arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 631 records · Page 35Linked to original sources

arXiv2025

Spatio-Temporal Progressive Attention Model for EEG Classification in Rapid Serial Visual Presentation Task

As a type of multi-dimensional sequential data, the spatial and temporal dependencies of electroencephalogram (EEG) signals should be further investigated. Thus, in this paper, we propose a novel spatial-temporal progressive attention model (STPAM) to improve EEG classification in rapid serial visual presentation (RSVP) tasks. STPAM first adopts three distinct spatial experts to learn the spatial topological information of brain regions progressively, which is used to minimize the interference of irrelevant brain regions. Concretely, the former expert filters out EEG electrodes in the relative brain regions to be used as prior knowledge for the next expert, ensuring that the subsequent experts gradually focus their attention on information from significant EEG electrodes. This process strengthens the effect of the important brain regions. Then, based on the above-obtained feature sequence with spatial information, three temporal experts are adopted to capture the temporal dependence by progressively assigning attention to the crucial EEG slices. Except for the above EEG classification method, in this paper, we build a novel Infrared RSVP EEG Dataset (IRED) which is based on dim infrared images with small targets for the first time, and conduct extensive experiments on it. The results show that our STPAM can achieve better performance than all the compared methods.

cs.CV↗

arXiv2025

MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling

The concept of integrating physics-based and data-driven approaches has become popular for modeling sustainable energy systems. However, the existing literature mainly focuses on the data-driven surrogates generated to replace physics-based models. These models often trade accuracy for speed but lack the generalizability, adaptability, and interpretability inherent in physics-based models, which are often indispensable in modeling real-world dynamic systems for optimization and control purposes. We propose a novel machine learning architecture, termed model-integrated neural networks (MINN), that can learn the physics-based dynamics of general autonomous or non-autonomous systems consisting of partial differential-algebraic equations (PDAEs). The obtained architecture systematically solves an unsettled research problem in control-oriented modeling, i.e., how to obtain optimally simplified models that are physically insightful, numerically accurate, and computationally tractable simultaneously. We apply the proposed neural network architecture to model the electrochemical dynamics of lithium-ion batteries and show that MINN is extremely data-efficient to train while being sufficiently generalizable to previously unseen input data, owing to its underlying physical invariants. The MINN battery model has an accuracy comparable to the first principle-based model in predicting both the system outputs and any locally distributed electrochemical behaviors but achieves two orders of magnitude reduction in the solution time.

cs.LG↗

arXiv2025

A family of linear codes that are either non-GRS MDS codes or NMDS codes

Both maximum distance separable (MDS) codes that are not equivalent to generalized Reed-Solomon (GRS) codes (non-GRS MDS codes) and near MDS (NMDS) codes have nice applications in communication and storage systems. In this paper, we introduce and study a new family of linear codes involving their parameters, weight distributions, and self-orthogonal properties. We prove that such codes are either non-GRS MDS codes or NMDS codes, and hence, they can produce as many of the desired codes as possible. We also completely determine their weight distributions with the help of the solutions to some subset sum problems. A sufficient and necessary condition for such codes to be self-orthogonal is characterized. Based on this condition, we further deduce that there are no self-dual codes in this class of linear codes and explicitly construct two new classes of almost self-dual codes.

cs.IT↗

arXiv2025

BAG: Body-Aligned 3D Wearable Asset Generation

While recent advancements have shown remarkable progress in general 3D shape generation models, the challenge of leveraging these approaches to automatically generate wearable 3D assets remains unexplored. To this end, we present BAG, a Body-aligned Asset Generation method to output 3D wearable asset that can be automatically dressed on given 3D human bodies. This is achived by controlling the 3D generation process using human body shape and pose information. Specifically, we first build a general single-image to consistent multiview image diffusion model, and train it on the large Objaverse dataset to achieve diversity and generalizability. Then we train a Controlnet to guide the multiview generator to produce body-aligned multiview images. The control signal utilizes the multiview 2D projections of the target human body, where pixel values represent the XYZ coordinates of the body surface in a canonical space. The body-conditioned multiview diffusion generates body-aligned multiview images, which are then fed into a native 3D diffusion model to produce the 3D shape of the asset. Finally, by recovering the similarity transformation using multiview silhouette supervision and addressing asset-body penetration with physics simulators, the 3D asset can be accurately fitted onto the target human body. Experimental results demonstrate significant advantages over existing methods in terms of image prompt-following capability, shape diversity, and shape quality. Our project page is available at https://bag-3d.github.io/.

cs.CV↗

arXiv2025

Weak solutions to a compressible viscous non-resistive MHD equations with general boundary data

