JB Huang launches quantization video series, starting with the fundamentals

jbhuang0604 · x · 2026-11-18

jbhuang0604 launched a new video series on low-precision ML. Episode one, 'How Neural Nets Survive Fewer Bits', covers quantization fundamentals — why low-precision models are faster, lighter and more energy-efficient. Upcoming episodes will cover weight/activation/KV-cache quantization, rotation-based techniques, and low-precision training.

Related event: UIUC Professor Launches Video Series on Neural Network Quantization(2 posts)→

Original post →

More from Research

Research channel →