Dmitry Lepikhin

3 papers · 2021–2022 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

EMNLP (1) ICLR (1) ICML (1)

Top co-authors

Orhan Firat (3) Maxim Krikun (3) Yanping Huang (3) zhifeng Chen (2) Yuanzhong Xu (2) Zongwei Zhou (1) Dehao Chen (1) Noam Shazeer (1) Kellie Webster (1) Kun Zhang (1)

Research topics

Deep Learning (2) Machine Learning (2) Natural Language Processing (2) Application Areas (2) Architectures (2) Optimization & Theory · Machine Learning (2) Applications (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Resources & Methods (1)

Keywords

mixture of expert (3) parameter efficiency (2) machine translation (1) conditional computation (1) multilingual machine translation (1) sparse model (1) sparse activation (1) inference optimization (1) model scaling (1) inference throughput (1) neural network (1) few-shot performance (1) efficient scaling (1) model compression (1) automatic sharding (1) knowledge distillation (1)

Papers

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts ICML 2022 Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021 GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding ICLR 2021