Ajay Patel
14 papers · 2018–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (7) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (8) π Cross-Pollinator (7)
πΊοΈ
Taxonomy Completionist
(37)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π₯
Mega-Team
(50)
π€
Dynamic Duo
(12)
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(66)
π
Century Club
(14)
Conferences
ACL (4)
EMNLP (3)
NAACL (2)
AAAI (1)
COLING (1)
CVPR (1)
EACL (1)
ICLR (1)
Top co-authors
Keywords
synthetic data generation
(3)
large language model
(3)
authorship attribution
(3)
text style transfer
(2)
multimodal learning
(2)
data augmentation
(2)
style embedding
(2)
contrastive learning
(2)
interpretable embedding
(2)
vision-language model
(2)
visual question answering
(1)
text generation
(1)
prompt engineering
(1)
image captioning
(1)
style transfer
(1)
few-shot learning
(1)
cross-lingual transfer
(1)
machine unlearning
(1)
gradient-based optimization
(1)
paraphrase generation
(1)
Papers
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
CVPR 2025
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples
NAACL 2025
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
ACL 2025
Quantifying Misattribution Unfairness in Authorship Attribution
ACL 2025
mStyleDistance: Multilingual Style Embeddings and their Evaluation
ACL 2025
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
COLING 2025
ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer
AAAI 2024
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
ACL 2024
TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
EMNLP 2024
Learning Interpretable Style Embeddings via Prompting LLMs
EMNLP 2023
Multilingual Bidirectional Unsupervised Translation through Multilingual Finetuning and Back-Translation
EACL 2023
Bidirectional Language Models Are Also Few-shot Learners
ICLR 2023
TopGuNN: Fast NLP Training Data Augmentation using Large Corpora
NAACL 2021
Magnitude: A Fast, Efficient Universal Vector Embedding Utility Package
EMNLP 2018