Mohammadreza Banaei
4 papers · 2021–2023 · 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
(17)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(4)
Natural Language Processing
(4)
Core AI
(4)
Resources & Methods
(4)
Machine Learning
(3)
Application Areas
(2)
Deep Learning
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types
(1)
Optimization & Theory
(1)
Techniques
(1)
Keywords
model compression
(2)
matrix factorization
(2)
multilingual language model
(2)
offline compression
(1)
logical reasoning
(1)
attention mechanism
(1)
cross-lingual transfer
(1)
language model
(1)
inference efficiency
(1)
autoencoder architecture
(1)
word embedding
(1)
transformer language model
(1)
language-neutral representation
(1)
transformer-based model
(1)
cross-lingual task
(1)
transformer model
(1)
embedding compression
(1)
cross-lingual reasoning
(1)
code-switched reasoning
(1)
word embedding compression
(1)
Papers
Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention
EMNLP 2023
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models
EACL 2023
Discovering Language-neutral Sub-networks in Multilingual Language Models
EMNLP 2022
Direction is what you need: Improving Word Embedding Compression in Large Language Models
ACL 2021