Generative Discovery of Partial Differential Equations by Learning from Math Handbooks
cs.LG, cs.AI, physics.comp-ph
Submitted: 2025-05-09
Updated: 2025-05-09
Code: https://github.com/woshixuhao/EqGPT
Terminology
Sources
- Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
- ChatSR: Multimodal Large Language Models for Scientific Formula Discovery
- PDEformer: Towards a Foundation Model for One-Dimensional Partial Differential Equations
- Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
- SymbolicGPT: A Generative Transformer Model for Symbolic Regression
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
- Distilling Wikipedia mathematical knowledge into neural network models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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