Vedanuj Goswami
15 papers · 2020–2023 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (38) π§ Keyword Pioneer π Interdisciplinary Bridge
π
Conference Polyglot
(9)
π
Cross-Pollinator
(5)
π
Century Club
(15)
ποΈ
Keyword Collector
(69)
β‘
Prolific Year
(7)
Conferences
ACL (3)
CVPR (2)
EMNLP (2)
ICLR (2)
NIPS (2)
EACL (1)
INTERSPEECH (1)
NAACL (1)
WACV (1)
Top co-authors
Keywords
multilingual translation
(4)
machine translation
(4)
multilingual machine translation
(4)
multimodal learning
(3)
transfer learning
(3)
cross-lingual transfer
(2)
visual question answering
(2)
transformer architecture
(2)
multilingual model
(2)
multi-task learning
(2)
mixture of expert
(2)
parallel corpus
(2)
data augmentation
(1)
temporal modeling
(1)
self-supervised learning
(1)
action recognition
(1)
representation learning
(1)
cross-modal learning
(1)
motion estimation
(1)
neural machine translation
(1)
Papers
Revisiting Machine Translation for Cross-lingual Classification
EMNLP 2023
Small Data, Big Impact: Leveraging Minimal Data for Effective Machine Translation
ACL 2023
Causes and Cures for Interference in Multilingual Translation
ACL 2023
MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation
INTERSPEECH 2023
SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations
ACL 2023
Language-Aware Multilingual Machine Translation with Self-Supervised Learning
EACL 2023
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
EMNLP 2023
Tricks for Training Sparse Translation Models
NAACL 2022
FLAVA: A Foundational Language and Vision Alignment Model
CVPR 2022
Only Time Can Tell: Discovering Temporal Data for Temporal Modeling
WACV 2021
Human-Adversarial Visual Question Answering
NIPS 2021
Creative Sketch Generation
ICLR 2021
MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond
ICLR 2021
12-in-1: Multi-Task Vision and Language Representation Learning
CVPR 2020
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
NIPS 2020