All Stories

  1. SparseDroop: Hardware–Software Co-Design for Mitigating Voltage Droop in DNN Accelerators
  2. Demo Abstract: A Low-Power Real-Time Hardware Accelerator for Edge Detection Using Stochastic Computing
  3. Demo Abstract: ECO: Low Power Context-Aware Multimodal AI on NPUs
  4. LLM-NPU: Towards Efficient Foundation Model Inference on Low-Power Neural Processing Units
  5. PRISM: Toward Energy-Efficient AIoT with Processing-In-Sensor+Memory in Battery-Free Devices
  6. DRAX: Revolutionizing Energy-Efficient DNN Collaboration
  7. Towards Energy-Accuracy Scalable Multimodal Cognitive Systems
  8. HIPEDAP: Energy-Efficient Hardware Accelerators for Hidden Periodicity Detection
  9. HIPER: Low Power, High Performance and Area-Efficient Hardware Accelerators for Hidden Periodicity Detection using Ramanujan Filter Banks
  10. An Efficient Multiplier-less Hardware for Hidden Periodicity Detection Using Ramanujan Filter Bank