Jingtong Hu

Latest

• ART: Customizing Accelerators for DNN-Enabled Real-Time Safety-Critical Systems(🔥📣New Paper & Project🔥📣! )
• EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
• CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
• CHEF: A Framework for Deploying Heterogeneous Models on Clusters with Heterogeneous FPGAs (🔥📣New Paper & Project🔥📣! )
• SCARIF: Towards Carbon Modeling of Cloud Servers with Accelerators (🔥📣New Paper & Project🔥📣! )
• Enabling On-Device Self-Supervised LLM Personalization with Selective Synthetic Data (🔥📣New Paper & Project🔥📣! )
• SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (🔥📣New Paper & Project🔥📣! )
• CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture (🔥📣New Paper & Project🔥📣! )
• Sustainable AI Processing at the Edge
• H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness
• EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization
• Algorithm-hardware Co-design of Attention Mechanism on FPGA Devices