Related papers: Virtual Parameter Sharpening: Dynamic Low-Rank Per…

Over the past decade there has been considerable interest in spectral algorithms for learning Predictive State Representations (PSRs). Spectral algorithms have appealing theoretical guarantees; however, the resulting models do not always…

For affine linear parameter-varying (LPV) systems, this paper develops two parameter reduction methods for reducing the dimension of the parameter space. The first method achieves the complexity reduction by transforming the affine LPV…

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and lower memory usage, they do not decrease computational cost.…

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable…

In this work we consider the problem of estimating a high-dimensional $p \times p$ covariance matrix $\Sigma$, given $n$ observations of confounded data with covariance $\Sigma + \Gamma \Gamma^T$, where $\Gamma$ is an unknown $p \times q$…

Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloning, overlooking the fundamental nature of robot learning as…

Standard vision-language-action (VLA) models rely on fitting statistical data priors, limiting their robust understanding of underlying physical dynamics. Reinforcement learning enhances physical grounding through exploration yet typically…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

We present a new computational approach to approximating a large, noisy data table by a low-rank matrix with sparse singular vectors. The approximation is obtained from thresholded subspace iterations that produce the singular vectors…

Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes…

Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that…

Matrix-level low-rank compression is a promising way to reduce the cost of large language models, but running compression and evaluating the resulting models on language tasks can be prohibitively expensive. Can compression-induced…

Computational efficiency has remained a critical consideration in scaling high-capacity language models, with inference latency and resource consumption presenting significant constraints on real-time applications. The study has introduced…

The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algorithmic-level optimizations such as token pruning and…

Deep neural networks have become the standard approach to building reliable Natural Language Processing (NLP) applications, ranging from Neural Machine Translation (NMT) to dialogue systems. However, improving accuracy by increasing the…

Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, requiring expensive pixel-level mask annotations. To tackle…

Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular value decomposition (SVD) has emerged as an effective post-training compression…

$N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M$ sparsity methods compress neural networks with a…

Networked systems usually face different random uncertainties that make the performance of the least-squares (LS) linear filter decline significantly. For this reason, great attention has been paid to the search for other kinds of…