cd/entity/Xu et al.· home› entities› Xu et al.
grep -l @xu et al. /news/*.json | wc -l → 1

Xu et al.

mentions 1 type Person feed RSS

// recent coverage 1 mentions

15:36
2026-08-04
pub.towardsai.net
ai-safety

Why Standard LLM Audits Miss 90% of Safety Failures

A new analysis warns that standard LLM safety audits miss up to 90% of failures because models are tested at full precision (FP16) but deployed under 4-bit or 8-bit Post-Training Quantization (PTQ), w…

// co-occurs with top 4 entities
Wee et al. 1 Yi et al. 1 Al Hakim et al. 1 Frantar et al. 1
// topics top 3 topics
ai safety 1 ai research 1 ai infrastructure 1