EbbFlow: PINN-Inspired Progressive Curriculum for MeanFlow Training
cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
- Classifier-Free Diffusion Guidance
- Discrete Meanflow Training Curriculum
- Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
- Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
- On Variance Reduction in Learning Mean Flows
- MeanSE: Efficient Generative Speech Enhancement with Mean Flows
- Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
- Overcoming the Curvature Bottleneck in MeanFlow
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