IEEE

CPERNN: An RNN-based Multi-scale Variable Interaction Model for electrical Time Series Forecasting

Abstract: Long-Term Time Series Forecasting plays a critical role in key domains such as electrical load prediction. Particularly, electrical time series data exhibit characteristics like ...
IEEE

Vision-Language Model-Driven Human-Vehicle Interaction for Autonomous Driving: Status, Challenge, and Innovation

Abstract: This paper investigates the potential of Vision-Language Models (VLMs) to enhance Human-Vehicle Interaction (HVI) in Autonomous Driving (AD) scenarios, particularly in interactions between ...
IEEE

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Abstract: Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardware ...
IEEE

Enabling Decoder-only Language Model Inference on a CNN Accelerator

Abstract: The remarkable success of Transformer architectures in Natural Language Processing (NLP) has led to increased demand for embedded systems capable of efficiently handling NLP tasks along with ...
IEEE

Efficient Cloud Removal for Remote Sensing Data Transmission via Model Compression and Sparse Accelerator Design

Abstract: Cloud coverage significantly degrades the quality and usability of remote sensing imagery, while also leading to unnecessary bandwidth consumption and power expenditure in satellite payloads ...
IEEE

Representation of Human arm Dynamic Intents With an Electrical Impedance Tomography (EIT)-Driven Musculoskeletal Model for Human–Robot Interaction

Abstract: Representing human arm dynamic intent is essential for effective human–robot interaction. Accurately and robustly decoding these intentions through mathematical modeling of neuromuscular ...
IEEE

Personalized User Interaction in Web Applications using Adaptive LLM Model

Abstract: The rapid evolution of web applications has made personalization and intuitive user experiences increasingly essential. The aim of this work is to provide a tailored large language model ...
IEEE

SA-DS: A Dataset for Large Language Model-Driven AI Accelerator Design Generation

Abstract: In the ever-evolving landscape of Deep Neural Networks (DNN) hardware acceleration, unlocking the true potential of systolic array accelerators has long been hindered by the daunting ...
IEEE

Exploiting Output Activation Sparsity Using Bit-Separable Multiplier in CNN Accelerator

Abstract: This paper demonstrates a bit-separable multiplier (BSM) in CNN accelerators to leverage output activation sparsity. BSM improves computational efficiency by predicting the output of ...
IEEE

A Low-Cost Multiplier-Free Accelerator for Binary Neural Network

Abstract: With the rapid development of artificial intelligence (AI), deploying deep learning models on resource-constrained edge devices has become increasingly challenging due to computational power ...
Geeky Gadgets

Awesome DIY Raspberry Pi 5 Offline AI Companion Inspired by BMO from Adventure Time

What if you could build your own personal AI companion, one that’s entirely offline, respects your privacy, and fits in the palm of your hand? brenpoly explores how a Raspberry Pi 5, a few carefully ...