Ahmet Üstün
24 papers · 2018–2026 · 7 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 ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (52) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
👥
Mega-Team · Squad
🤝
Dynamic Duo
(10)
❓
The Questioner
(4)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
📈
Trend Setter
🗃️
Keyword Collector
(118)
Top co-authors
Research topics
Machine Learning
(19)
Natural Language Processing
(17)
Deep Learning
(13)
Artificial Intelligence
(11)
Resources & Methods
(11)
Learning Types · Machine Learning
(10)
Application Areas
(8)
Core AI
(8)
Learning Types · Deep Learning
(8)
Applications
(7)
Architectures
(5)
Learning Paradigms
(5)
Optimization & Theory
(4)
Core Methods
(3)
Models
(3)
Keywords
large language model
(7)
transfer learning
(4)
machine translation
(4)
model compression
(4)
mixture of expert
(3)
multilingual language model
(3)
dependency parsing
(3)
reinforcement learning from human feedback
(3)
adapter module
(3)
unsupervised translation
(2)
parameter-efficient fine-tuning
(2)
instruction fine-tuning
(2)
zero-shot learning
(2)
morphological tagging
(2)
model quantization
(2)
model alignment
(2)
attention mechanism
(2)
multi-task learning
(2)
cross-lingual transfer
(2)
language model alignment
(2)
Papers
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
ACL 2026
Command-A-Translate: Raising the Bar of Machine Translation with Difficulty Filtering
EMNLP 2025
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Experts
EMNLP 2025
To Code or Not To Code? Exploring Impact of Code in Pre-training
ICLR 2025
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
EMNLP 2025
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
ACL 2024
Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model
ACL 2024
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs
ACL 2024
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
NeurIPS 2024
How Does Quantization Affect Multilingual LLMs?
EMNLP 2024
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
ICLR 2024
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
EMNLP 2024
Intriguing Properties of Quantization at Scale
NeurIPS 2023
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer
EMNLP 2022
When does Parameter-Efficient Transfer Learning Work for Machine Translation?
EMNLP 2022
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
NAACL 2021
Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP
EACL 2021
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters
EMNLP 2021
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions
EACL 2021
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
EMNLP 2021
FiSSA at SemEval-2020 Task 9: Fine-tuned for Feelings
SemEval 2020
UDapter: Language Adaptation for Truly Universal Dependency Parsing
EMNLP 2020
Multi-Team: A Multi-attention, Multi-decoder Approach to Morphological Analysis.
ACL 2019
Characters or Morphemes: How to Represent Words?
ACL 2018