Ankush Garg
7 papers · 2021–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (11)
π
Triple Crown
β
The Questioner
Conferences
NIPS (3)
ICLR (2)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
neural machine translation
(2)
multi-task learning
(2)
in-context learning
(1)
empirical study
(1)
deep learning
(1)
optimization algorithm
(1)
language model
(1)
multilingual learning
(1)
machine translation evaluation
(1)
fine-grained evaluation
(1)
multi-task optimization
(1)
data scaling
(1)
large language model
(1)
weighted loss
(1)
neural network
(1)
multidimensional quality metrics
(1)
error categorization
(1)
power law
(1)
deep multi-task learning
(1)
task loss weighting
(1)
Papers
The Devil Is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
EMNLP 2023
Binarized Neural Machine Translation
NIPS 2023
Order Matters in the Presence of Dataset Imbalance for Multilingual Learning
NIPS 2023
Do Current Multi-Task Optimization Methods in Deep Learning Even Help?
NIPS 2022
A Loss Curvature Perspective on Training Instabilities of Deep Learning Models
ICLR 2022
Data Scaling Laws in NMT: The Effect of Noise and Architecture
ICML 2022
The geometry of integration in text classification RNNs
ICLR 2021