Related papers: SparseDVFS: Sparse-Aware DVFS for Energy-Efficient…

A recent trend in DNN development is to extend the reach of deep learning applications to platforms that are more resource and energy constrained, e.g., mobile devices. These endeavors aim to reduce the DNN model size and improve the…

Diffusion models (DMs) excel in image generation but suffer from slow inference and training-inference discrepancies. Although gradient-based solvers for DMs accelerate denoising inference, they often lack theoretical foundations in…

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize…

Recently, sparse training has emerged as a promising paradigm for efficient deep learning on edge devices. The current research mainly devotes efforts to reducing training costs by further increasing model sparsity. However, increasing…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

This work proposes a novel Energy-Aware Network Operator Search (ENOS) approach to address the energy-accuracy trade-offs of a deep neural network (DNN) accelerator. In recent years, novel inference operators have been proposed to improve…

Recently, there has been a trend of shifting the execution of deep learning inference tasks toward the edge of the network, closer to the user, to reduce latency and preserve data privacy. At the same time, growing interest is being devoted…

Exploiting sparsity in deep neural networks (DNNs) has been a promising area for meeting the growing computation requirements. To minimize the overhead of sparse acceleration, hardware designers have proposed structured sparsity support,…

This paper proposes Semantic Inference (SINF) that creates semantic subgraphs in a Deep Neural Network(DNN) based on a new Discriminative Capability Score (DCS) to drastically reduce the DNN computational load with limited performance…

Distributed systems can be found in various applications, e.g., in robotics or autonomous driving, to achieve higher flexibility and robustness. Thereby, data flow centric applications such as Deep Neural Network (DNN) inference benefit…

Training deep neural networks (DNNs) on edge devices has attracted increasing attention due to its potential to address challenges related to domain adaptation and privacy preservation. However, DNNs typically rely on large datasets for…

On-chip buses are typically designed to meet performance constraints at worst-case conditions, including process corner, temperature, IR-drop, and neighboring net switching pattern. This can result in significant performance slack at more…

Fiber-optic sensing, especially distributed optical fiber vibration (DVS) sensing, is gaining importance in internet of things (IoT) applications, such as industrial safety monitoring and intrusion detection. Despite their wide application,…

Deep learning has driven significant technological advancements, but its high energy consumption limits its use on battery-operated edge devices. Spiking Neural Networks (SNNs) offer promising reductions in inference-time energy…

DNNs are ubiquitous on edge devices nowadays. With its increasing importance and use cases, it's not likely to pack all DNNs into device memory and expect that each inference has been warmed up. Therefore, cold inference, the process to…

Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using…

The increasing pervasiveness of intelligent mobile applications requires to exploit the full range of resources offered by the mobile-edge-cloud network for the execution of inference tasks. However, due to the heterogeneity of such…

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a small subset of parameters. While current PEFT methods have…