Papers with vision-aided unsupervised constituency parsing
Vision-aided Unsupervised Constituency Parsing with Multi-MLLM Debating (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches require explicit cross-modal alignment, but new approaches address these challenges. |
| Approach: | They propose a framework for vision-aided unsupervised constituency parsing . they leverage multimodal large language models pre-trained on diverse image-text or video-text data . |
| Outcome: | The proposed framework achieves state-of-the-art performance on image-text and video-text datasets, improving robustness and accuracy. |