Oleksii Kuchaiev
15 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (6) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Academic Marathon (7)
π
Cross-Pollinator
(11)
πΊοΈ
Taxonomy Completionist
(38)
π
Renaissance Researcher
(5)
π§¬
Topic Evolution
π
Conference Pioneer
β
The Questioner
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(62)
π
Century Club
(15)
Conferences
ACL (4)
EMNLP (4)
ICLR (2)
INTERSPEECH (2)
NAACL (2)
NIPS (1)
Top co-authors
Keywords
automatic speech recognition
(4)
language model
(3)
neural machine translation
(3)
large language model
(3)
end-to-end model
(3)
retrieval-augmented generation
(2)
supervised fine-tuning
(2)
word error rate
(2)
speech translation
(2)
preference learning
(2)
model alignment
(2)
low-rank adaptation
(2)
model editing
(1)
language model alignment
(1)
machine translation
(1)
preference optimization
(1)
knowledge distillation
(1)
reward modeling
(1)
human feedback
(1)
text generation
(1)
Papers
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
ACL 2025
HelpSteer2-Preference: Complementing Ratings with Preferences
ICLR 2025
HelpSteer 2: Open-source dataset for training top-performing reward models
NIPS 2024
GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning
EMNLP 2024
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
NAACL 2024
Tied-LoRA: Enhancing parameter efficiency of LoRA with Weight Tying
NAACL 2024
Leveraging Synthetic Targets for Machine Translation
ACL 2023
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
EMNLP 2023
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
EMNLP 2023
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022
ACL 2022
NVIDIA NeMoβs Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21
EMNLP 2021
SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition
INTERSPEECH 2021
Jasper: An End-to-End Convolutional Neural Acoustic Model
INTERSPEECH 2019
OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models
ACL 2018
Mixed Precision Training
ICLR 2018