Marcin Chochowski
5 papers · 2018–2024 · 4 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(4)
Natural Language Processing
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Application Areas
(3)
Applications · Natural Language Processing
(3)
Core AI
(2)
Learning Types · Deep Learning
(2)
Computer Science
(1)
Applications · Computer Science
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Keywords
neural machine translation
(3)
multilingual model
(2)
knowledge distillation
(2)
data augmentation
(1)
document-level translation
(1)
parallel corpus
(1)
system combination
(1)
model pruning
(1)
low-resource language
(1)
language model
(1)
synthetic data
(1)
model ensemble
(1)
model ensembling
(1)
compression ratio
(1)
beam search
(1)
throughput increase
(1)
key-value cache compression
(1)
low-resource translation
(1)
neural network
(1)
basque english
(1)
Papers
Compact Language Models via Pruning and Knowledge Distillation
NeurIPS 2024
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
ICML 2024
Samsung R&D Institute Poland submission to WAT 2021 Indic Language Multilingual Task
ACL 2021
Samsung R&D Institute Poland submission to WMT20 News Translation Task
EMNLP 2020
Samsung and University of Edinburgh’s System for the IWSLT 2018 Low Resource MT Task
EMNLP 2018