相关论文: HeSS: Head Sensitivity Score for Sparsity Redistri…

Heteroscedastic regression considering the varying noises among observations has many applications in the fields like machine learning and statistics. Here we focus on the heteroscedastic Gaussian process (HGP) regression which integrates…

The attention mechanism has demonstrated superior performance for inference over nodes in graph neural networks (GNNs), however, they result in a high computational burden during both training and inference. We propose FastGAT, a method to…

Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without requiring repeated model retraining. However, their scalability is often limited by the…

Consider a linear regression model where the design matrix X has n rows and p columns. We assume (a) p is much large than n, (b) the coefficient vector beta is sparse in the sense that only a small fraction of its coordinates is nonzero,…

3DGS is an emerging and increasingly popular technology in the field of novel view synthesis. Its highly realistic rendering quality and real-time rendering capabilities make it promising for various applications. However, when applied to…

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to…

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Stochastic optimization algorithms are widely used for large-scale data analysis due to their low per-iteration costs, but they often suffer from slow asymptotic convergence caused by inherent variance. Variance-reduced techniques have been…

We present ErasureHead, a new approach for distributed gradient descent (GD) that mitigates system delays by employing approximate gradient coding. Gradient coded distributed GD uses redundancy to exactly recover the gradient at each…

Long-context video understanding and generation pose a significant computational challenge for Transformer-based video models due to the quadratic complexity of self-attention. While existing sparse attention methods employ coarse-grained…

Sparsity-constrained optimization has wide applicability in machine learning, statistics, and signal processing problems such as feature selection and compressive Sensing. A vast body of work has studied the sparsity-constrained…

Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention…

In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…

Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication…

We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS). While 3DGS has proven effective for both real-time rendering and semantic scene understanding, prior works…

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

Human head detection, keypoint estimation, and 3D head model fitting are essential tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in…

High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across…

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are…

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…