Cover Image

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ji, Sihui, Chen, Xi, Yang, Shuai, Tao, Xin, Wan, Pengfei, Zhao, Hengshuang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MemFlow: Optical Flow Estimation and Prediction with Memory
by: Dong, Qiaole, et al.
Published: (2024)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
by: Ji, Sihui, et al.
Published: (2025)

LayerFlow: A Unified Model for Layer-aware Video Generation
by: Ji, Sihui, et al.
Published: (2025)

VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
by: Tu, Yuanpeng, et al.
Published: (2025)

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
by: Yang, Zhenhao, et al.
Published: (2026)

WorldMem: Long-term Consistent World Simulation with Memory
by: Xiao, Zeqi, et al.
Published: (2025)

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
by: Zhao, Lin, et al.
Published: (2026)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
by: Jin, Hongbo, et al.
Published: (2025)

FashionComposer: Compositional Fashion Image Generation
by: Ji, Sihui, et al.
Published: (2024)

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
by: Yu, Jiwen, et al.
Published: (2025)

StoryMem: Multi-shot Long Video Storytelling with Memory
by: Zhang, Kaiwen, et al.
Published: (2025)

MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
by: Fuest, Michael, et al.
Published: (2025)

DiffDoctor: Diagnosing Image Diffusion Models Before Treating
by: Wang, Yiyang, et al.
Published: (2025)

FlowNar: Scalable Streaming Narration for Long-Form Videos
by: Zhong, Zeyun, et al.
Published: (2026)

AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
by: Zhang, Shuheng, et al.
Published: (2025)

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
by: Chen, Xi, et al.
Published: (2025)

CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding
by: Patel, Shrenik, et al.
Published: (2025)

Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
by: Tu, Yuanpeng, et al.
Published: (2024)

MTV-Inpaint: Multi-Task Long Video Inpainting
by: Yang, Shiyuan, et al.
Published: (2025)

MemCam: Memory-Augmented Camera Control for Consistent Video Generation
by: Gao, Xinhang, et al.
Published: (2026)

Stable Velocity: A Variance Perspective on Flow Matching
by: Yang, Donglin, et al.
Published: (2026)

MatAnyone: Stable Video Matting with Consistent Memory Propagation
by: Yang, Peiqing, et al.
Published: (2025)

FlowConsist: Make Your Flow Consistent with Real Trajectory
by: Zhang, Tianyi, et al.
Published: (2026)

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
by: Yu, Wei, et al.
Published: (2026)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
by: Xie, Yiweng, et al.
Published: (2026)

Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency
by: Xue, Xi, et al.
Published: (2025)

Hybrid Cost Volume for Memory-Efficient Optical Flow
by: Zhao, Yang, et al.
Published: (2024)

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
by: Liang, Feng, et al.
Published: (2023)

Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume
by: Xu, Gangwei, et al.
Published: (2023)

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
by: Guo, Yanjun, et al.
Published: (2026)

Owl-1: Omni World Model for Consistent Long Video Generation
by: Huang, Yuanhui, et al.
Published: (2024)

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
by: Gao, Xianqiang, et al.
Published: (2026)

FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
by: Gao, Wenshuo, et al.
Published: (2025)

FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation
by: Margaryan, Hovhannes, et al.
Published: (2026)

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
by: Yang, Ling, et al.
Published: (2024)

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
by: Zhao, Zengqun, et al.
Published: (2026)

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use
by: Wen, Siwei, et al.
Published: (2026)

SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
by: Zheng, Xinyi, et al.
Published: (2026)

Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
by: Ding, Kaixin, et al.
Published: (2025)

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
by: Li, Kangcong, et al.
Published: (2026)