Physics-Informed One-Step Generation on Long-short flow maps
cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Physics-Informed Diffusion Models
- D-Flow: Differentiating through Flows for Controlled Generation
- On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training
- Gradient-Free Generation for Hard-Constrained Systems
- Generative Modeling via Drifting
- Consistency Models Made Easy
- SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- A Long-Short Flow-Map Perspective for Drifting Models
- Functional Mean Flow in Hilbert Space
- Trajectory Consistency for One-Step Generation on Euler Mean Flows
- PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics
- Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
- MORPH: PDE Foundation Models with Arbitrary Data Modality
- SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs
- Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints
- FunDiff: Diffusion Models over Function Spaces for Physics-Informed Generative Modeling
- AlphaFlow: Understanding and Improving MeanFlow Models
- Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation
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