Mixture-of-experts routing
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Head-to-head results where a newer method reports beating TiDE. Values are copied from the source paper's tables — verify against the cited paper.
TimeMoE-Large beats TiDE
0.322 vs 0.419
MSE · [ETTm1]
TimeMoE-Ultra beats TiDE
0.373 vs 0.455
MSE · [ETTh1]
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.