 EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge
Distillation and Modal-adaptive PruningAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Write and Paint: Generative Vision-Language Models are Unified Modal
LearnersInternational Conference on Learning Representations (ICLR), 2022 |
 BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions DatasetInternational Conference on Language Resources and Evaluation (LREC), 2022 |
 Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual
ConceptsInternational Conference on Machine Learning (ICML), 2021 |
