44 articles mentioning Matrix-Game-3.0
arXiv:2508.08822v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) models are currently driven by a significant upscaling of their complexity, with massive matrix-multiplication workloads representing the major computational bottleneck. In-memory computing (IMC) architectures are
arXiv:2511.21686v2 Announce Type: replace Abstract: Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where specialized agent
arXiv:2604.18450v1 Announce Type: cross Abstract: Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before overfitting dominates. We provide an analytically tractable random-matrix model that reproduces this phe
arXiv:2509.11983v2 Announce Type: replace Abstract: Neural network (NN) training is inherently a large-scale matrix optimization problem, yet the matrix structure of NN parameters has long been overlooked. Recently, the optimizer Muon \citep{jordanmuon}, which explicitly exploits this structure, has
arXiv:2505.07033v2 Announce Type: replace-cross Abstract: Many classification performance metrics exist, each suited to a specific application. However, these metrics often differ in scale and can exhibit varying sensitivity to class imbalance rates in the test set. As a result, it is difficult to u
arXiv:2604.16398v1 Announce Type: cross Abstract: Q-matrices are a cornerstone of theory-driven assessment and learning analytics, making item demands and students' underlying knowledge components and misconceptions explicit and actionable. However, Q-matrices are typically crafted by experts, makin
arXiv:2604.18539v1 Announce Type: new Abstract: This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is proposed that aligns predicted act distributions with corpus-derived transition patterns. Evaluated on a
arXiv:2511.10909v2 Announce Type: replace-cross Abstract: Modern AI accelerators rely on matrix multiply-accumulate units (MMAUs), such as NVIDIA Tensor Cores and AMD Matrix Cores, to accelerate deep neural network workloads. MMAUs expose only instruction-level or API-level interfaces of matrix mult
arXiv:2604.15242v1 Announce Type: new Abstract: We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al. (2025) recently showed that achieving last-iterate convergence in this setting is harder when the players are uncoupled, by proving a lower bound on the exploitab
arXiv:2506.13139v2 Announce Type: replace-cross Abstract: Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In particular, the proportional regime where the
arXiv:2604.09687v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel on many multimodal reasoning benchmarks, but these evaluations often do not require an exhaustive readout of the image and can therefore obscure failures in faithfully capturing all visual details. We intro
arXiv:2604.13432v1 Announce Type: cross Abstract: Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations (e.g., sort
arXiv:2510.06685v2 Announce Type: replace-cross Abstract: Self-attention layers have become fundamental building blocks of modern deep neural networks, yet their theoretical understanding remains limited, particularly from the perspective of random matrix theory. In this work, we provide a rigorous
arXiv:2604.12128v1 Announce Type: new Abstract: We investigate how self-referential inputs alter the internal matrix dynamics of large language models. Measuring 106 scalar metrics across up to 7 analysis passes on four models from three architecture families -- Qwen3-VL-8B, Llama-3.2-11B, Llama-3.3
arXiv:2604.09742v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on vector-level split and merge operations that introduce non-negligible co
arXiv:2502.07114v2 Announce Type: replace-cross Abstract: Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton
arXiv:2604.11615v1 Announce Type: cross Abstract: Matrix extensions have emerged as an essential feature in modern CPUs to address the surging demands of AI workloads. However, existing designs often incur substantial hardware and software design overhead. Tight coupling with the CPU pipeline compli
arXiv:2604.10326v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite advances in alignment and instruction tuning. We propose Head-Masked Nullspace Steering (HMNS), a circ
arXiv:2409.09298v2 Announce Type: replace-cross Abstract: The Matrix Profile (MP), a versatile tool for time series data mining, has been shown effective in time series anomaly detection (TSAD). This paper delves into the problem of anomaly detection in multidimensional time series, a common occurre
arXiv:2601.16294v2 Announce Type: replace-cross Abstract: General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art vendor libraries tune tensor layouts, parallelization schemes, and cache blocking to minimize data movement across the memory hierarc
arXiv:2512.12911v2 Announce Type: replace-cross Abstract: This study evaluates thresholds for removing singular values from singular value decomposition-based low-rank approximations of deep neural network weight matrices. Each weight matrix is modeled as the sum of signal and noise matrices. The lo
arXiv:2604.08161v1 Announce Type: new Abstract: Dynamic neuroimaging data, such as emission tomography measurements of radiotracer transport in blood or cerebrospinal fluid, often exhibit diffusion-like properties. These introduce distance-dependent temporal delays, scale-differences, and stretching
arXiv:2604.02445v2 Announce Type: replace Abstract: Matrix Profile (MP) methods are an interpretable and scalable family of distance-based methods for time-series anomaly detection, but strong benchmark performance still depends on design choices beyond a vanilla nearest-neighbor profile. This techn
