Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs
cs.LG, stat.ML
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/ypzpy/Text-conditional-prior
Terminology
Sources
- Conditional Sampling via Wasserstein Autoencoders and Triangular Transport
- A Survey on Diffusion Models for Inverse Problems
- Error Analysis of Bayesian Inverse Problems with Generative Priors
- LLM-Prior: A Framework for Knowledge-Driven Prior Elicitation and Aggregation
- Adam: A Method for Stochastic Optimization
- DeepSeek-V3 Technical Report
- A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptions
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- What Do Language Priors Contribute to Darcy-Flow Inversion? A Mechanistic Audit
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