Cover Image

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Xinlei, Xu, Chengming, Zhang, Guibin, Chen, Zhangquan, Zhang, Yudong, He, Yongbo, Jiang, Peng-Tao, Zhang, Jiangning, Hu, Xiaobin, Yan, Shuicheng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dual Latent Memory for Visual Multi-agent System
by: Yu, Xinlei, et al.
Published: (2026)

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
by: Yu, Xinlei, et al.
Published: (2025)

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
by: Zhang, Guibin, et al.
Published: (2025)

Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
by: Yu, Xinlei, et al.
Published: (2025)

Mem-W: Latent Memory-Native GUI Agents
by: Zhang, Guibin, et al.
Published: (2026)

MemEvolve: Meta-Evolution of Agent Memory Systems
by: Zhang, Guibin, et al.
Published: (2025)

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
by: Sun, Haiyue, et al.
Published: (2025)

Boosting Reasoning in Large Multimodal Models via Activation Replay
by: Xing, Yun, et al.
Published: (2025)

PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
by: Chen, Zhisheng, et al.
Published: (2026)

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
by: Yu, Xinlei, et al.
Published: (2026)

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
by: Zhang, Guibin, et al.
Published: (2025)

PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models
by: He, Qingdong, et al.
Published: (2024)

Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations
by: Zhang, Tong, et al.
Published: (2026)

Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval
by: Xue, Zhucun, et al.
Published: (2026)

RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation
by: Jiang, Juntao, et al.
Published: (2025)

L2P: Unlocking Latent Potential for Pixel Generation
by: Chen, Zhennan, et al.
Published: (2026)

Data Augmentation in Human-Centric Vision
by: Jiang, Wentao, et al.
Published: (2024)

FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
by: Yin, Bo, et al.
Published: (2025)

SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology
by: Nie, Zheng, et al.
Published: (2026)

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
by: Zhang, Guibin, et al.
Published: (2025)

Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
by: Zhang, Lingfeng, et al.
Published: (2025)

PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
by: Xie, Zhifei, et al.
Published: (2026)

ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
by: Feng, Tao, et al.
Published: (2026)

What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
by: Lin, Hangyu, et al.
Published: (2026)

CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory
by: Zhang, Weichen, et al.
Published: (2025)

LatentMem: Customizing Latent Memory for Multi-Agent Systems
by: Fu, Muxin, et al.
Published: (2026)

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
by: Jiang, Boyuan, et al.
Published: (2024)

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
by: Chen, Yinan, et al.
Published: (2025)

NextMem: Towards Latent Factual Memory for LLM-based Agents
by: Zhang, Zeyu, et al.
Published: (2026)

Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
by: Li, Pengteng, et al.
Published: (2026)

FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing
by: Huang, Xijie, et al.
Published: (2026)

Vision-Language Models Unlock Task-Centric Latent Actions
by: Nikulin, Alexander, et al.
Published: (2026)

ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model
by: Xu, Chengming, et al.
Published: (2024)

Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding
by: Liu, Ying, et al.
Published: (2026)

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
by: Chen, Zhangquan, et al.
Published: (2025)

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
by: Ren, Xiyu, et al.
Published: (2026)

Explore In-Context Segmentation via Latent Diffusion Models
by: Wang, Chaoyang, et al.
Published: (2024)

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
by: Zhong, Zhiyuan, et al.
Published: (2025)

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding
by: Jiang, Juntao, et al.
Published: (2026)

Mem-T: Densifying Rewards for Long-Horizon Memory Agents
by: Yue, Yanwei, et al.
Published: (2026)