Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance

• URL: http://arxiv.org/abs/2508.18177v1
• Date: Mon, 25 Aug 2025 16:32:32 GMT
• Title: Scene-Aware Vectorized Memory Multi-Agent Framework with Cross-Modal Differentiated Quantization VLMs for Visually Impaired Assistance
• Authors: Xiangxiang Wang, Xuanyu Wang, YiJia Luo, Yongbin Yu, Manping Fan, Jingtao Zhang, Liyong Ren,
• Abstract summary: This study proposes a cross-modal differiated quantization framework for vision-language models (VLMs) and a scene-aware vectorized memory multi-agent system for visually impaired assistance.<n>The modular framework was developed implementing differentiated processing strategies, effectively reducing memory requirements from 38GB to 16GB while maintaining model performance.
• Score: 4.6432462796838125
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This study proposes the dual technological innovation framework, including a cross-modal differ entiated quantization framework for vision-language models (VLMs) and a scene-aware vectorized memory multi-agent system for visually impaired assistance. The modular framework was developed implementing differentiated processing strategies, effectively reducing memory requirements from 38GB to 16GB while maintaining model performance. The multi-agent architecture combines scene classification, vectorized memory, and multimodal interaction, enabling persistent storage and efficient retrieval of scene memories. Through perception-memory-reasoning workflows, the system provides environmental information beyond the current view using historical memories. Experiments show the quantized 19B-parameter model only experiences a 2.05% performance drop on MMBench and maintains 63.7 accuracy on OCR-VQA (original: 64.9), outperforming smaller models with equivalent memory requirements like the Molmo-7B series. The system maintains response latency between 2.83-3.52 seconds from scene analysis to initial speech output, substantially faster than non-streaming methods. This research advances computational efficiency and assistive technology, offering visually impaired users comprehensive real-time assistance in scene perception, text recognition, and navigation.

Related papers

• LatentMem: Customizing Latent Memory for Multi-Agent Systems [44.59989123744384]
  We propose LatentMem, a learnable multi-agent memory framework designed to customize agent-specific memories in a token-efficient manner.<n>Specifically, LatentMem comprises an experience bank that stores raw interaction trajectories in a lightweight form, and a memory composer that synthesizes compact latent memories conditioned on retrieved experience and agent-specific contexts.
  arXiv  Detail & Related papers  (2026-02-03T03:03:16Z)
• See More, Store Less: Memory-Efficient Resolution for Video Moment Retrieval [5.835635134105812]
  We propose SMORE (See MORE, store less), a framework that enhances memory efficiency while maintaining high information resolution.<n>SMORE (1) uses query-guided captions to encode semantics aligned with user intent, (2) applies query-aware importance modulation to highlight relevant segments, and (3) adaptively compresses frames to preserve key content.<n> Experimental validation reveals that SMORE achieves state-of-the-art performance on QVHighlights, Charades-STA, and ActivityNet-Captions benchmarks.
  arXiv  Detail & Related papers  (2026-01-14T10:28:11Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• MemLoRA: Distilling Expert Adapters for On-Device Memory Systems [71.32550994522738]
  Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during dialogues.<n>MemLoRA is a novel memory system that integrates small Vision-Language Models.<n>VLM-integrated MemLoRA-V shows massive improvements in caption-based approaches.
  arXiv  Detail & Related papers  (2025-12-04T12:56:30Z)
• UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning [22.029614513198663]
  Memory-layer architectures offer an appealing alternative with very few memory access.<n>We present UltraMemV2, a redesigned memory-layer architecture that closes this performance gap.<n>We demonstrate that UltraMemV2 performance parity with 8-expert MoE models under same computation and parameters but significantly low memory access.
  arXiv  Detail & Related papers  (2025-08-26T07:33:11Z)
• HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback [0.0]
  We introduce HQ-SMem, for High Quality video segmentation and tracking using Smart Memory.<n>Our approach incorporates three key innovations: (i) leveraging SAM with High-Quality masks (SAM-HQ) alongside appearance-based candidate-selection to refine coarse segmentation masks, resulting in improved object boundaries; (ii) implementing a dynamic smart memory mechanism that selectively stores relevant key frames while discarding redundant ones; and (iii) dynamically updating the appearance model to effectively handle complex topological object variations and reduce drift throughout the video.
  arXiv  Detail & Related papers  (2025-07-25T03:28:05Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.89792845476579]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)
• APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval [41.81696346270799]
  Current large language models (LMs) struggle with hour-level video understanding.<n>bftextAdaptive textbfPivot MLbfVisual information textbfRetrieval (textbfAPVR), a training-free framework that hierarchically retrieves and retains sufficient and important visual information.
  arXiv  Detail & Related papers  (2025-06-05T12:27:10Z)
• LiVOS: Light Video Object Segmentation with Gated Linear Matching [116.58237547253935]
  LiVOS is a lightweight memory network that employs linear matching via linear attention. For longer and higher-resolution videos, it matched STM-based methods with 53% less GPU memory and supports 4096p inference on a 32G consumer-grade GPU.
  arXiv  Detail & Related papers  (2024-11-05T05:36:17Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• TF-SASM: Training-free Spatial-aware Sparse Memory for Multi-object Tracking [6.91631684487121]
  Multi-object tracking (MOT) in computer vision remains a significant challenge, requiring precise localization and continuous tracking of multiple objects in video sequences. We propose a novel memory-based approach that selectively stores critical features based on object motion and overlapping awareness. Our approach significantly improves over MOTRv2 in the DanceTrack test set, demonstrating a gain of 2.0% AssA score and 2.1% in IDF1 score.
  arXiv  Detail & Related papers  (2024-07-05T07:55:19Z)
• A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames [57.758863967770594]
  We build on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion.<n>We expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed.
  arXiv  Detail & Related papers  (2023-12-12T16:10:19Z)
• Memory-Efficient Continual Learning Object Segmentation for Long Video [7.9190306016374485]
  We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos. Motivated by the success of continual learning techniques in preserving previously-learned knowledge, here we propose Gated-Regularizer Continual Learning (GRCL) and a Reconstruction-based Memory Selection Continual Learning (RMSCL) Experimental results show that the proposed methods are able to improve the performance of Online VOS models by more than 8%, with improved robustness on long-video datasets.
  arXiv  Detail & Related papers  (2023-09-26T21:22:03Z)
• Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS [0.0]
  Camera-based Deep Learning algorithms are increasingly needed for perception in Automated Driving systems. constraints from the automotive industry challenge the deployment of CNNs by imposing embedded systems with limited computational resources. We propose an approach to embed a multi-task CNN network under such conditions on a commercial prototype platform.
  arXiv  Detail & Related papers  (2021-01-19T19:29:38Z)

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.