arXiv subjects

Yuxin Ma

Publications and source records attributed to Yuxin Ma.

At least 37 records · Page 2Linked to original sources

arXiv2026

On Transferring Transferability: Towards a Theory for Size Generalization

Many modern learning tasks require models that can take inputs of varying sizes. Consequently, dimension-independent architectures have been proposed for domains where the inputs are graphs, sets, and point clouds. Recent work on graph neural networks has explored whether a model trained on low-dimensional data can transfer its performance to higher-dimensional inputs. We extend this body of work by introducing a general framework for transferability across dimensions. We show that transferability corresponds precisely to continuity in a limit space formed by identifying small problem instances with equivalent large ones. This identification is driven by the data and the learning task. We instantiate our framework on existing architectures, and implement the necessary changes to ensure their transferability. Finally, we provide design principles for designing new transferable models. Numerical experiments support our findings.

cs.LG↗

arXiv2026

Superconductivity of 30.4 K and its Reemergence under Pressure in Fe1.11Se Synthesized via Ion-exchange and De-intercalation Reaction

Binary stoichiometry FeSe (s-FeSe) is a well-known parent of high-temperature unconventional superconductors owing to its charge-neutral layer, highly tunable structure and electronic properties, and rich interplays among multiple electronic phases. Yet the s-FeSe synthesized via high-temperature equilibrium reactions bears the notorious interstitial Fe,where merely 3% of them is sufficient to kill the superconductivity. Here, we successfully synthesized a new non-stoichiometric Fe1.11Se single crystal with a superconducting onset temperature (Tconset) of 30.4 K through a hydrothermal ion-exchange and de-intercalation route. 11% interstitial Fe ions exceed the equilibrium phase diagram limit. Intriguingly, under physical pressure, the Tconset of exhibits a "V"-shaped evolution with a minimum at 2-2.6 GPa, and then upturning into a second superconducting region, reminiscent of the behaviors in FeSe intercalates. Furthermore, a pressure-induced possible magnetic order, previously only observed in pressurized s-FeSe, shows up. These results offer fresh insights into the role of interstitial Fe in governing superconducting and transport properties under non-equilibrium synthesis and tuning strategies.

cond-mat.supr-con↗

arXiv2026

MAR: Efficient Large Language Models via Module-aware Architecture Refinement

Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address these issues, we propose Module-aware Architecture Refinement (MAR), a two-stage framework that integrates State Space Models (SSMs) for linear-time sequence modeling and applies activation sparsification to reduce FFN costs. In addition, to mitigate low information density and temporal mismatch in integrating Spiking Neural Networks (SNNs) with SSMs, we design the Adaptive Ternary Multi-step Neuron (ATMN) and the Spike-aware Bidirectional Distillation Strategy (SBDS). Extensive experiments demonstrate that MAR effectively restores the performance of its dense counterpart under constrained resources while substantially reducing inference energy consumption. Furthermore, it outperforms efficient models of comparable or even larger scale, underscoring its potential for building efficient and practical LLMs.

cs.AI↗

arXiv2026

Hebbian Learning with Global Direction

Backpropagation algorithm has driven the remarkable success of deep neural networks, but its lack of biological plausibility and high computational costs have motivated the ongoing search for alternative training methods. Hebbian learning has attracted considerable interest as a biologically plausible alternative to backpropagation. Nevertheless, its exclusive reliance on local information, without consideration of global task objectives, fundamentally limits its scalability. Inspired by the biological synergy between neuromodulators and local plasticity, we introduce a novel model-agnostic Global-guided Hebbian Learning (GHL) framework, which seamlessly integrates local and global information to scale up across diverse networks and tasks. In specific, the local component employs Oja's rule with competitive learning to ensure stable and effective local updates. Meanwhile, the global component introduces a sign-based signal that guides the direction of local Hebbian plasticity updates. Extensive experiments demonstrate that our method consistently outperforms existing Hebbian approaches. Notably, on large-scale network and complex datasets like ImageNet, our framework achieves the competitive results and significantly narrows the gap with standard backpropagation.