This paper is concerned with a compressible MHD equations describing the evolution of viscous non-resistive fluids in piecewise regular bounded Lipschitz domains. Under the general inflow-outflow boundary conditions, we prove existence of global-in-time weak solutions with finite energy initial data. The present result extends considerably the previous work by Li and Sun [\emph{J. Differential Equations.}, 267 (2019), pp. 3827-3851], where the homogeneous Dirichlet boundary condition for velocity field is treated. The proof leans on the specific mathematical structure of equations and the recently developed theory of open fluid systems. Furthermore, we establish the weak-strong uniqueness principle, namely a weak solution coincides with the strong solution on the lifespan of the latter provided they emanate from the same initial and boundary data. This basic property is expected to be useful in the study of convergence of numerical solutions.

math.AP↗

arXiv2025

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, and search-related data. Then, it prompts the same LLM to generate diverse domain-relevant questions from unlabeled corpora, with an additional filtering strategy to retain high-quality synthetic examples. By leveraging these self-generated synthetic examples, the LLM can improve their performance on domain-specific RAG tasks. Experiments on 11 datasets, spanning two backbone sizes and three domains, demonstrate that SimRAG outperforms baselines by 1.2\%--8.6\%.

cs.CL↗

arXiv2025

Scalable Machine Learning Training Infrastructure for Online Ads Recommendation and Auction Scoring Modeling at Google

Large-scale Ads recommendation and auction scoring models at Google scale demand immense computational resources. While specialized hardware like TPUs have improved linear algebra computations, bottlenecks persist in large-scale systems. This paper proposes solutions for three critical challenges that must be addressed for efficient end-to-end execution in a widely used production infrastructure: (1) Input Generation and Ingestion Pipeline: Efficiently transforming raw features (e.g., "search query") into numerical inputs and streaming them to TPUs; (2) Large Embedding Tables: Optimizing conversion of sparse features into dense floating-point vectors for neural network consumption; (3) Interruptions and Error Handling: Minimizing resource wastage in large-scale shared datacenters. To tackle these challenges, we propose a shared input generation technique to reduce computational load of input generation by amortizing costs across many models. Furthermore, we propose partitioning, pipelining, and RPC (Remote Procedure Call) coalescing software techniques to optimize embedding operations. To maintain efficiency at scale, we describe novel preemption notice and training hold mechanisms that minimize resource wastage, and ensure prompt error resolution. These techniques have demonstrated significant improvement in Google production, achieving a 116% performance boost and an 18% reduction in training costs across representative models.

cs.DC↗

arXiv2025

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning

Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks; however, they still encounter challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. This challenge is particularly pronounced in tasks involving multi-step processes, such as logical reasoning and multi-hop question answering, where understanding implicit relationships between entities and leveraging multi-hop connections in the given context are crucial. Graphs, as fundamental data structures, explicitly represent pairwise relationships between entities, thereby offering the potential to enhance LLMs' reasoning capabilities. External graphs have proven effective in supporting LLMs across multiple tasks. However, in many reasoning tasks, no pre-existing graph structure is provided. Can we structure implicit knowledge derived from context into graphs to assist LLMs in reasoning? In this paper, we propose Reasoning with Graphs (RwG) by first constructing explicit graphs from the context and then leveraging these graphs to enhance LLM reasoning performance on reasoning tasks. Extensive experiments demonstrate the effectiveness of the proposed method in improving both logical reasoning and multi-hop question answering tasks.

cs.CL↗

arXiv2025

A Preliminary Survey of Semantic Descriptive Model for Images

Considering the lack of a unified framework for image description and deep cultural analysis at the subject level in the field of Ancient Chinese Paintings (ACP), this study utilized the Beijing Palace Museum's ACP collections to develop a semantic model integrating the iconological theory with a new workflow for term extraction and mapping. Our findings underscore the model's effectiveness. SDM can be used to support further art-related knowledge organization and cultural exploration of ACPs.

cs.DL↗

arXiv2025

Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation

Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting control over the motion of objects in videos generated by any video diffusion model is a challenging problem. In this paper, we propose a novel zero-shot moving object trajectory control framework, Motion-Zero, to enable a bounding-box-trajectories-controlled text-to-video diffusion model. To this end, an initial noise prior module is designed to provide a position-based prior to improve the stability of the appearance of the moving object and the accuracy of position. In addition, based on the attention map of the U-net, spatial constraints are directly applied to the denoising process of diffusion models, which further ensures the positional and spatial consistency of moving objects during the inference. Furthermore, temporal consistency is guaranteed with a proposed shift temporal attention mechanism. Our method can be flexibly applied to various state-of-the-art video diffusion models without any training process. Extensive experiments demonstrate our proposed method can control the motion trajectories of objects and generate high-quality videos. Our project page is https://vpx-ecnu.github.io/MotionZero-website/

