ROAM freezes specialist models and uses LLM priors plus online evidence in a 5-D semantic latent space to cut major-shift MAE by over 20% with under 0.02 ms overhead.
Deep subdomain learning adaptation network: A sensor fault-tolerant soft sensor for industrial processes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
CGSTAE learns correlation graphs with spatial self-attention, derives causal graphs via a three-step invariance algorithm, and uses GCLSTM encoder-decoder to monitor industrial processes on Tennessee Eastman and air separation data.
citing papers explorer
-
Open-Ended Scenario Reasoning for Specialist Model Adaptation
ROAM freezes specialist models and uses LLM priors plus online evidence in a 5-D semantic latent space to cut major-shift MAE by over 20% with under 0.02 ms overhead.
-
Graph Autoencoder for Process Monitoring
CGSTAE learns correlation graphs with spatial self-attention, derives causal graphs via a three-step invariance algorithm, and uses GCLSTM encoder-decoder to monitor industrial processes on Tennessee Eastman and air separation data.