# LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs

arXiv: https://arxiv.org/abs/2507.00505 · HTML: https://mlsanity.com/paper/2507.00505/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 54 of its 64 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 30 of 54)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)

## Built on by (most cited first, 8 of 8)

- [ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models](https://mlsanity.com/paper/2604.12251/) (2026)
- [RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios](https://mlsanity.com/paper/2512.24561/) (2025)
- [PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding](https://mlsanity.com/paper/2605.30126/) (2026)
- [SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs](https://mlsanity.com/paper/2604.13710/) (2026)
- [TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction](https://mlsanity.com/paper/2607.04484/) (2026)
- [STAR: A Spatial-Topology Aware Routing Framework for Generalizable 3D Scene Understanding](https://mlsanity.com/paper/2608.11699/) (2026)
- [SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem](https://mlsanity.com/paper/2609.07064/) (2026)
- [Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack](https://mlsanity.com/paper/2609.37096/) (2026)

## Abstract (arXiv)

The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local relationships between adjacent patches, leading to weaker visual representation, which in turn affects the detailed understanding ability of MLLMs. To solve this, we propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation. Our approach offers three key advantages: 1) We propose a novel Projector, which uses convolutional kernels to derive visual spatial tokens from ViT patch features, simulating two visual spatial ordering approaches: "from central region to global" and "from abstract to specific". Then, a cross-attention mechanism is applied to fuse fine-grained visual information, enriching the overall visual representation. 2) We present two model variants: LLaVA-SP-Cropping, which focuses on detail features through progressive cropping, and LLaVA-SP-Pooling, which captures global semantics through adaptive pooling, enabling the model to handle diverse visual understanding tasks. 3) Extensive experiments show that LLaVA-SP, fine-tuned with LoRA, achieves significant performance improvements across various multimodal benchmarks, outperforming the state-of-the-art LLaVA-1.5 model in multiple tasks with nearly identical inference latency. The code and models are available at https://github.com/CnFaker/LLaVA-SP.