Related papers: Deploying Machine Learning Models to Ahead-of-Time…

A lot of recent progress has been made in ultra low-bit quantization, promising significant improvements in latency, memory footprint and energy consumption on edge devices. Quantization methods such as Learned Step Size Quantization can…

Processing computer vision applications (CVA) on mobile devices is challenging due to limited battery life and computing power. While cloud-based remote processing of CVA offers abundant computational resources, it introduces latency issues…

The foundation-model ecosystem remains highly centralized because training requires immense compute resources and is therefore largely limited to large cloud operators. Edge-assisted foundation model training that harnesses spare compute on…

The increased demand for data privacy and security in machine learning (ML) applications has put impetus on effective edge training on Internet-of-Things (IoT) nodes. Edge training aims to leverage speed, energy efficiency and adaptability…

Convolutional Neural Networks (CNNs) are used for a wide range of image-related tasks such as image classification and object detection. However, a large pre-trained CNN model contains a lot of redundancy considering the task-specific edge…

Automated hand gesture recognition has been a focus of the AI community for decades. Traditionally, work in this domain revolved largely around scenarios assuming the availability of the flow of images of the user hands. This has partly…

System-on-Chip Field-Programmable Gate Arrays (SoC-FPGAs) offer significant throughput gains for machine learning (ML) edge inference applications via the design of co-processor accelerator systems. However, the design effort for training…

Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…

Energy modeling can enable energy-aware software development and assist the developer in meeting an application's energy budget. Although many energy models for embedded processors exist, most do not account for processor-specific…

Emerging multimodal LLMs (MLLMs) exhibit strong cross-modality perception and reasoning capabilities and hold great potential for various applications at edge. However, MLLMs typically consist of a compute-intensive modality encoder and a…

In this paper, an edge-side model training study is conducted on a resource-limited smart meter. The motivation of grid-edge intelligence and the concept of on-device training are introduced. Then, the technical preparation steps for…

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some…

Generative Artificial Intelligence (GenAI) applies models and algorithms such as Large Language Model (LLM) and Foundation Model (FM) to generate new data. GenAI, as a promising approach, enables advanced capabilities in various…

General matrix multiplication (GEMM) is a ubiquitous computing kernel/algorithm for data processing in diverse applications, including artificial intelligence (AI) and deep learning (DL). Recent shift towards edge computing has inspired…

Aiming at achieving artificial general intelligence (AGI) for Metaverse, pretrained foundation models (PFMs), e.g., generative pretrained transformers (GPTs), can effectively provide various AI services, such as autonomous driving, digital…

The advancements in machine learning opened a new opportunity to bring intelligence to the low-end Internet-of-Things nodes such as microcontrollers. Conventional machine learning deployment has high memory and compute footprint hindering…

The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" the bottleneck where data movement latency outstrips arithmetic throughput. Standard inference runtimes often incur significant…

Increasing AI computing demands and slowing transistor scaling have led to the advent of Multi-Chip-Module (MCMs) based accelerators. MCMs enable cost-effective scalability, higher yield, and modular reuse by partitioning large chips into…

Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource…