arXiv subjects

Yuxin Ma

Publications and source records attributed to Yuxin Ma.

At least 55 records · Page 3Linked to original sources

arXiv2025

Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction

Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability barriers for non-professionals, with intricate operational procedures severely hindering creative productivity. To address this, we propose a Large Language Model (LLM)-aided text animation editing system that enables real-time intent tracking and flexible editing. The system introduces an agent-based dual-stream pipeline that integrates context-aware inline suggestions and conversational guidance as well as employs a semantic-animation mapping to facilitate LLM-driven creative intent translation. Besides, the system supports synchronized text-animation previews and parametric adjustments via unified controls to improve editing workflow. A user study evaluates the system, highlighting its ability to help non-professional users complete animation workflows while validating the pipeline. The findings encourage further exploration of integrating LLMs into a comprehensive video creation workflow.

cs.HC↗

arXiv2025

NeurIPS 2024 ML4CFD Competition: Results and Retrospective Analysis

The integration of machine learning (ML) into the physical sciences is reshaping computational paradigms, offering the potential to accelerate demanding simulations such as computational fluid dynamics (CFD). Yet, persistent challenges in accuracy, generalization, and physical consistency hinder the practical deployment of ML models in scientific domains. To address these limitations and systematically benchmark progress, we organized the ML4CFD competition, centered on surrogate modeling for aerodynamic simulations over two-dimensional airfoils. The competition attracted over 240 teams, who were provided with a curated dataset generated via OpenFOAM and evaluated through a multi-criteria framework encompassing predictive accuracy, physical fidelity, computational efficiency, and out-of-distribution generalization. This retrospective analysis reviews the competition outcomes, highlighting several approaches that outperformed baselines under our global evaluation score. Notably, the top entry exceeded the performance of the original OpenFOAM solver on aggregate metrics, illustrating the promise of ML-based surrogates to outperform traditional solvers under tailored criteria. Drawing from these results, we analyze the key design principles of top submissions, assess the robustness of our evaluation framework, and offer guidance for future scientific ML challenges.

cs.LG↗

arXiv2025

On a shrink-and-expand technique for symmetric block eigensolvers

In symmetric block eigenvalue algorithms, such as the subspace iteration algorithm and the locally optimal block preconditioned conjugate gradient (LOBPCG) algorithm, a large block size is often employed to achieve robustness and rapid convergence. However, using a large block size also increases the computational cost. Traditionally, the block size is typically reduced after convergence of some eigenpairs, known as deflation. In this work, we propose a non-deflation-based, more aggressive technique, where the block size is adjusted dynamically during the algorithm. This technique can be applied to a wide range of block eigensolvers, reducing computational cost without compromising convergence speed. We present three adaptive strategies for adjusting the block size, and apply them to four well-known eigensolvers as examples. Detailed theoretical analysis and numerical experiments are provided to illustrate the efficiency of the proposed technique. In practice, an overall acceleration of 20% to 30% is observed.

math.NA↗

arXiv2025

DataLab: A Unified Platform for LLM-Powered Business Intelligence

Business intelligence (BI) transforms large volumes of data within modern organizations into actionable insights for informed decision-making. Recently, large language model (LLM)-based agents have streamlined the BI workflow by automatically performing task planning, reasoning, and actions in executable environments based on natural language (NL) queries. However, existing approaches primarily focus on individual BI tasks such as NL2SQL and NL2VIS. The fragmentation of tasks across different data roles and tools lead to inefficiencies and potential errors due to the iterative and collaborative nature of BI. In this paper, we introduce DataLab, a unified BI platform that integrates a one-stop LLM-based agent framework with an augmented computational notebook interface. DataLab supports various BI tasks for different data roles in data preparation, analysis, and visualization by seamlessly combining LLM assistance with user customization within a single environment. To achieve this unification, we design a domain knowledge incorporation module tailored for enterprise-specific BI tasks, an inter-agent communication mechanism to facilitate information sharing across the BI workflow, and a cell-based context management strategy to enhance context utilization efficiency in BI notebooks. Extensive experiments demonstrate that DataLab achieves state-of-the-art performance on various BI tasks across popular research benchmarks. Moreover, DataLab maintains high effectiveness and efficiency on real-world datasets from Tencent, achieving up to a 58.58% increase in accuracy and a 61.65% reduction in token cost on enterprise-specific BI tasks.

