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

• URL: http://arxiv.org/abs/2512.14699v1
• Date: Tue, 16 Dec 2025 18:59:59 GMT
• Title: MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
• Authors: Sihui Ji, Xi Chen, Shuai Yang, Xin Tao, Pengfei Wan, Hengshuang Zhao,
• Abstract summary: Existing solutions maintain the memory by compressing historical frames with predefined strategies.<n>We propose MemFlow to address this problem.<n>MemFlow achieves outstanding long-context consistency with negligible burden.
• Score: 54.07515675393396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with predefined strategies. However, different to-generate video chunks should refer to different historical cues, which is hard to satisfy with fixed strategies. In this work, we propose MemFlow to address this problem. Specifically, before generating the coming chunk, we dynamically update the memory bank by retrieving the most relevant historical frames with the text prompt of this chunk. This design enables narrative coherence even if new event happens or scenario switches in future frames. In addition, during generation, we only activate the most relevant tokens in the memory bank for each query in the attention layers, which effectively guarantees the generation efficiency. In this way, MemFlow achieves outstanding long-context consistency with negligible computation burden (7.9% speed reduction compared with the memory-free baseline) and keeps the compatibility with any streaming video generation model with KV cache.

Related papers

• Flow caching for autoregressive video generation [72.10021661412364]
  We present FlowCache, the first caching framework specifically designed for autoregressive video generation.<n>Our method achieves remarkable speedups of 2.38 times on MAGI-1 and 6.7 times on SkyReels-V2, with negligible quality degradation.
  arXiv  Detail & Related papers  (2026-02-11T13:11:04Z)
• Mixture of Contexts for Long Video Generation [72.96361488755986]
  We recast long-context video generation as an internal information retrieval task.<n>We propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine.<n>As we scale the data and gradually sparsify the routing, the model allocates compute to salient history, preserving identities, actions, and scenes over minutes of content.
  arXiv  Detail & Related papers  (2025-08-28T17:57:55Z)
• Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval [33.15952106579093]
  We propose Context-as-Memory, which utilizes historical context as memory for video generation.<n>Considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module.<n>Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs.
  arXiv  Detail & Related papers  (2025-06-03T17:59:05Z)
• Streaming Long Video Understanding with Large Language Models [83.11094441893435]
  VideoStreaming is an advanced vision-language large model (VLLM) for video understanding. It capably understands arbitrary-length video with a constant number of video streaming tokens encoded and propagatedly selected. Our model achieves superior performance and higher efficiency on long video benchmarks.
  arXiv  Detail & Related papers  (2024-05-25T02:22:09Z)
• MemFlow: Optical Flow Estimation and Prediction with Memory [54.22820729477756]
  We present MemFlow, a real-time method for optical flow estimation and prediction with memory. Our method enables memory read-out and update modules for aggregating historical motion information in real-time. Our approach seamlessly extends to the future prediction of optical flow based on past observations.
  arXiv  Detail & Related papers  (2024-04-07T04:56:58Z)
• Learning Quality-aware Dynamic Memory for Video Object Segmentation [32.06309833058726]
  We propose a Quality-aware Dynamic Memory Network (QDMN) to evaluate the segmentation quality of each frame. Our QDMN achieves new state-of-the-art performance on both DAVIS and YouTube-VOS benchmarks.
  arXiv  Detail & Related papers  (2022-07-16T12:18:04Z)
• Recurrent Dynamic Embedding for Video Object Segmentation [54.52527157232795]
  We propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. We propose an unbiased guidance loss during the training stage, which makes SAM more robust in long videos. We also design a novel self-correction strategy so that the network can repair the embeddings of masks with different qualities in the memory bank.
  arXiv  Detail & Related papers  (2022-05-08T02:24:43Z)

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.