ICML "multimodal representations" Papers
2 papers found
Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
Ishaan Rawal, Alexander Matyasko, Shantanu Jaiswal et al.
ICML 2024posterarXiv:2306.08889
Improving fine-grained understanding in image-text pre-training
Ioana Bica, Anastasija Ilic, Matthias Bauer et al.
ICML 2024posterarXiv:2401.09865