# Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation

arXiv: https://arxiv.org/abs/2410.10319 · HTML: https://mlsanity.com/paper/2410.10319/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [MobileVLM V2: Faster and Stronger Baseline for Vision Language Model](https://mlsanity.com/paper/2402.03766/) (2024)
- [InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD](https://mlsanity.com/paper/2404.06512/) (2024)
- [SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models](https://mlsanity.com/paper/2402.05935/) (2024)
- [OtterHD: A High-Resolution Multi-modality Model](https://mlsanity.com/paper/2311.04219/) (2023)

## Built on by (most cited first, 1 of 1)

- [MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs](https://mlsanity.com/paper/2606.31383/) (2026)

## Abstract (arXiv)

The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of the MLLM. Current explorations on the projector focus on reducing the number of visual tokens to improve efficiency, often overlooking the inherent spatial discrepancy between the serialized 2-dimensional visual token sequences and natural language token sequences. A Spatial-Aware Efficient Projector (SAEP) is proposed to address this issue. In detail, our SAEP method employs an modified separable depthwise convolution module on multi-layer visual features to enhance the spatial information of visual tokens. As a result, our SAEP method can not only largely reduce the number of visual tokens by 75%, but also significantly improve the multimodal spatial understanding capability of MLLMs. Moreover, compared to existing projectors, our SAEP gets best performances on massive multimodal evaluation benchmarks, which denotes its effectiveness on bridging the modality gap.