Unlocking the Duality between Flow and Field Matching
cs.LG
Submitted: 2026-02-02
Updated: 2026-11-14
Code: https://github.com/Newbeeer/pfgmpp
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Stochastic interpolants with data-dependent couplings
- On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
- Mean Flows for One-step Generative Modeling
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- GenPhys: From Physical Processes to Generative Models
- Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications
- Overclocking Electrostatic Generative Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Improving and generalizing flow-based generative models with minibatch optimal transport
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