Architecture-Aware Mixed Precision for Replica-Exchange Training of Geometry-Aware Neural Operators with Uncertainty Quantification
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning
- Mixed Precision Training of Neural ODEs
- Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference
- AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions
- DeepJEB: 3D Deep Learning-based Synthetic Jet Engine Bracket Dataset
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning