| title | LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? |
|---|---|
| authors | Kechen Fang, Yihua Qin, Chongyi Wang, Wenshuo Ma, Tianyu Yu, Yuan Yao |
| date | 2026-05-09 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.08985 |
| upvotes | 23 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT compression. Global encoding produces massive token sequences, while post-ViT compression incurs the full quadratic attention cost of the ViT before any token reduction takes place. In this work, we revisit this convention along two dimensions: the encoding strategy and visual token compression. First, controlled experiments show that slice-based encoding outperforms global encoding across benchmarks, suggesting that preserving local details through sliced views can be more beneficial than applying global attention for fine-grained perception. Second, we introduce intra-ViT early compression, which reduces tokens in shallow ViT layers and substantially lowers visual-encoding FLOPs while preserving downstream performance. By integrating intra-ViT compression into the slice-based encoding framework, we present LLaVA-UHD v4, an efficient and compute-controllable visual encoding scheme tailored for high-resolution inputs. Across a diverse set of benchmarks covering document understanding, OCR, and general VQA, LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% while matching or even surpassing baseline performance. These results suggest that visual-encoding efficiency can be substantially improved without sacrificing downstream performance, providing a practical design direction for efficient high-resolution MLLMs. All model weights and code will be publicly released to support further research. |
cite
@misc{fang2026llava,
title={LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?},
author={Kechen Fang and Yihua Qin and Chongyi Wang and Wenshuo Ma and Tianyu Yu and Yuan Yao},
year={2026},
eprint={2605.08985},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.08985}
}