Large Language Models

The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce. In particular, the development of highly efficient and practical LLMs for the medical domain is challenging due to the complexity of medical knowledge and the limited availability of high-quality data. To bridge this gap, we introduce Baichuan-M1, a series of large language models specifically optimized for medical applications. Unlike traditional approaches that simply continue pretraining on existing models or apply post-training to a general base model, Baichuan-M1 is trained from scratch with a dedicated focus on enhancing medical capabilities. Our model is trained on 20 trillion tokens and incorporates a range of effective training methods that strike a balance between general capabilities and medical expertise. As a result, Baichuan-M1 not only performs strongly across general domains such as mathematics and coding but also excels in specialized medical fields. We have open-sourced Baichuan-M1-14B, a mini version of our model, which can be accessed through the following links.

cs.CL↗

arXiv2025

Baichuan-Omni-1.5 Technical Report

We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks.

cs.CL↗

arXiv2024

In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning

We applied few-shot in-context learning on the OPT-1.3B model for the natural language inference task and employed knowledge distillation to internalize the context information, reducing model parameter from 1.3B to 125M and achieving a size reduction from 2.5GB to 0.25GB. Compared to using in-context learning alone on similarly sized models, this context distillation approach achieved a nearly 50% improvement in out-of-domain accuracy, demonstrating superior knowledge transfer capabilities over prompt-based methods. Furthermore, this approach reduced memory consumption by up to 60% while delivering a 20% improvement in out-of-domain accuracy compared to conventional pattern-based fine-tuning.

cs.CL↗

arXiv2024

Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems

Deep learning has made significant applications in the field of data science and natural science. Some studies have linked deep neural networks to dynamic systems, but the network structure is restricted to the residual network. It is known that residual networks can be regarded as a numerical discretization of dynamic systems. In this paper, we back to the classical network structure and prove that the vanilla feedforward networks could also be a numerical discretization of dynamic systems, where the width of the network is equal to the dimension of the input and output. Our proof is based on the properties of the leaky-ReLU function and the numerical technique of splitting method to solve differential equations. Our results could provide a new perspective for understanding the approximation properties of feedforward neural networks.

cs.LG↗

arXiv2024

Crater-shaped Enrichment of $\mathrm{V}_\mathrm{Si}$ Color Centers in $4H$-SiC using Single-Pulse Near-Infrared Femtosecond Laser Processing

Currently, Si vacancy ($\mathrm{V}_\mathrm{Si}$) color centers in SiC are of significant interest due to their potential applications in quantum sensing and quantum communication. Meanwhile, the qualities of laser-induced color centers are well guaranteed. Femtosecond laser processing suffices for increasing the yield of $\mathrm{V}_\mathrm{Si}$ color centers in bulk materials and forms crater-shaped enriched regions on the surface. However, there is a notable absence of existing simulation methods to explain the mechanisms behind laser-assisted $\mathrm{V}_\mathrm{Si}$ color center generation. In this work, we design a three-dimensional molecular dynamics (3D-MD) model using an integral hemi-ellipsoidal shell mathematical model to simulate the interaction of Gaussian laser beams with bulk materials. Furthermore, we calculate the transmittance, absorption coefficient, refractive index, and reflectivity of $4H$-SiC. Then, the absorptance of a 1030 nm laser in 350 μm-thick $4H$-SiC material is abtained to simulate the energy loss during the actual processing. Finally, the study analyzes the movement trajectories of $\mathrm{V}_\mathrm{Si}$ color centers and explains the source of $\mathrm{V}_\mathrm{Si}$ on the surface. This analysis explains the reasons for the enrichment of color centers in the crater-shaped regions formed after laser deposition. Our work provides an effective 3D-MD modeling approach to study the processing mechanisms of laser interaction with semiconductor materials, offering insights into efficient $\mathrm{V}_\mathrm{Si}$ color center creation processes.

physics.optics↗

arXiv2024

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation

The study of universal approximation properties (UAP) for neural networks (NN) has a long history. When the network width is unlimited, only a single hidden layer is sufficient for UAP. In contrast, when the depth is unlimited, the width for UAP needs to be not less than the critical width $w^*_{\min}=\max(d_x,d_y)$, where $d_x$ and $d_y$ are the dimensions of the input and output, respectively. Recently, \cite{cai2022achieve} shows that a leaky-ReLU NN with this critical width can achieve UAP for $L^p$ functions on a compact domain ${K}$, \emph{i.e.,} the UAP for $L^p({K},\mathbb{R}^{d_y})$. This paper examines a uniform UAP for the function class $C({K},\mathbb{R}^{d_y})$ and gives the exact minimum width of the leaky-ReLU NN as $w_{\min}=\max(d_x,d_y)+Δ(d_x, d_y)$, where $Δ(d_x, d_y)$ is the additional dimensions for approximating continuous functions with diffeomorphisms via embedding. To obtain this result, we propose a novel lift-flow-discretization approach that shows that the uniform UAP has a deep connection with topological theory.

cs.LG↗

arXiv2023

General model for segregation forces in flowing granular mixtures

Particle segregation in dense flowing size-disperse granular mixtures is driven by gravity and shear, but predicting the associated segregation force due to both effects has remained an unresolved challenge. Here, a model of the combined gravity- and kinematics-induced segregation force on a single intruder particle is integrated with a model of the concentration dependence of the gravity-induced segregation force. The result is a general model of the net particle segregation force in flowing size-bidisperse granular mixtures. Using discrete element method simulations for comparison, the model correctly predicts the segregation force for a variety of mixture concentrations and flow conditions in both idealized and natural shear flows.

cond-mat.soft↗

arXiv2022

Designing minimally-segregating granular mixtures for gravity-driven surface flows

In dense flowing bidisperse particle mixtures varying in size or density alone, smaller particles sink (driven by percolation) and lighter particles rise (driven by buoyancy). But when the particle species differ from each other in both size and density, percolation and buoyancy can either enhance (large/light and small/heavy) or oppose (large/heavy and small/light) each other. In the latter case, a local equilibrium condition can exist in which the two segregation mechanisms balance and particles remain mixed: this allows the design of minimally-segregating mixtures by specifying particle size ratio, density ratio, and mixture concentration. Using experimentally validated DEM simulations, we show that mixtures specified by the methodology remain relatively well-mixed in the thin rapid surface flows characteristic of heaps and tumblers commonly used in industry. Furthermore, minimally-segregating particle mixtures prepared in a fully segregated state in a tumbler mix over time and eventually reach a state of nearly uniform species concentration.

cond-mat.soft↗

arXiv2021

Segregation forces in dense granular flows: Closing the gap from single intruders to mixtures

Using simulations and a virtual-spring-based approach, we measure the segregation force, Fseg, over a range of size-bidisperse mixture concentrations, particle size ratios, and shear rates to develop a model for Fseg that extends its applicability from the well-studied non-interacting intruders regime to finite-concentration mixtures where cooperative phenomena occur. The model predicts the concentration below which the single intruder assumption applies and provides an accurate description of the pressure partitioning between species.

cond-mat.soft↗