MSQ: Memory-Efficient Bit Sparsification Quantization

Documenti analoghi

• TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision
  di: Kim, Jinhee, et al.
  Pubblicazione: (2025)
• MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
  di: Wang, Dongwei, et al.
  Pubblicazione: (2026)
• Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
  di: Kim, Jinhee, et al.
  Pubblicazione: (2025)
• Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators
  di: Kim, Jiyoon, et al.
  Pubblicazione: (2025)
• MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures
  di: Kang, Do Yeong, et al.
  Pubblicazione: (2025)