arXiv:2602.18377v3 Announce Type: replace-cross Abstract: Quantum reservoir computers (QRCs) have emerged as a promising approach to quantum machine learning, since they utilize the natural dynamics of quantum systems for data processing and are simple to train. Here, we consider $n$-qubit quantum e
arXiv:2505.16932v4 Announce Type: replace-cross Abstract: Computing the polar decomposition and the related matrix sign function has been a well-studied problem in numerical analysis for decades. Recently, it has emerged as an important subroutine within the Muon optimizer for training deep neural n
arXiv:2604.04701v1 Announce Type: new Abstract: Large language models (LLMs) have achieved outstanding performance across a wide range of natural language processing tasks, but their enormous parameter counts impose ubstantial memory and computational overheads. This challenge is particularly critic
arXiv:2506.09749v3 Announce Type: replace-cross Abstract: In complex engineering systems, the dependencies among components or development activities are often modeled and analyzed using Design Structure Matrix (DSM). Reorganizing elements within a DSM to minimize feedback loops and enhance modulari
arXiv:2604.02335v1 Announce Type: new Abstract: Modeling groundwater flow in three-dimensional fractured crystalline media requires accounting for strong spatial heterogeneity induced by fractures. Fine-scale discrete fracture-matrix (DFM) simulations can capture this complexity but are computationa
arXiv:2604.02505v1 Announce Type: cross Abstract: Recently, Jiang et al. [2026] developed Leon, a practical variant of One-sided Shampoo [Xie et al., 2025a, An et al., 2025] algorithm for online convex optimization, which does not require computing a costly quadratic projection at each iteration. Un
arXiv:2510.05528v2 Announce Type: replace Abstract: Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hardware acceleration, existing
arXiv:2305.08175v4 Announce Type: replace-cross Abstract: Noisy marginals are a common form of confidentiality protecting data release and are useful for many downstream tasks such as contingency table analysis, construction of Bayesian networks, and even synthetic data generation. Privacy mechanism
arXiv:2509.25302v2 Announce Type: replace Abstract: The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective misalignment
arXiv:2604.00868v1 Announce Type: cross Abstract: Matrix mechanisms are often used to provide unbiased differentially private query answers when publishing statistics or creating synthetic data. Recent work has developed matrix mechanisms, such as ResidualPlanner and Weighted Fourier Factorizations,
arXiv:2603.20527v2 Announce Type: replace Abstract: Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of the loss landscape . The central challenge in this field lies in balancing preconditioning effectiven
arXiv:2604.00060v1 Announce Type: cross Abstract: The low-rank matrix recovery problem seeks to reconstruct an unknown $n_1 \times n_2$ rank-$r$ matrix from $m$ linear measurements, where $m\ll n_1n_2$. This problem has been extensively studied over the past few decades, leading to a variety of algo
arXiv:2603.29715v1 Announce Type: new Abstract: Nonnegative matrix factorization (NMF) approximates a nonnegative matrix, $X$, by the product of two nonnegative factors, $WH$, where $W$ has $r$ columns and $H$ has $r$ rows. In this paper, we consider NMF using the component-wise L1 norm as the error
arXiv:2603.28346v1 Announce Type: new Abstract: Efficient estimation of high-dimensional matrices-including covariance and precision matrices-is a cornerstone of modern multivariate statistics. Most existing studies have focused primarily on the theoretical properties of the estimators (e.g., consis
arXiv:2603.28534v1 Announce Type: new Abstract: Transformer-based language models achieve strong performance across NLP tasks, but their quadratic parameter scaling with hidden dimension makes deployment on resource-constrained hardware expensive. We study Matrix Product Operator (MPO) decomposition
arXiv:2603.27072v1 Announce Type: cross Abstract: Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and the set of minimizers remains
arXiv:2603.26739v1 Announce Type: cross Abstract: In 2006 we proposed Quantum Fuzzy Sets, observing that states of a quantum register could serve as characteristic functions of fuzzy subsets, embedding Zadeh's unit interval into the Bloch sphere. That paper was deliberately preliminary. In the two d
arXiv:2603.27462v1 Announce Type: cross Abstract: Matrix-vector multiplication is a fundamental building block in neural networks, vector databases, and large language models, particularly during inference. As a result, efficient matrix-vector multiplication engines directly translate into more effi
arXiv:2411.15624v2 Announce Type: replace-cross Abstract: Precision matrix estimation is essential in various fields; yet it is challenging when samples for the target study are limited. Transfer learning can enhance estimation accuracy by leveraging data from related source studies. We propose Tran
arXiv:2603.25863v1 Announce Type: cross Abstract: This paper proposes a method for dynamic hand gesture recognition based on the composition of two models: the MediaPipe Hand Landmarker, responsible for extracting 21 skeletal keypoints of the hand, and a convolutional neural network (CNN) trained to