AI Paper Atlas

Research map / Time series / Long-term forecasting

ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness

Chang Liu, Bohao Zhao, Jingtao Ding, Yong Li

ICML 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters

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 hierarchical patch merging and expansion (ScaleFormer U-Net structure) (ablation)ChaosNexus · Synthetic chaotic systemssMAPE@128: 74.161 -> 68.901Improved
add Mixture-of-Experts layers instead of plain feed-forward (ablation)ChaosNexus · Synthetic chaotic systemssMAPE@128: 73.076 -> 68.901Improved
add MMD-based auxiliary regularization (ablation)ChaosNexus · Synthetic chaotic systemssMAPE@512: 110.228 -> 100.293Improved
add MMD regularization (ablation)ChaosNexus · Synthetic chaotic systemsD_Lyap: 0.103 -> 0.065Improved
add wavelet-scattering frequency fingerprint (ablation)ChaosNexus · Synthetic chaotic systemssMAPE@128: 72.699 -> 68.901Improved
pretrain on chaotic systems corpus (fine-tune general time series model)Chronos-L · Synthetic chaotic systemsD_stsp: 11.731 -> 2.685Improved
increase model parameters from 2.83M to 52.63M (ablation)ChaosNexus · Synthetic chaotic systemssMAPE@128: improved by 49.83%Improved
increase number of training time points per system with fixed system diversity (ablation)ChaosNexus · Synthetic chaotic systems (zero-shot)sMAPENo clear effect
increase number of distinct training systems (ablation)ChaosNexus · Synthetic chaotic systems (zero-shot)sMAPEImproved
use ChaosNexus instead of Panda as spectral entropy rises (Lorenz-96, F varied)ChaosNexus · Lorenz-96 varying forcing FME_LRw: Panda near 4.5 vs ChaosNexus approx 2.5Improved
pretrain on synthetic chaotic systems then use zero-shot for forecastingChaosNexus · WEATHER-5K temperature, 120-hour horizonMAE: zero-shot below 1°C vs baselines at least 3°C after fine-tuningImproved
add few-shot fine-tuning on WEATHER-5KChaosNexus · WEATHER-5K temperatureMAEImproved

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