Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
Research paper by Yi-Fan Zhang and collaborators. Published 2024-06-12. Topics: Large Multimodal Models, high resolution, resolution upscaling, global view, adapters.
Resource information
- Authors
- Yi-Fan Zhang, Qingsong Wen, Chaoyou Fu, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin
- Research topics
- Large Multimodal Models, high resolution, resolution upscaling, global view, adapters, local patches, learnable query embeddings, similarity-based selector, less is more, end-to-end training, alternating training, local compression
- Publication date
- 2024-06-12
- Publication
- arXiv
- Last record update
- Nov 3, 2026
