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

• URL: http://arxiv.org/abs/2507.00505v3
• Date: Fri, 04 Jul 2025 13:15:34 GMT
• Title: LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
• Authors: Haoran Lou, Chunxiao Fan, Ziyan Liu, Yuexin Wu, Xinliang Wang,
• Abstract summary: We propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation.<n>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.
• Score: 4.478610052538001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression [1.8893427856534721]
  We propose InternVL-X, which outperforms the InternVL model in both performance and efficiency.<n>By utilizing 20% or fewer visual tokens, InternVL-X achieves state-of-the-art performance on 7 public MLLM benchmarks, and improves the average metric by 2.34% across 12 tasks.
  arXiv  Detail & Related papers  (2025-03-27T09:31:35Z)
• LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer [110.39467860530819]
  Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding.<n>We present LLaVA-UHD v2, an MLLM with advanced perception abilities by introducing a well-designed vision-language projector.<n>Hiwin transformer enhances MLLM's ability to capture diverse multi-modal visual granularities, by incorporating our constructed high-resolution semantic pyramid.
  arXiv  Detail & Related papers  (2024-12-18T14:07:46Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation.<n>We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE)<n>DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding [39.68348330596116]
  We propose modelname, a simple yet effective multi-layer feature fuser that efficiently integrates deep and shallow features from Vision Transformers (ViTs) Specifically, it leverages semantically aligned deep features as queries to dynamically extract missing details from shallow features. modelnameachieves significant improvements in visual representation and benchmark performance.
  arXiv  Detail & Related papers  (2024-10-15T17:55:22Z)
• Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See [37.7015406019386]
  Multimodal Large Language Models (MLLMs) treat visual tokens from visual encoders as text tokens.<n>As token counts grow, the quadratic scaling of computation in LLMs introduces an efficiency bottleneck.<n>In this study, we investigate the redundancy in visual computation at both the parameter and computational pattern levels within LLaVA.
  arXiv  Detail & Related papers  (2024-10-08T16:13:24Z)
• INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model [71.50973774576431]
  We propose a novel MLLM, INF-LLaVA, designed for effective high-resolution image perception. We introduce a Dual-perspective Cropping Module (DCM), which ensures that each sub-image contains continuous details from a local perspective. Second, we introduce Dual-perspective Enhancement Module (DEM) to enable the mutual enhancement of global and local features.
  arXiv  Detail & Related papers  (2024-07-23T06:02:30Z)
• TokenPacker: Efficient Visual Projector for Multimodal LLM [37.1071749188282]
  The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) We propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. Our approach compresses the visual tokens by 75%89%, while achieves comparable or even better performance across diverse benchmarks.
  arXiv  Detail & Related papers  (2024-07-02T16:10:55Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• Matryoshka Multimodal Models [92.41824727506751]
  We propose M3: Matryoshka Multimodal Models, which learns to represent visual content as nested sets of visual tokens. We find that COCO-style benchmarks only need around 9 visual tokens to obtain accuracy similar to that of using all 576 tokens.
  arXiv  Detail & Related papers  (2024-05-27T17:59:56Z)
• HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models [70.25499865569353]
  We introduce HyperLLaVA, which involves adaptive tuning of the projector and LLM parameters, in conjunction with a dynamic visual expert and language expert. Our solution significantly surpasses LLaVA on existing MLLM benchmarks, including MME, MMBench, SEED-Bench, and LLaVA-Bench.
  arXiv  Detail & Related papers  (2024-03-20T09:42:43Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model [17.3535277338312]
  u-LLaVA is an innovative unifying multi-task framework that integrates pixel, regional, and global features to refine the perceptual faculties of MLLMs. This work contributes a novel mask-based multi-task dataset comprising 277K samples, crafted to challenge and assess the fine-grained perception capabilities of MLLMs.
  arXiv  Detail & Related papers  (2023-11-09T13:18:27Z)
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models [36.41816380074965]
  We investigate the effectiveness of different vision encoders within Large Language Models (MLLMs) Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. We propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging.
  arXiv  Detail & Related papers  (2023-10-13T02:41:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.