Path-independent Flow Matching for Multi-parameter Generative Dynamics
cs.LG
Submitted: 2026-05-13
Updated: 2026-11-16
Terminology
Sources
- Multimarginal generative modeling with stochastic interpolants
- Building Normalizing Flows with Stochastic Interpolants
- Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
- Characterization of barycenters in the Wasserstein space by averaging optimal transport maps
- Distribution's template estimate with Wasserstein metrics
- Diffusion Schr\"odinger Bridge with Applications to Score-Based Generative Modeling
- Neural Ordinary Differential Equations
- Generative Adversarial Networks
- Denoising Diffusion Probabilistic Models
- Statistical Efficiency of Score Matching: The View from Isoperimetry
- Flow Matching for Generative Modeling
- I$^2$SB: Image-to-Image Schr\"odinger Bridge
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- A survey of the Schr\"odinger problem and some of its connections with optimal transport
- Compositional Learning of Dynamical System Models Using Port-Hamiltonian Neural Networks
- Curly Flow Matching for Learning Non-gradient Field Dynamics
- Scene Graph Disentanglement and Composition for Generalizable Complex Image 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