Liam Fedus

3 papers · 2021–2023 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 👥 Mega-Team (67) ❓ The Questioner

Conferences

EMNLP (1) ICML (1) JMLR (1)

Top co-authors

Nan Du (2) Toju Duke (2) Noam Shazeer (2) Yanqi Zhou (2) Yi Tay (2) Hyung Won Chung (2) Adam Roberts (2) Zongwei Zhou (2) Marie Pellat (2) Kevin Robinson (2)

Keywords

transformer architecture (1) few-shot learning (1) mixture of expert (1) sparse activation (1) parameter efficiency (1) multi-step reasoning (1) nlp application (1) large language model (1) few-shot performance (1) architecture modification (1) implementation detail (1) efficient scaling (1)

Papers

PaLM: Scaling Language Modeling with Pathways JMLR 2023

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts ICML 2022

Do Transformer Modifications Transfer Across Implementations and Applications? EMNLP 2021