APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems
Ranking
Overall
78
Content
95
Popularity
39
Observed public metrics from 1 member.
Merged summary
TL;DR - APO is an unsupervised alignment framework for predicting 3D atomic structures without ground-truth coordinates. It reportedly improves crystal and antibody structure prediction while reducing inference costs.
- Adapts group-relative policy optimization to 3D atomic environments.
- Combines rewards for dominant latent structural modes and thermodynamic stability.
- Selects physically plausible configurations from sampled groups, enabling self-correction.
- Reportedly surpasses supervised baselines in match rates and structural fidelity while straightening probability paths for faster inference.
Sources (1)
APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - APO is an unsupervised alignment framework for predicting 3D atomic structures without ground-truth coordinates. It reportedly improves crystal and antibody structure prediction while reducing inference costs.
- Adapts group-relative policy optimization to 3D atomic environments.
- Combines rewards for dominant latent structural modes and thermodynamic stability.
- Selects physically plausible configurations from sampled groups, enabling self-correction.
- Reportedly surpasses supervised baselines in match rates and structural fidelity while straightening probability paths for faster inference.