Active rejection enables reliable generalization of universal machine-learning interatomic potentials
Universal machine learning interatomic potentials (uMLIPs) bridge quantum-mechanical accuracy and large-scale molecular dynamics, but the cost of high-accuracy calculations such as r$^2$SCAN limits training to datasets that remain small relative to the open materials space. Strong average benchmark performance also does not guarantee reliable energy--force predictions for every structure. We propose Adaptive Multi-Teacher Routing (ATR), which reformulates high-fidelity data construction as a structure-wise decision problem under uncertainty. Using a small set of real r$^2$SCAN labels, ATR cali
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%arogozhnikov/hep_ml →
- PossiblePossibly related (embedding) · 54%deepmodeling/DeePTB →
- PossiblePossibly related (embedding) · 52%janosh/matbench-discovery →
- PossiblePossibly related (embedding) · 51%electrocatalysis-group/atomic-recipes →
- PossiblePossibly related (embedding) · 49%Guiding generative models to uncover diverse and novel crystals via reinforcement learning →
- LinkedLinked via arxiv author · 85%Mingxiang Luo →
“Active rejection enables reliable generalization of universal machine-learning interatomic potentials”
- LinkedLinked via arxiv author · 85%Xinnan Mao →
“Active rejection enables reliable generalization of universal machine-learning interatomic potentials”
- LinkedLinked via arxiv author · 85%Lu Wang →
“Active rejection enables reliable generalization of universal machine-learning interatomic potentials”