Related papers: UniFormer: Unified and Efficient Transformer for R…
Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art…
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that…
For decades, advances in electronics were directly driven by the scaling of CMOS transistors according to Moore's law. However, both the CMOS scaling and the classical computer architecture are approaching fundamental and practical limits,…
Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…
Deploying learning-based controllers across heterogeneous robots is challenging due to platform differences, inconsistent interfaces, and inefficient middleware. To address these issues, we present UniCon, a lightweight framework that…
One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in…
Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises…
The predictive power of Convolutional Neural Networks (CNNs) has been an integral factor for emerging latency-sensitive applications, such as autonomous drones and vehicles. Such systems employ multiple CNNs, each one trained for a…
With the growing model size, deep neural networks (DNN) are increasingly trained over massive GPU accelerators, which demands a proper parallelization plan that transforms a DNN model into fine-grained tasks and then schedules them to GPUs…
Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational…
In recent years, Convolutional Neural Networks (ConvNets) have become an enabling technology for a wide range of novel embedded Artificial Intelligence systems. Across the range of applications, the performance needs vary significantly,…
Implementing convolutional neural networks (CNNs) on field-programmable gate arrays (FPGAs) has emerged as a promising alternative to GPUs, offering lower latency, greater power efficiency and greater flexibility. However, this development…
As more deep learning models are being applied in real-world applications, there is a growing need for modeling and learning the representations of neural networks themselves. An efficient representation can be used to predict target…
In this paper, a scalable neural network hardware architecture for image segmentation is proposed. By sharing the same computing resources, both convolution and deconvolution operations are handled by the same process element array. In…
Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…
Artificial intelligence (AI) research today is largely driven by ever-larger neural network models trained on graphics processing units (GPUs). This paradigm has yielded remarkable progress, but it also risks entrenching a hardware lottery…
Transformers have become the dominant architecture across a wide range of domains, largely due to the effectiveness of multi-head attention in capturing diverse representation subspaces. However, standard multi-head attention activates all…
Recently, Graph Transformers have emerged as a promising solution to alleviate the inherent limitations of Graph Neural Networks (GNNs) and enhance graph representation performance. Unfortunately, Graph Transformers are computationally…
Traffic forecasting is a cornerstone of smart city management, enabling efficient resource allocation and transportation planning. Deep learning, with its ability to capture complex nonlinear patterns in spatiotemporal (ST) data, has…
Graph neural networks (GNNs) have pushed the state-of-the-art (SOTA) for performance in learning and predicting on large-scale data present in social networks, biology, etc. Since integrated circuits (ICs) can naturally be represented as…