Does Text Steer Neural PDE Surrogates? A Controlled Diagnostic with OperatorCLIP
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning
- GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEs
- Towards Multi-spatiotemporal-scale Generalized PDE Modeling
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
- Poseidon: Efficient Foundation Models for PDEs
- APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
- Explain Like I'm Five: Using LLMs to Improve PDE Surrogate Models with Text
- CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics
- PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
- Fine-Tune Language Models as Multi-Modal Differential Equation Solvers
- PDEformer-1: A Foundation Model for One-Dimensional Partial Differential Equations
- Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks