ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters

Documenti analoghi

• Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting
  di: Shahidzadeh, Mohammad, et al.
  Pubblicazione: (2024)
• DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
  di: Ghavami, Behnam, et al.
  Pubblicazione: (2024)
• A Semi Black-Box Adversarial Bit-Flip Attack with Limited DNN Model Information
  di: Ghavami, Behnam, et al.
  Pubblicazione: (2024)
• Compressing Deep Neural Networks Using Explainable AI
  di: Soroush, Kimia, et al.
  Pubblicazione: (2025)
• QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
  di: Zandieh, Amir, et al.
  Pubblicazione: (2024)