M cubed: Reframing Training Measures for Discretized Physical Simulations
cs.AI, cs.LG
Submitted: 2026-05-09
Updated: 2026-11-01
Code: https://github.com/PhysDataRefine/M3
Terminology
Sources
- AB-UPT for Automotive and Aerospace Applications
- AhmedML: High-Fidelity Computational Fluid Dynamics Dataset for Incompressible, Low-Speed Bluff Body Aerodynamics
- DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics
- GNOT: A General Neural Operator Transformer for Operator Learning
- Geometry Aware Operator Transformer as an Efficient and Accurate Neural Surrogate for PDEs on Arbitrary Domains
- Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
- RL-PINNs: Reinforcement Learning-Driven Adaptive Sampling for Efficient Training of PINNs
- Determinantal Point Processes for Mini-Batch Diversification
- A Short Survey on Importance Weighting for Machine Learning
- A Survey on Deep Active Learning: Recent Advances and New Frontiers
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents