Towards General Continuous Memory for Vision-Language Models

• URL: http://arxiv.org/abs/2505.17670v2
• Date: Mon, 07 Jul 2025 20:01:47 GMT
• Title: Towards General Continuous Memory for Vision-Language Models
• Authors: Wenyi Wu, Zixuan Song, Kun Zhou, Yifei Shao, Zhiting Hu, Biwei Huang,
• Abstract summary: Language models (LMs) and their extension, vision-language models (VLMs) have achieved remarkable performance across various tasks.<n>They still struggle with complex reasoning tasks that require multimodal or multilingual real-world knowledge.<n>We propose using continuous memory, a compact set of dense embeddings to represent multimodal and multilingual knowledge.<n>Our approach CoMEM utilizes VLM's original capabilities to encode arbitrary multimodal and multilingual knowledge into just 8 continuous embeddings.
• Score: 39.95345066340921
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual real-world knowledge. To support such capabilities, an external memory system that can efficiently provide relevant multimodal information is essential. Existing approaches generally concatenate image and text tokens into a long sequence as memory, which, however, may drastically increase context length and even degrade performance. In contrast, we propose using continuous memory, a compact set of dense embeddings to more effectively and efficiently represent multimodal and multilingual knowledge. Our key insight is that a VLM can serve as its own continuous memory encoder. We empirically show that this design improves performance on complex multimodal reasoning tasks. Building on this, we introduce a data-efficient and parameter-efficient method to fine-tune the VLM into a memory encoder, requiring only 1.2% of the model's parameters and a small corpus of 15.6K self-synthesized samples. Our approach CoMEM utilizes VLM's original capabilities to encode arbitrary multimodal and multilingual knowledge into just 8 continuous embeddings. Since the inference-time VLM remains frozen, our memory module is plug-and-play and can be flexibly integrated as needed. Extensive experiments across eight multimodal reasoning benchmarks demonstrate the effectiveness of our approach.

Related papers

• V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding [40.784423313750075]
  Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios.<n>We propose a novel positional encoding approach that employs variable increments for visual tokens, enabling more efficient management of long multimodal sequences.<n>We show that the fine-tuned model achieves strong performance on both standard and long-context multimodal tasks.
  arXiv  Detail & Related papers  (2024-12-12T18:59:46Z)
• InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions [104.90258030688256]
  This project introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input.<n>This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time.
  arXiv  Detail & Related papers  (2024-12-12T18:58:30Z)
• Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion [40.56646959926701]
  Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models.<n>Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vision encoders.<n>We introduce VisionFuse, a novel integration framework that efficiently utilizes multiple vision encoders from off-the-shelf MLLMs.
  arXiv  Detail & Related papers  (2024-12-02T09:02:28Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• EMMA: Efficient Visual Alignment in Multi-Modal LLMs [56.03417732498859]
  EMMA is a lightweight cross-modality module designed to efficiently fuse visual and textual encodings.<n>EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations.
  arXiv  Detail & Related papers  (2024-10-02T23:00:31Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion [58.15403987979496]
  CREMA is a generalizable, highly efficient, and modular modality-fusion framework for video reasoning.<n>We propose a novel progressive multimodal fusion design supported by a lightweight fusion module and modality-sequential training strategy.<n>We validate our method on 7 video-language reasoning tasks assisted by diverse modalities, including VideoQA and Video-Audio/3D/Touch/Thermal QA.
  arXiv  Detail & Related papers  (2024-02-08T18:27:22Z)
• RET-LLM: Towards a General Read-Write Memory for Large Language Models [53.288356721954514]
  RET-LLM is a novel framework that equips large language models with a general write-read memory unit. Inspired by Davidsonian semantics theory, we extract and save knowledge in the form of triplets. Our framework exhibits robust performance in handling temporal-based question answering tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:53:38Z)

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.