CoMemo: LVLMs Need Image Context with Image Memory

• URL: http://arxiv.org/abs/2506.06279v1
• Date: Fri, 06 Jun 2025 17:59:06 GMT
• Title: CoMemo: LVLMs Need Image Context with Image Memory
• Authors: Shi Liu, Weijie Su, Xizhou Zhu, Wenhai Wang, Jifeng Dai,
• Abstract summary: CoMemo is a dual-path architecture that combines a Context image path with an image Memory path for visual processing.<n>We introduce RoPE-DHR, a novel positional encoding mechanism that employs thumbnail-based positional aggregation to maintain 2D spatial awareness.
• Score: 51.681858871027345
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce suboptimal characteristics for multimodal processing. First, LVLMs exhibit a bimodal distribution in attention allocation, leading to the progressive neglect of middle visual content as context expands. Second, conventional positional encoding schemes fail to preserve vital 2D structural relationships when processing dynamic high-resolution images. To address these limitations, we propose CoMemo - a dual-path architecture that combines a Context image path with an image Memory path for visual processing, effectively alleviating visual information neglect. Additionally, we introduce RoPE-DHR, a novel positional encoding mechanism that employs thumbnail-based positional aggregation to maintain 2D spatial awareness while mitigating remote decay in extended sequences. Evaluations across seven benchmarks,including long-context comprehension, multi-image reasoning, and visual question answering, demonstrate CoMemo's superior performance compared to conventional LVLM architectures. Project page is available at https://lalbj.github.io/projects/CoMemo/.

Related papers

• Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models [18.02840698188587]
  We propose a novel kernel-based method to align CLIP's visual representation with that of DINOv2.<n>Our image-only alignment fine-tuning exhibits significant improvements in zero-shot object recognition, fine-grained spatial reasoning.
  arXiv  Detail & Related papers  (2025-06-03T07:44:43Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval [50.062817677022586]
  Zero-Shot Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens.<n>We propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI) to construct two complementary training tasks using only unlabeled images.
  arXiv  Detail & Related papers  (2025-05-26T08:56:59Z)
• From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs [23.011836329934255]
  Vision Dynamic Embedding-Guided Pretraining (VDEP) is a hybrid autoregressive training paradigm for MLLMs.<n>The proposed method seamlessly integrates into standard models without architectural changes.<n> Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods.
  arXiv  Detail & Related papers  (2025-02-13T09:04:28Z)
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling [56.130911402831906]
  This paper aims to improve the performance of video large language models (LM) via long and rich context (LRC) modeling.<n>We develop a new version of InternVideo2.5 with focus on enhancing the original MLLMs' ability to perceive fine-grained details in videos.<n> Experimental results demonstrate this unique designML LRC greatly improves the results of video MLLM in mainstream understanding benchmarks.
  arXiv  Detail & Related papers  (2025-01-21T18:59:00Z)
• TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations [23.188508465235717]
  We propose two strategies to enhance the model's capability in video understanding tasks. The first approach focuses on the enhancement of Rotary Position Embedding (RoPE) with Temporal-Aware Dual RoPE. The second approach involves enhancing the Attention Mask with the Frame-wise Block Causal Attention Mask.
  arXiv  Detail & Related papers  (2024-09-05T02:54:17Z)
• Semantic Alignment for Multimodal Large Language Models [72.10272479476161]
  We introduce Semantic Alignment for Multi-modal large language models (SAM) By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis. By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis.
  arXiv  Detail & Related papers  (2024-08-23T06:48:46Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuning [35.39822183728463]
  We present a novel Prompt-IML framework for detecting tampered images. Humans tend to discern authenticity of an image based on semantic and high-frequency information. Our model can achieve better performance on eight typical fake image datasets.
  arXiv  Detail & Related papers  (2024-01-01T03:45:07Z)
• Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models [50.07056960586183]
  We propose Position-enhanced Visual Instruction Tuning (PVIT) to extend the functionality of Multimodal Large Language Models (MLLMs) This integration promotes a more detailed comprehension of images for the MLLM. We present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model.
  arXiv  Detail & Related papers  (2023-08-25T15:33:47Z)

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.