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)→
More from Research
- Eval methodology: statistical tests are valid, but conclusions must span prompt, judge, and harness variance — srchvrs · 2026-11-18
- RL lecturer shares lecture slides: supervised learning approximates, RL discovers functions — KyleMorgenstein · 2026-11-18
- Supervised vs self-supervised is a false dichotomy: RL is where it ends up — KyleMorgenstein · 2026-11-18
- "Supervised vs self-supervised" is a false dichotomy, argues UT RL lecturer — KyleMorgenstein · 2026-11-18
- ELLIS Sites NeurIPS Fest 2026 returns across Europe with 18 accepted NeurIPS papers — DocXavi · 2026-11-18
- Decompiled Instagram APK reveals on-device models and probing for 23 installed AI apps — ChenhaoTan · 2026-11-18