cs.CV↗

arXiv2025

Resource Allocation for the Training of Image Semantic Communication Networks

Semantic communication is a new paradigm that aims at providing more efficient communication for the next-generation wireless network. It focuses on transmitting extracted, meaningful information instead of the raw data. However, deep learning-enabled image semantic communication models often require a significant amount of time and energy for training, which is unacceptable, especially for mobile devices. To solve this challenge, our paper first introduces a distributed image semantic communication system where the base station and local devices will collaboratively train the models for uplink communication. Furthermore, we formulate a joint optimization problem to balance time and energy consumption on the local devices during training while ensuring effective model performance. An adaptable resource allocation algorithm is proposed to meet requirements under different scenarios, and its time complexity, solution quality, and convergence are thoroughly analyzed. Experimental results demonstrate the superiority of our algorithm in resource allocation optimization against existing benchmarks and discuss its impact on the performance of image semantic communication systems.

cs.SI↗

arXiv2025

CCIS-Diff: A Generative Model with Stable Diffusion Prior for Controlled Colonoscopy Image Synthesis

Colonoscopy is crucial for identifying adenomatous polyps and preventing colorectal cancer. However, developing robust models for polyp detection is challenging by the limited size and accessibility of existing colonoscopy datasets. While previous efforts have attempted to synthesize colonoscopy images, current methods suffer from instability and insufficient data diversity. Moreover, these approaches lack precise control over the generation process, resulting in images that fail to meet clinical quality standards. To address these challenges, we propose CCIS-DIFF, a Controlled generative model for high-quality Colonoscopy Image Synthesis based on a Diffusion architecture. Our method offers precise control over both the spatial attributes (polyp location and shape) and clinical characteristics of polyps that align with clinical descriptions. Specifically, we introduce a blur mask weighting strategy to seamlessly blend synthesized polyps with the colonic mucosa, and a text-aware attention mechanism to guide the generated images to reflect clinical characteristics. Notably, to achieve this, we construct a new multi-modal colonoscopy dataset that integrates images, mask annotations, and corresponding clinical text descriptions. Experimental results demonstrate that our method generates high-quality, diverse colonoscopy images with fine control over both spatial constraints and clinical consistency, offering valuable support for downstream segmentation and diagnostic tasks.

cs.CV↗

arXiv2025

Contention-Aware Microservice Deployment in Collaborative Mobile Edge Networks

As an emerging computing paradigm, mobile edge computing (MEC) provides processing capabilities at the network edge, aiming to reduce latency and improve user experience. Meanwhile, the advancement of containerization technology facilitates the deployment of microservice-based applications via edge node collaboration, ensuring highly efficient service delivery. However, existing research overlooks the resource contention among microservices in MEC. This neglect potentially results in inadequate resources for microservices constituting latency-sensitive applications, leading to increased response time and ultimately compromising quality of service (QoS). To solve this problem, we propose the Contention-Aware Multi-Application Microservice Deployment (CAMD) algorithm for collaborative MEC, balancing rapid response for applications with low-latency requirements and overall processing efficiency. The CAMD algorithm decomposes the overall deployment problem into manageable sub-problems, each focusing on a single microservice, then employs a heuristic approach to optimize these sub-problems, and ultimately arrives at an optimized deployment scheme through an iterative process. Finally, the superiority of the proposed algorithm is evidenced through intensive experiments and comparison with baseline algorithms.

cs.NI↗

arXiv2025

Modular Vehicle Routing Problem: Applications in Logistics

Recent studies and industry advancements indicate that modular vehicles (MVs) have the potential to enhance transportation systems through their ability to dock and split during a trip. Although various applications of MVs have been explored across different domains, their application in logistics remains underexplored. This study examines the use of MVs in cargo delivery to reduce total delivery costs. We model the delivery problem for MVs as a variant of the Vehicle Routing Problem, referred to as the Modular Vehicle Routing Problem (MVRP). In the MVRP, MVs can either serve customers independently or dock with other MVs to form a platoon, thereby reducing the average cost per unit. In this study, we mainly focus on two fundamental types of MVRPs, namely the capacitated MVRP and the MVRP with time windows. To address these problems, we first developed mixed-integer linear programming (MILP) models, which can be solved using commercial optimization solvers. Given the NP-hardness of this problem, we also designed a Tabu Search (TS) algorithm with a solution representation based on Gantt charts and a neighborhood structure tailored for the MVRP. Multi-start and shaking strategies were incorporated into the TS algorithm to escape local optima. Additionally, we explored other potential applications in logistics and discussed problem settings for three MVRP variants. Results from numerical experiments indicate that the proposed algorithm successfully identifies nearly all optimal solutions found by the MILP model in small-size benchmark instances, while also demonstrating good convergence speed in large-size benchmark instances. Comparative experiments show that the MVRP approach can reduce costs by approximately 5.6\% compared to traditional delivery methods. Sensitivity analyses reveal that improving the cost-saving capability of MV platooning can enhance overall benefits.

