Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
paper
Fields
id
sources/pap-attn-qwen2-vl-mropePublisher
arXiv
Kind
paper
Published
2024-09-18
Accessed
2026-10-03
notes
arXiv preprint; no journal_ref. Introduces M-RoPE for multimodal position encoding.
Notes
arXiv preprint; no journal_ref. Introduces M-RoPE for multimodal position encoding.
Cross-references
This record references no other records.