AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

WeightFlow: Learning Stochastic Dynamics via Evolving Weight of Neural Network

Ruikun Li, Jiazhen Liu, Huandong Wang, Qingmin Liao, Yong Li

AAAI 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 4 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
integrate along a latent control path (CDE) instead of directly over time (ODE) (ablation)WeightFlow · five simulated systemsWasserstein distance: Toggle Switch W 0.90 -> 0.82Improved
use autoencoder-based path projection instead of other projection algorithms (ablation)WeightFlow · simulated systemsWasserstein distanceImproved
add sequential aligning (warm-start from previous snapshot weights) in warm-up (ablation)WeightFlow · five simulated systemsWasserstein distanceImproved
reduce training data to 20% (ablation)WeightFlow · five simulated systemsWasserstein distanceNo clear effect
use a 1-dim latent path instead of higher dimensions (ablation)WeightFlow · five simulated systemsWasserstein distanceNo clear effect
shuffle the autoregressive order randomly (ablation)WeightFlow · five simulated systemsWasserstein distanceNo clear effect
replace GRU backbone with a Transformer backbone (ablation)WeightFlow · five simulated systemsWasserstein distanceNo clear effect
increase backbone hidden dimension beyond 8 (ablation)WeightFlow · five simulated systemsWasserstein distanceNo clear effect
model dynamics in weight space (WeightFlow) instead of DeepRUOTstochastic dynamics models · EpidemicWasserstein distance: 1.78 -> 1.10Improved
model dynamics in weight space (WeightFlow) instead of DeepRUOTstochastic dynamics models · Signalling Cascade 1 and 2Wasserstein distance: 0.52 -> 0.48; 0.51 -> 0.49No clear effect
model dynamics in weight space (WeightFlow) instead of NLSBstochastic dynamics models · Embryoid bodyWasserstein distance: 14.39 -> 14.18No clear effect
model dynamics in weight space (WeightFlow) instead of RUOTstochastic dynamics models · beta-cellMMD: 0.06 -> 0.02Improved

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