cs.AI↗

arXiv2025

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

This paper presents LLaDA2.0 -- a tuple of discrete diffusion large language models (dLLM) scaling up to 100B total parameters through systematic conversion from auto-regressive (AR) models -- establishing a new paradigm for frontier-scale deployment. Instead of costly training from scratch, LLaDA2.0 upholds knowledge inheritance, progressive adaption and efficiency-aware design principle, and seamless converts a pre-trained AR model into dLLM with a novel 3-phase block-level WSD based training scheme: progressive increasing block-size in block diffusion (warm-up), large-scale full-sequence diffusion (stable) and reverting back to compact-size block diffusion (decay). Along with post-training alignment with SFT and DPO, we obtain LLaDA2.0-mini (16B) and LLaDA2.0-flash (100B), two instruction-tuned Mixture-of-Experts (MoE) variants optimized for practical deployment. By preserving the advantages of parallel decoding, these models deliver superior performance and efficiency at the frontier scale. Both models were open-sourced.

cs.LG↗

arXiv2025

On the loss of orthogonality in low-synchronization variants of reorthogonalized block classical Gram-Schmidt

Interest in communication-avoiding orthogonalization schemes for high-performance computing has been growing recently. This manuscript addresses open questions about the numerical stability of various block classical Gram-Schmidt variants that have been proposed in the past few years. An abstract framework is employed, the flexibility of which allows for new rigorous bounds on the loss of orthogonality in these variants. We first analyze a generalization of (reorthogonalized) block classical Gram-Schmidt and show that a "strong" intrablock orthogonalization routine is only needed for the very first block in order to maintain orthogonality on the level of the unit roundoff. In particular, this ``strong" first step does not have to be a reorthogonalized QR itself and subsequent steps can use less stable QR variants, thus keeping the overall communication costs low. Then, using this variant, which has four synchronization points per block column, we remove the synchronization points one at a time and analyze how each alteration affects the stability of the resulting method. Our analysis shows that the variant requiring only one synchronization per block column cannot be guaranteed to be stable in practice, as stability begins to degrade with the first reduction of synchronization points. Our analysis of block methods also provides new theoretical results for the single-column case. In particular, it is proven that DCGS2 from [Bielich, D. et al. Par. Comput. 112 (2022)] and CGS-2 from [Świrydowicz, K. et al, Num. Lin. Alg. Appl. 28 (2021)] are as stable as Householder QR. Numerical examples from the BlockStab toolbox are included throughout, to help compare variants and illustrate the effects of different choices of intraorthogonalization subroutines.

math.NA↗

arXiv2025

Nonlinear Laplacians: Tunable principal component analysis under directional prior information

We introduce a new family of algorithms for detecting and estimating a rank-one signal from a noisy observation under prior information about that signal's direction, focusing on examples where the signal is known to have entries biased to be positive. Given a matrix observation $\mathbf{Y}$, our algorithms construct a nonlinear Laplacian, another matrix of the form $\mathbf{Y}+\mathrm{diag}(σ(\mathbf{Y1}))$ for a nonlinear $σ:\mathbb{R}\to\mathbb{R}$, and examine the top eigenvalue and eigenvector of this matrix. When $\mathbf{Y}$ is the (suitably normalized) adjacency matrix of a graph, our approach gives a class of algorithms that search for unusually dense subgraphs by computing a spectrum of the graph "deformed" by the degree profile $\mathbf{Y1}$. We study the performance of such algorithms compared to direct spectral algorithms (the case $σ=0$) on models of sparse principal component analysis with biased signals, including the Gaussian planted submatrix problem. For such models, we rigorously characterize the strength of rank-one signal, as a function of $σ$, required for an outlier eigenvalue to appear in the spectrum of a nonlinear Laplacian matrix. While identifying the $σ$ that minimizes the required signal strength in closed form seems intractable, we explore three approaches to design $σ$ numerically: exhaustively searching over simple classes of $σ$, learning $σ$ from datasets of problem instances, and tuning $σ$ using black-box optimization of the critical signal strength. We find both theoretically and empirically that, if $σ$ is chosen appropriately, then nonlinear Laplacian spectral algorithms substantially outperform direct spectral algorithms, while retaining the conceptual simplicity of spectral methods compared to broader classes of computations like approximate message passing or general first order methods.

