Enhancing Transformer Representations of Symbolic ODE Expressions
cs.LG, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 13 pages, 9 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
- Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithm
- PINNsAgent: Automated PDE Surrogation with Large Language Models
- Transolver: A Fast Transformer Solver for PDEs on General Geometries
- GENSR: Symbolic Regression Based in Equation Generative Space
- Deep Learning for Symbolic Mathematics
- Transformer with Tree-order Encoding for Neural Program Generation
- Tree-Based Deep Learning for Ranking Symbolic Integration Algorithms
- SymPlex: A Structure-Aware Transformer for Symbolic PDE Solving
- Finite Expression Method for Solving High-Dimensional Partial Differential Equations
- Semantic Representations of Mathematical Expressions in a Continuous Vector Space
- Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks