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

Leviathan et al.

mentions 1 type Person feed RSS

// recent coverage 1 mentions

09:33
2026-09-17
leoniemonigatti.com
large-language-models

Speculative decoding makes LLMs go brrr

Speculative decoding, an inference optimization introduced independently by Chen et al. at DeepMind and Leviathan et al. at Google in 2023, cuts LLM decoding latency without changing output quality by…

// co-occurs with top 3 entities
DeepMind 1 Google 1 Chen et al. 1
// topics top 4 topics
large language models 1 ai research 1 ai infrastructure 1 machine learning 1