math.OC↗

arXiv2025

Population Aware Diffusion for Time Series Generation

Diffusion models have shown promising ability in generating high-quality time series (TS) data. Despite the initial success, existing works mostly focus on the authenticity of data at the individual level, but pay less attention to preserving the population-level properties on the entire dataset. Such population-level properties include value distributions for each dimension and distributions of certain functional dependencies (e.g., cross-correlation, CC) between different dimensions. For instance, when generating house energy consumption TS data, the value distributions of the outside temperature and the kitchen temperature should be preserved, as well as the distribution of CC between them. Preserving such TS population-level properties is critical in maintaining the statistical insights of the datasets, mitigating model bias, and augmenting downstream tasks like TS prediction. Yet, it is often overlooked by existing models. Hence, data generated by existing models often bear distribution shifts from the original data. We propose Population-aware Diffusion for Time Series (PaD-TS), a new TS generation model that better preserves the population-level properties. The key novelties of PaD-TS include 1) a new training method explicitly incorporating TS population-level property preservation, and 2) a new dual-channel encoder model architecture that better captures the TS data structure. Empirical results in major benchmark datasets show that PaD-TS can improve the average CC distribution shift score between real and synthetic data by 5.9x while maintaining a performance comparable to state-of-the-art models on individual-level authenticity.

cs.LG↗

arXiv2024

Bijections around Springer numbers

Arnol'd proved in 1992 that Springer numbers enumerate the Snakes, which are type $B$ analogs of alternating permutations. Chen, Fan and Jia in 2011 introduced the labeled ballot paths and established a ``hard'' bijection with snakes. Callan conjectured in 2012 and Han--Kitaev--Zhang proved recently that rc-invariant alternating permutations are counted by Springer numbers. Very recently, Chen--Fang--Kitaev--Zhang investigated multi-dimensional permutations and proved that weakly increasing $3$-dimensional permutations are also counted by Springer numbers. In this work, we construct a sequence of ``natural'' bijections linking the above four combinatorial objects.

math.CO↗

arXiv2024

Causal-aware Graph Neural Architecture Search under Distribution Shifts

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph scenarios, mainly because the graph-architecture correlations they exploit might be spurious and varying across distributions. We propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts. The problem remains unexplored with following challenges: how to discover the causal graph-architecture relationship that has stable predictive abilities across distributions, and how to handle distribution shifts with the discovered causal graph-architecture relationship to search the generalized graph architectures. To address these challenges, we propose Causal-aware Graph Neural Architecture Search (CARNAS), which is able to capture the causal graph-architecture relationship during the architecture search process and discover the generalized graph architecture under distribution shifts. Specifically, we propose Disentangled Causal Subgraph Identification to capture the causal subgraphs that have stable prediction abilities across distributions. Then, we propose Graph Embedding Intervention to intervene on causal subgraphs within the latent space, ensuring that these subgraphs encapsulate essential features for prediction while excluding non-causal elements. Additionally, we propose Invariant Architecture Customization to reinforce the causal invariant nature of the causal subgraphs, which are utilized to tailor generalized graph architectures. Extensive experiments demonstrate that CARNAS achieves advanced out-of-distribution generalization ability.

cs.LG↗

arXiv2024

Atomistic modeling of the structure and diffusion processes at Al(110)/Si(001) interphase boundaries obtained by vapor deposition

We report on molecular dynamics simulations of the atomic structure and diffusion processes at Al(110)/Si(001) interphase boundary created by simulated vapor deposition of Al(Si) alloy onto Si(001) substrate. An array of parallel misfit dislocations of both full and partial types is observed at the interface. Si atoms segregate to the misfit dislocations, with segregation to full dislocations being stronger. The interface diffusion is dominated by short-circuit diffusion along the misfit dislocations, creating a significant diffusion anisotropy. Diffusion of Al and Si atoms along the full misfit dislocations is faster than along the partial misfit dislocations. Due to the presence of the misfit dislocations, diffusion at the Al(110)/Si(001) interface studied here is faster than diffusion at the Al(111)/Si(111) interfaces investigated in our previous work.

cond-mat.mtrl-sci↗