Related papers: TorchSparse: Efficient Point Cloud Inference Engin…

The exponentially growing model size drives the continued success of deep learning, but it brings prohibitive computation and memory cost. From the algorithm perspective, model sparsification and quantization have been studied to alleviate…

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to…

Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs. Sparse Winograd merges these two and thus has the potential to offer a…

Graph-based Point Cloud Networks (PCNs) are powerful tools for processing sparse sensor data with irregular geometries, as found in high-energy physics detectors. However, deploying models in such environments remains challenging due to…

NVIDIA's 2:4 Sparse Tensor Cores deliver 2x throughput but demand strict 50% pruning -- a ratio that collapses LLM reasoning accuracy (Qwen3: 54% to 15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive no…

This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks deployed on resource-constrained devices at the edge of the…

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Driven by deep learning, there has been a surge of specialized processors for matrix multiplication, referred to as TensorCore Units (TCUs). These TCUs are capable of performing matrix multiplications on small matrices (usually 4x4 or…

General-purpose Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental kernel in scientific computing and deep learning. The emergence of new matrix computation units such as Tensor Cores (TCs) brings more opportunities for SpMM…

Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions…

Semantic understanding and completion of real world scenes is a foundational primitive of 3D Visual perception widely used in high-level applications such as robotics, medical imaging, autonomous driving and navigation. Due to the curse of…

Machine learning, particularly deep neural network inference, has become a vital workload for many computing systems, from data centers and HPC systems to edge-based computing. As advances in sparsity have helped improve the efficiency of…

Sparse Convolution (SC) is widely used for processing 3D point clouds that are inherently sparse. Different from dense convolution, SC preserves the sparsity of the input point cloud by only allowing outputs to specific locations. To…

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not…

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the…

Many recent GPUs feature matrix multiplication engines (aka Tensor Core Units or TCUs) that perform small fixed-size matrix-matrix products at very high throughput. They have been used very effectively to speed up dense matrix-matrix…

Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. In this paper, we advocate that…

Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models…

This work proposes a method for depth completion of sparse LiDAR data using a convolutional neural network which can be used to generate semi-dense depth maps and "almost" full 3D point-clouds with significantly lower root mean squared…

In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on…