相关论文: TinyFormer: Efficient Transformer Design and Deplo…

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications involving…

Machine learning (ML) models are widely used in many important domains. For efficiently processing these computational- and memory-intensive applications, tensors of these over-parameterized models are compressed by leveraging sparsity,…

The paradigm shift towards local and on-device inference under stringent resource constraints is represented by the tiny machine learning (TinyML) domain. The primary goal of TinyML is to integrate intelligence into tiny, low-cost devices…

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by…

Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…

Faster inference of deep learning models is highly demanded on edge devices and even servers, for both financial and environmental reasons. To address this issue, we propose SoftNeuro, a novel, high-performance inference framework with…

Due to reduced manufacturing yields, traditional monolithic chips cannot keep up with the compute, memory, and communication demands of data-intensive applications, such as rapidly growing deep neural network (DNN) models. Chiplet-based…

Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a…

In this paper, we demonstrate a compiler that can optimize sparse and recurrent neural networks, both of which are currently outside of the scope of existing neural network compilers (sparse neural networks here stand for networks that can…

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering…

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

AI's widespread integration has led to neural networks (NNs) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained…

Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datasets and substantial…

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because…

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,…

The depth completion task is a critical problem in autonomous driving, involving the generation of dense depth maps from sparse depth maps and RGB images. Most existing methods employ a spatial propagation network to iteratively refine the…

Modern deep learning approaches usually utilize modality-specific processing. For example, the most common deep learning approach to image classification involves decoding image file bytes into an RGB tensor which is passed into a neural…

By identifying four important components of existing LiDAR-camera 3D object detection methods (LiDAR and camera candidates, transformation, and fusion outputs), we observe that all existing methods either find dense candidates or yield…

Communication efficiency in federated learning (FL) remains a critical challenge for resource-constrained environments. While prototype-based FL reduces communication overhead by sharing class prototypes-mean activations in the penultimate…