Generative modelling with jump-diffusions
cs.LG, stat.ML
Submitted: 2025-03-09
Updated: 2026-02-06
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Heavy-tailed denoising score matching
- Generator Matching: Generative modeling with arbitrary Markov processes
- Non-Normal Diffusion Models
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Denoising Diffusion Gamma Models
- Heavy-Tailed Diffusion Models
- A Unified Approach to Analysis and Design of Denoising Markov Models
- Heavy-Tailed Diffusion with Denoising L'evy Probabilistic Models
- Improving and generalizing flow-based generative models with minibatch optimal transport
- Fast Sampling of Diffusion Models with Exponential Integrator
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