Tag
The paper presents Conservative Hybrid Graph Network (CHGN), a method for modeling dynamic process systems that allows extrapolation to unseen larger graphs without retraining and improves fault prediction in industrial applications.
TriRoute introduces a single lightweight controller that jointly decides attention mode, expert selection, and KV-cache bit-width for each token, achieving superior efficiency and robustness compared to independently tuned combinations of MoD, MoE, and KV-quantization.