Midpoint Generative Models
cs.LG
Submitted: 2026-05-28
Updated: 2026-11-14
Code: https://github.com/NVlabs/edm2https:
Terminology
Sources
- Denoising Diffusion Implicit Models
- Mean Flows for One-step Generative Modeling
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Zero-Flow Encoders
- TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
- One-step Diffusion Models with $f$-Divergence Distribution Matching
- Flow Generator Matching
- Improved Techniques for Training Consistency Models
- Denoising Diffusion Bridge Models
- Diffusion Bridge Implicit Models
- CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
- Inductive Moment Matching
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