stat.ML↗

arXiv2025

dInfer: An Efficient Inference Framework for Diffusion Language Models

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet their widespread adoption remains constrained by the lack of a standardized and efficient inference framework. We present dInfer, an efficient and extensible framework for dLLM inference. dInfer decomposes the inference pipeline into four modular components--model, diffusion iteration manager, decoding strategy, and KV-cache manager--and integrates novel algorithms for each component alongside system-level optimizations. Through this combination of algorithmic innovations and system enhancements, dInfer achieves substantial efficiency gains without compromising output quality on LLaDA-MoE. At batch size 1, it surpasses 1,100 tokens per second on HumanEval and averages over 800 tokens per second across six benchmarks on $8\times$ H800 GPUs. Compared to prior systems, dInfer delivers a $10\times$ speedup over Fast-dLLM while maintaining similar model performance. Even compared to the AR model (with a comparable number of activation parameters and performance) QWen2.5-3B, which is highly optimized with the latest vLLM inference engine, dInfer still delivers a $2$-$3\times$ speedup. The implementation of dInfer is open-sourced at https://github.com/inclusionAI/dInfer.

cs.CL↗

arXiv2025

GamerAstra: Supporting 2D Non-Twitch Video Games for Blind and Low-Vision Players through a Multi-Agent Framework

Blind and low-vision (BLV) players face critical challenges in engaging with video games due to the inaccessibility of visual elements, difficulties navigating interfaces, and limitations in performing interaction. Meanwhile, the development of specialized accessibility features typically requires substantial programming effort and is often implemented on a game-by-game basis. To address these challenges, we introduce GamerAstra, a multi-agent human-AI collaboration framework that leverages a multi-agent design to facilitate access to 2D non-twitch video games for BLV players. It integrates vision-language models and computer vision techniques, enabling interaction with games lacking native accessibility support. The framework also incorporates custom assistance granularities to support varying degrees of visual impairment and enhances interface navigation through multiple input modalities. Technical evaluations and user studies indicate that GamerAstra effectively enhances playability and provides a more immersive gaming experience for BLV players. These findings also underscore potential avenues for advancing intelligent accessibility frameworks in the gaming domain.

cs.HC↗

arXiv2025

VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Models

Vision-language (VL) models have shown transformative potential across various critical domains due to their capability to comprehend multi-modal information. However, their performance frequently degrades under distribution shifts, making it crucial to assess and improve robustness against real-world data corruption encountered in practical applications. While advancements in VL benchmark datasets and data augmentation (DA) have contributed to robustness evaluation and improvement, there remain challenges due to a lack of in-depth comprehension of model behavior as well as the need for expertise and iterative efforts to explore data patterns. Given the achievement of visualization in explaining complex models and exploring large-scale data, understanding the impact of various data corruption on VL models aligns naturally with a visual analytics approach. To address these challenges, we introduce VisMoDAl, a visual analytics framework designed to evaluate VL model robustness against various corruption types and identify underperformed samples to guide the development of effective DA strategies. Grounded in the literature review and expert discussions, VisMoDAl supports multi-level analysis, ranging from examining performance under specific corruptions to task-driven inspection of model behavior and corresponding data slice. Unlike conventional works, VisMoDAl enables users to reason about the effects of corruption on VL models, facilitating both model behavior understanding and DA strategy formulation. The utility of our system is demonstrated through case studies and quantitative evaluations focused on corruption robustness in the image captioning task.

cs.HC↗

arXiv2025

Mixed precision iterative refinement for least squares with linear equality constraints and generalized least squares problems

Recent development on mixed precision techniques has largely enhanced the performance of various linear algebra solvers, one of which being the solver for the least squares problem $\min_{x}\lVert b-Ax\rVert_{2}$. By transforming least squares problems into augmented linear systems, mixed precision techniques are capable of refining the lower precision solution to the working precision. In this paper, we propose mixed precision iterative refinement algorithms for two variants of least squares problems -- the least squares problem with linear equality constraints (LSE) and the generalized least squares problem (GLS). Both classical and GMRES-based iterative refinement can be applied to augmented systems of these two problems to improve the accuracy of the solution. For reasonably well-conditioned problems, our algorithms reduce the execution time by a factor of 40% on average compared to the fixed precision ones from LAPACK on the x86-64 architecture.