cs.DB↗

arXiv2025

CalliSense: An Interactive Educational Tool for Process-based Learning in Chinese Calligraphy

Process-based learning is crucial for the transmission of intangible cultural heritage, especially in complex arts like Chinese calligraphy, where mastering techniques cannot be achieved by merely observing the final work. To explore the challenges faced in calligraphy heritage transmission, we conducted semi-structured interviews (N=8) as a formative study. Our findings indicate that the lack of calligraphy instructors and tools makes it difficult for students to master brush techniques, and teachers struggle to convey the intricate details and rhythm of brushwork. To address this, we collaborated with calligraphy instructors to develop an educational tool that integrates writing process capture and visualization, showcasing the writing rhythm, hand force, and brush posture. Through empirical studies conducted in multiple teaching workshops, we evaluated the system's effectiveness with teachers (N=4) and students (N=12). The results show that the tool significantly enhances teaching efficiency and aids learners in better understanding brush techniques.

cs.HC↗

arXiv2025

HarmonyCut: Supporting Creative Chinese Paper-cutting Design with Form and Connotation Harmony

Chinese paper-cutting, an Intangible Cultural Heritage (ICH), faces challenges from the erosion of traditional culture due to the prevalence of realism alongside limited public access to cultural elements. While generative AI can enhance paper-cutting design with its extensive knowledge base and efficient production capabilities, it often struggles to align content with cultural meaning due to users' and models' lack of comprehensive paper-cutting knowledge. To address these issues, we conducted a formative study (N=7) to identify the workflow and design space, including four core factors (Function, Subject Matter, Style, and Method of Expression) and a key element (Pattern). We then developed HarmonyCut, a generative AI-based tool that translates abstract intentions into creative and structured ideas. This tool facilitates the exploration of suggested related content (knowledge, works, and patterns), enabling users to select, combine, and adjust elements for creative paper-cutting design. A user study (N=16) and an expert evaluation (N=3) demonstrated that HarmonyCut effectively provided relevant knowledge, aiding the ideation of diverse paper-cutting designs and maintaining design quality within the design space to ensure alignment between form and cultural connotation.

cs.HC↗

arXiv2025

ParetoLens: A Visual Analytics Framework for Exploring Solution Sets of Multi-objective Evolutionary Algorithms

In the domain of multi-objective optimization, evolutionary algorithms are distinguished by their capability to generate a diverse population of solutions that navigate the trade-offs inherent among competing objectives. This has catalyzed the ascension of evolutionary multi-objective optimization (EMO) as a prevalent approach. Despite the effectiveness of the EMO paradigm, the analysis of resultant solution sets presents considerable challenges. This is primarily attributed to the high-dimensional nature of the data and the constraints imposed by static visualization methods, which frequently culminate in visual clutter and impede interactive exploratory analysis. To address these challenges, this paper introduces ParetoLens, a visual analytics framework specifically tailored to enhance the inspection and exploration of solution sets derived from the multi-objective evolutionary algorithms. Utilizing a modularized, algorithm-agnostic design, ParetoLens enables a detailed inspection of solution distributions in both decision and objective spaces through a suite of interactive visual representations. This approach not only mitigates the issues associated with static visualizations but also supports a more nuanced and flexible analysis process. The usability of the framework is evaluated through case studies and expert interviews, demonstrating its potential to uncover complex patterns and facilitate a deeper understanding of multi-objective optimization solution sets. A demo website of ParetoLens is available at https://dva-lab.org/paretolens/.

