AI Paper Atlas

Research map / Time series / Long-term forecasting

Dynamic Fractal Mamba: A Neural Renormalization Group Flow for Scale-Invariant Sequence Modeling

Shenglei Fang, Xianfang Sun, You Zhou

ICML 2026 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models

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 recursive weight-shared hierarchy over stacked Mamba (ablation)DF-Mamba-TS · ETTm2MSE: 0.210 -> 0.158Improved
add weight sharing across recursion depths (ablation)DF-Mamba-TS · ETTm2MSE: 0.180 -> 0.158Improved
use exponential instead of linear time-step scaling (ablation)DF-Mamba-TS · ETTm2MSE: 0.194 -> 0.158Improved
use exponential instead of constant time-step scaling (ablation)DF-Mamba-TS · ETTm2MSE: 0.186 -> 0.158Improved
use learned coarse-graining instead of naive pooling (ablation)DF-Mamba-TS · ETTm2MSE: 0.169 -> 0.158Improved
use gated fusion instead of simple addition (ablation)DF-Mamba-TS · ETTm2MSE: 0.163 -> 0.158Improved
add cross-scale consistency loss (ablation)DF-Mamba-TS · ETTm2MSE: 0.167 -> 0.158Improved
add reconstruction loss (ablation)DF-Mamba-TS · ETTm2MSE: 0.171 -> 0.158Improved
add both auxiliary losses to task loss (ablation)DF-Mamba-TS · ETTm2MSE: 0.174 -> 0.158Improved
add consistency loss (ablation)DF-Mamba · Breast histopathology (train L=256)accuracy (%): 71.11 -> 77.78Improved
add exponential time-scaler (ablation)DF-Mamba · Breast histopathology (train L=256)accuracy (%): 71.11 -> 77.78Improved
add consistency loss (ablation)DF-Mamba · Breast histopathology (train L=64)accuracy (%): 66.67 -> 71.11Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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