math.NA↗

arXiv2025

RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to enhance large language models (LLMs) by integrating external knowledge retrieval with generative capabilities. While significant advancements have been made in improving retrieval accuracy and response quality, a critical challenge remains that the internal knowledge integration and retrieval-generation interactions in RAG workflows are largely opaque. This paper introduces RAGTrace, an interactive evaluation system designed to analyze retrieval and generation dynamics in RAG-based workflows. Informed by a comprehensive literature review and expert interviews, the system supports a multi-level analysis approach, ranging from high-level performance evaluation to fine-grained examination of retrieval relevance, generation fidelity, and cross-component interactions. Unlike conventional evaluation practices that focus on isolated retrieval or generation quality assessments, RAGTrace enables an integrated exploration of retrieval-generation relationships, allowing users to trace knowledge sources and identify potential failure cases. The system's workflow allows users to build, evaluate, and iterate on retrieval processes tailored to their specific domains of interest. The effectiveness of the system is demonstrated through case studies and expert evaluations on real-world RAG applications.

cs.HC↗

arXiv2025

The Performance of Low-Synchronization Variants of Reorthogonalized Block Classical Gram--Schmidt

Numerous applications, such as Krylov subspace solvers, make extensive use of the block classical Gram-Schmidt (BCGS) algorithm and its reorthogonalized variants for orthogonalizing a set of vectors. For large-scale problems in distributed memory settings, the communication cost, particularly the global synchronization cost, is a major performance bottleneck. In recent years, many low-synchronization BCGS variants have been proposed in an effort to reduce the number of synchronization points. The work [E. Carson, Y. Ma, arXiv preprint 2411.07077] recently proposed stable one-synchronization and two-synchronization variants of BCGS, i.e., BCGSI+P-1S and BCGSI+P-2S. In this work, we evaluate the performance of BCGSI+P-1S and BCGSI+P-2S on a distributed memory system compared to other well-known low-synchronization BCGS variants. In comparison to the classical reorthogonalized BCGS algorithm (BCGSI+), numerical experiments demonstrate that BCGSI+P-1S and BCGSI+P-2S can achieve up to 4 times and 2 times speedups, respectively, and perform similarly to other (less stable) one-synchronization and two-synchronization variants. BCGSI+P-1S and BCGSI+P-2S are therefore recommended as the best choice in practice for computing an economic QR factorization on distributed memory systems due to their superior stability when compared to other variants with the same synchronization cost.

cs.DC↗

arXiv2025

PatternSight: A Perceptual Grouping Effectiveness Assessment Approach for Graphical Patterns in Charts

The boom in visualization generation tools has significantly lowered the threshold for chart authoring. Nevertheless, chart authors with an insufficient understanding of perceptual theories may encounter difficulties in evaluating the effectiveness of chart representations, thereby struggling to identify the appropriate chart design to convey the intended data patterns. To address this issue, we propose a perception simulation model that can assess the perceptual effectiveness of charts by predicting graphical patterns that chart viewers are likely to notice. The perception simulation model integrates perceptual theory into visual feature extraction of chart elements to provide interpretable model outcomes. Human perceptual results proved that the outcome of our model can simulate the perceptual grouping behaviors of most chart viewers and cover diverse perceptual results. We also embed the model into a prototype interface called PatternSight to facilitate chart authors in assessing whether the chart design can satisfy their pattern representation requirements as expected and determining feasible improvements of visual design. According to the results of a user experiment, PatternSight can effectively assist chart authors in optimizing chart design for representing data patterns.

cs.HC↗

arXiv2025

AnyAni: An Interactive System with Generative AI for Animation Effect Creation and Code Understanding in Web Development

Generative AI assistants have been widely used in front-end programming. However, besides code writing, developers often encounter the need to generate animation effects. As novices in creative design without the assistance of professional designers, developers typically face difficulties in describing, designing, and implementing desired animations. To address this issue, we conducted a formative study (N=6) to identify the challenges that code developers face when dealing with animation design issues. Then, we introduce AnyAni, a human-AI collaborative system that supports front-end developers in the ideation, manipulation, and implementation of animation effects. The system combines the assistance of generative AI in creative design by adopting a nonlinear workflow for iterative animation development. In addition, developers can understand and learn the code generated for implementing animations through various interactive methods. A user study (N=9) demonstrated the usability of AnyAni in animation effect creation support for developers.

cs.HC↗

arXiv2025

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion

Ultra-high-definition (UHD) image restoration often faces computational bottlenecks and information loss due to its extremely high resolution. Existing studies based on Variational Autoencoders (VAE) improve efficiency by transferring the image restoration process from pixel space to latent space. However, degraded components are inherently coupled with background elements in degraded images, both information loss during compression and information gain during compensation remain uncontrollable. These lead to restored images often exhibiting image detail loss and incomplete degradation removal. To address this issue, we propose a Controlled Differential Disentangled VAE, which utilizes Hierarchical Contrastive Disentanglement Learning and an Orthogonal Gated Projection Module to guide the VAE to actively discard easily recoverable background information while encoding more difficult-to-recover degraded information into the latent space. Additionally, we design a Complex Invertible Multiscale Fusion Network to handle background features, ensuring their consistency, and utilize a latent space restoration network to transform the degraded latent features, leading to more accurate restoration results. Extensive experimental results demonstrate that our method effectively alleviates the information loss problem in VAE models while ensuring computational efficiency, significantly improving the quality of UHD image restoration, and achieves state-of-the-art results in six UHD restoration tasks with only 1M parameters.

cs.CV↗

arXiv2025

FEWSim: A Visual Analytic Framework for Exploring the Nexus of Food-Energy-Water Simulations

The interdependencies of food, energy, and water (FEW) systems create a nexus opportunity to explore the strengths and vulnerabilities of individual and cross-sector interactions within FEW systems. However, the variables quantifying nexus interactions are hard to observe, which hinders the cross-sector analysis. To overcome such challenges, we present FEWSim, a visual analytics framework designed to support domain experts in exploring and interpreting simulation results from a coupled FEW model. FEWSim employs a three-layer asynchronous architecture: the model layer integrates food, energy, and water models to simulate the FEW nexus; the middleware layer manages scenario configuration and execution; and the visualization layer provides interactive visual exploration of simulated time-series results across FEW sectors. The visualization layer further facilitates the exploration across multiple scenarios and evaluates scenario differences in performance using sustainability indices of the FEW nexus. We demonstrate the utility of FEWSim through a case study for the Phoenix Active Management Area (AMA) in Arizona.

cs.HC↗

arXiv2025

On the backward stability of s-step GMRES

Communication, i.e., data movement, is a critical bottleneck for the performance of classical Krylov subspace method solvers on modern computer architectures. Variants of these methods which avoid communication have been introduced, which, while equivalent in exact arithmetic, can be unstable in finite precision. In this work, we address the backward stability of $s$-step GMRES, also known as communication-avoiding GMRES. Compared to the ``modular framework'' proposed in [A.~Buttari, N.~J.~Higham, T.~Mary, \& B.~Vieublé. Preprint in 2024.], we present an improved framework for simplifying the analysis of $s$-step GMRES, which includes standard GMRES ($s=1$) as a special case, by isolating the effects of rounding errors in the QR factorization and the solution of the least squares problem. The key advantage of this new framework is that it is evident how the orthogonalization method affects the backward error, and it is not necessary to re-evaluate anything other than the orthogonalization itself when modifying the orthogonalization used in GMRES. Using this framework, we analyze $s$-step GMRES with popular block orthogonalization methods: block modified Gram--Schmidt and reorthogonalized block classical Gram--Schmidt algorithms. An example illustrates the resulting instability of $s$-step GMRES when paired with the classical $s$-step Arnoldi process and shows the limitations of popular strategies for resolving this instability. To address this issue, we propose a modified $s$-step Arnoldi process that allows for much larger block size $s$ while maintaining satisfactory accuracy, as confirmed by our numerical experiments.

math.NA↗