cs.NE↗

arXiv2024

A mixed precision Jacobi SVD algorithm

We propose a mixed precision Jacobi algorithm for computing the singular value decomposition (SVD) of a dense matrix. After appropriate preconditioning, the proposed algorithm computes the SVD in a lower precision as an initial guess, and then performs one-sided Jacobi rotations in the working precision as iterative refinement. By carefully transforming a lower precision solution to a higher precision one, our algorithm achieves about 2 times speedup on the x86-64 architecture compared to the usual one-sided Jacobi SVD algorithm in LAPACK, without sacrificing the accuracy.

math.NA↗

arXiv2024

Reorthogonalized Pythagorean variants of block classical Gram-Schmidt

Block classical Gram-Schmidt (BCGS) is commonly used for orthogonalizing a set of vectors $X$ in distributed computing environments due to its favorable communication properties relative to other orthogonalization approaches, such as modified Gram-Schmidt or Householder. However, it is known that BCGS (as well as recently developed low-synchronization variants of BCGS) can suffer from a significant loss of orthogonality in finite-precision arithmetic, which can contribute to instability and inaccurate solutions in downstream applications such as $s$-step Krylov subspace methods. A common solution to improve the orthogonality among the vectors is reorthogonalization. Focusing on the "Pythagorean" variant of BCGS, introduced in [E. Carson, K. Lund, & M. Rozložník. SIAM J. Matrix Anal. Appl. 42(3), pp. 1365--1380, 2021], which guarantees an $O(\varepsilon)κ^2(X)$ bound on the loss of orthogonality as long as $O(\varepsilon)κ^2(X)<1$, where $\varepsilon$ denotes the unit roundoff, we introduce and analyze two reorthogonalized Pythagorean BCGS variants. These variants feature favorable communication properties, with asymptotically two synchronization points per block column, as well as an improved $O(\varepsilon)$ bound on the loss of orthogonality. Our bounds are derived in a general fashion to additionally allow for the analysis of mixed-precision variants. We verify our theoretical results with a panel of test matrices and experiments from a new version of the \texttt{BlockStab} toolbox.

math.NA↗

arXiv2024

ParetoTracker: Understanding Population Dynamics in Multi-objective Evolutionary Algorithms through Visual Analytics

Multi-objective evolutionary algorithms (MOEAs) have emerged as powerful tools for solving complex optimization problems characterized by multiple, often conflicting, objectives. While advancements have been made in computational efficiency as well as diversity and convergence of solutions, a critical challenge persists: the internal evolutionary mechanisms are opaque to human users. Drawing upon the successes of explainable AI in explaining complex algorithms and models, we argue that the need to understand the underlying evolutionary operators and population dynamics within MOEAs aligns well with a visual analytics paradigm. This paper introduces ParetoTracker, a visual analytics framework designed to support the comprehension and inspection of population dynamics in the evolutionary processes of MOEAs. Informed by preliminary literature review and expert interviews, the framework establishes a multi-level analysis scheme, which caters to user engagement and exploration ranging from examining overall trends in performance metrics to conducting fine-grained inspections of evolutionary operations. In contrast to conventional practices that require manual plotting of solutions for each generation, ParetoTracker facilitates the examination of temporal trends and dynamics across consecutive generations in an integrated visual interface. The effectiveness of the framework is demonstrated through case studies and expert interviews focused on widely adopted benchmark optimization problems.

cs.NE↗

arXiv2024

Evidence of a hydrated mineral enriched in water and ammonium molecules in the Chang'e-5 lunar sample

