Liquid latent dynamics with disentangled degradation and condition states improve sensor forecasting RMSE to 0.2266 and degradation-state correlation to 0.5960 over GRU baselines on C-MAPSS but lag on direct RUL regression.
Advances in Neural Information Processing Systems , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.
citing papers explorer
-
Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling
Liquid latent dynamics with disentangled degradation and condition states improve sensor forecasting RMSE to 0.2266 and degradation-state correlation to 0.5960 over GRU baselines on C-MAPSS but lag on direct RUL regression.
-
A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models
Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.