2

EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
PDF Slides
CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
Cite PDF Code
CHEF: A Framework for Deploying Heterogeneous Models on Clusters with Heterogeneous FPGAs (🔥📣New Paper & Project🔥📣! )
PDF
Sustainable AI Processing at the Edge
PDF Cite
EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization
Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles …
PDF Cite
Algorithm-hardware Co-design of Attention Mechanism on FPGA Devices
Multi-head self-attention (attention mechanism) has been employed in a variety of fields such as machine translation, language …
PDF Cite
Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks (🔥Best Paper)
With the recent advancement of multilayer convolutional neural networks (CNN) and fully connected networks (FCN), deep learning has …
PDF Cite