The presence and distribution of water on the Moon are fundamental to our understanding of the Earth-Moon system. Despite extensive research and remote detection, the origin and chemical form of lunar water (H2O) have remained elusive. In this study, we present the discovery of a hydrated mineral, (NH4)MgCl3*6H2O, in lunar soil samples returned by the Chang'e-5 mission, containing approximately 41 wt% H2O. The mineral's structure and composition closely resemble novograblenovite, a terrestrial fumarole mineral formed through the reaction of hot basalt with water-rich volcanic gases, and carnallite, an earth evaporite mineral. We rule out terrestrial contamination or rocket exhaust as the origin of this hydrate, based on its chemical and isotopic compositions and formation conditions. The presence of ammonium indicates a more complex lunar degassing history and highlights its potential as a resource for lunar habitation. Our findings also suggest that water molecules can persist in sunlit areas of the Moon as hydrated salt, providing crucial constraints to the fugacity of water and ammonia vapor in lunar volcanic gases.

astro-ph.EP↗

arXiv2024

Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting

Spatiotemporal forecasting techniques are significant for various domains such as transportation, energy, and weather. Accurate prediction of spatiotemporal series remains challenging due to the complex spatiotemporal heterogeneity. In particular, current end-to-end models are limited by input length and thus often fall into spatiotemporal mirage, i.e., similar input time series followed by dissimilar future values and vice versa. To address these problems, we propose a novel self-supervised pre-training framework Spatial-Temporal-Decoupled Masked Pre-training (STD-MAE) that employs two decoupled masked autoencoders to reconstruct spatiotemporal series along the spatial and temporal dimensions. Rich-context representations learned through such reconstruction could be seamlessly integrated by downstream predictors with arbitrary architectures to augment their performances. A series of quantitative and qualitative evaluations on six widely used benchmarks (PEMS03, PEMS04, PEMS07, PEMS08, METR-LA, and PEMS-BAY) are conducted to validate the state-of-the-art performance of STD-MAE. Codes are available at https://github.com/Jimmy-7664/STD-MAE.

cs.LG↗

arXiv2024

TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic

Recent achievements in deep learning (DL) have shown its potential for predicting traffic flows. Such predictions are beneficial for understanding the situation and making decisions in traffic control. However, most state-of-the-art DL models are considered "black boxes" with little to no transparency for end users with respect to the underlying mechanisms. Some previous work tried to "open the black boxes" and increase the interpretability of how predictions are generated. However, it still remains challenging to handle complex models on large-scale spatio-temporal data and discover salient spatial and temporal patterns that significantly influence traffic flows. To overcome the challenges, we present TrafPS, a visual analytics approach for interpreting traffic prediction outcomes to support decision-making in traffic management and urban planning. The measurements, region SHAP and trajectory SHAP, are proposed to quantify the impact of flow patterns on urban traffic at different levels. Based on the task requirement from the domain experts, we employ an interactive visual interface for multi-aspect exploration and analysis of significant flow patterns. Two real-world case studies demonstrate the effectiveness of TrafPS in identifying key routes and decision-making support for urban planning.

cs.LG↗

arXiv2023

GeoExplainer: A Visual Analytics Framework for Spatial Modeling Contextualization and Report Generation

Geographic regression models of various descriptions are often applied to identify patterns and anomalies in the determinants of spatially distributed observations. These types of analyses focus on answering why questions about underlying spatial phenomena, e.g., why is crime higher in this locale, why do children in one school district outperform those in another, etc.? Answers to these questions require explanations of the model structure, the choice of parameters, and contextualization of the findings with respect to their geographic context. This is particularly true for local forms of regression models which are focused on the role of locational context in determining human behavior. In this paper, we present GeoExplainer, a visual analytics framework designed to support analysts in creating explanative documentation that summarizes and contextualizes their spatial analyses. As analysts create their spatial models, our framework flags potential issues with model parameter selections, utilizes template-based text generation to summarize model outputs, and links with external knowledge repositories to provide annotations that help to explain the model results. As analysts explore the model results, all visualizations and annotations can be captured in an interactive report generation widget. We demonstrate our framework using a case study modeling the determinants of voting in the 2016 US Presidential Election.

cs.HC↗

arXiv2023

A Comparative Visual Analytics Framework for Evaluating Evolutionary Processes in Multi-objective Optimization

Evolutionary multi-objective optimization (EMO) algorithms have been demonstrated to be effective in solving multi-criteria decision-making problems. In real-world applications, analysts often employ several algorithms concurrently and compare their solution sets to gain insight into the characteristics of different algorithms and explore a broader range of feasible solutions. However, EMO algorithms are typically treated as black boxes, leading to difficulties in performing detailed analysis and comparisons between the internal evolutionary processes. Inspired by the successful application of visual analytics tools in explainable AI, we argue that interactive visualization can significantly enhance the comparative analysis between multiple EMO algorithms. In this paper, we present a visual analytics framework that enables the exploration and comparison of evolutionary processes in EMO algorithms. Guided by a literature review and expert interviews, the proposed framework addresses various analytical tasks and establishes a multi-faceted visualization design to support the comparative analysis of intermediate generations in the evolution as well as solution sets. We demonstrate the effectiveness of our framework through case studies on benchmarking and real-world multi-objective optimization problems to elucidate how analysts can leverage our framework to inspect and compare diverse algorithms.

cs.NE↗

arXiv2023

Understand Data Preprocessing for Effective End-to-End Training of Deep Neural Networks

In this paper, we primarily focus on understanding the data preprocessing pipeline for DNN Training in the public cloud. First, we run experiments to test the performance implications of the two major data preprocessing methods using either raw data or record files. The preliminary results show that data preprocessing is a clear bottleneck, even with the most efficient software and hardware configuration enabled by NVIDIA DALI, a high-optimized data preprocessing library. Second, we identify the potential causes, exercise a variety of optimization methods, and present their pros and cons. We hope this work will shed light on the new co-design of ``data storage, loading pipeline'' and ``training framework'' and flexible resource configurations between them so that the resources can be fully exploited and performance can be maximized.

cs.LG↗

arXiv2023

A mixed precision LOBPCG algorithm

The locally optimal block preconditioned conjugate gradient (LOBPCG) algorithm is a popular approach for computing a few smallest eigenvalues and the corresponding eigenvectors of a large Hermitian positive definite matrix A. In this work, we propose a mixed precision variant of LOBPCG that uses a (sparse) Cholesky factorization of A computed in reduced precision as the preconditioner. To further enhance performance, a mixed precision orthogonalization strategy is proposed. To analyze the impact of reducing precision in the preconditioner on performance, we carry out a rounding error and convergence analysis of PINVIT, a simplified variant of LOBPCG. Our theoretical results predict and our numerical experiments confirm that the impact on convergence remains marginal. In practice, our mixed precision LOBPCG algorithm typically reduces the computation time by a factor of 1.4--2.0 on both CPUs and GPUs.

math.NA↗

arXiv2023

BiFeat: Supercharge GNN Training via Graph Feature Quantization

Graph Neural Networks (GNNs) is a promising approach for applications with nonEuclidean data. However, training GNNs on large scale graphs with hundreds of millions nodes is both resource and time consuming. Different from DNNs, GNNs usually have larger memory footprints, and thus the GPU memory capacity and PCIe bandwidth are the main resource bottlenecks in GNN training. To address this problem, we present BiFeat: a graph feature quantization methodology to accelerate GNN training by significantly reducing the memory footprint and PCIe bandwidth requirement so that GNNs can take full advantage of GPU computing capabilities. Our key insight is that unlike DNN, GNN is less prone to the information loss of input features caused by quantization. We identify the main accuracy impact factors in graph feature quantization and theoretically prove that BiFeat training converges to a network where the loss is within $ε$ of the optimal loss of uncompressed network. We perform extensive evaluation of BiFeat using several popular GNN models and datasets, including GraphSAGE on MAG240M, the largest public graph dataset. The results demonstrate that BiFeat achieves a compression ratio of more than 30 and improves GNN training speed by 200%-320% with marginal accuracy loss. In particular, BiFeat achieves a record by training GraphSAGE on MAG240M within one hour using only four GPUs.

cs.LG↗