Published Feb 24, 2020
107 - Multi-Modal Transformers, with Hao Tan and Mohit Bansal
Delve into the world of multi-modal transformers with experts Hao Tan and Mohit Bansal as they explore the innovative LXMERT model, highlighting its superior pre-training techniques, cross-modal learning benefits, and groundbreaking integration of vision and language through advanced embedding and cross attention.
