AI Paper Atlas

Research map / Video / Video generation

FreeMem: Enhancing Consistency in Long Video Generation via Tuning-Free Memory

Jibin Peng, Di Lin, Zhecheng Xu, Haoran Lu, Ruonan Liu, Wuyuan Xie, Miaohui Wang, Lingyu Liang, Yi Wang, Qing Guo

AAAI 2026 · Video › Video generation · approach: Autoregressive long video generation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add noise memory (ablation)FreeMem on FreeNoise · FreeNoise 64 frames ablationsub first: 85.24 -> 93.92Improved
add token memory on top of noise memory (ablation)FreeMem on FreeNoise · FreeNoise 64 frames ablationsub first: 93.92 -> 94.68Improved
add attention memory on top of noise and token memory (ablation)FreeMem on FreeNoise · FreeNoise 64 frames ablationsub first: 94.68 -> 95.96Improved
add noise memory instead of FreeInit (ablation)FreeMem on FreeNoise · FreeNoise 64 frames ablationsub first: 91.65 -> 93.92Improved
use both rearrange steps in noise memory rather than only the second (ablation)FreeMem noise memory · FreeNoise 64 frames ablationsub first: 93.58 -> 93.92Improved
average similar tokens in fusion instead of replacing them (ablation)FreeMem token memory · FreeNoise 64 frames ablationsub first: 84.70 -> 86.10Improved
update token memory instead of only using initial memory (ablation)FreeMem token memory · FreeNoise 64 frames ablationsub pre: 96.41 -> 97.09Improved
use dynamic attention memory instead of concatenating first-frame key/value (ablation)FreeMem attention memory · FreeNoise 64 frames ablationsub first: 86.50 -> 87.68Improved
add FreeMem to FreeNoiseFreeNoise · VBench 64 framessub first: 85.24 -> 95.96Improved
add FreeMem to StreamingT2VStreamingT2V · VBench 64 framessub first: 82.89 -> 85.26Improved
add FreeMem for 256 framesStreamingT2V base · 256 framessub first: 52.96 -> 58.81Improved
add FreeMem to FIFO-Diffusion (compute cost)FIFO-Diffusion · VBench 64 framesinference time (s): 770 ± 5 -> 1180 ± 5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy