Maxim Krikun
7 papers · 2019–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (14) π Conference Polyglot (5) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π₯
Mega-Team
(27)
Conferences
ICLR (2)
ICML (2)
EMNLP (1)
INTERSPEECH (1)
NAACL (1)
Top co-authors
Keywords
machine translation
(3)
neural machine translation
(2)
parameter efficiency
(2)
mixture of expert
(2)
self-supervised learning
(1)
knowledge distillation
(1)
in-context learning
(1)
text generation
(1)
prompt-based learning
(1)
low-resource language
(1)
sparse model
(1)
sparse activation
(1)
inference optimization
(1)
inference throughput
(1)
data weighting
(1)
training curriculum
(1)
subtitle translation
(1)
markup transfer
(1)
timed bleu
(1)
neural network
(1)
Papers
The Unreasonable Effectiveness of Few-shot Learning for Machine Translation
ICML 2023
Scaling Laws for Neural Machine Translation
ICLR 2022
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
Subtitle Translation as Markup Translation
INTERSPEECH 2021
Reinforcement Learning based Curriculum Optimization for Neural Machine Translation
NAACL 2019