kksniak / metric-flow-matchingLinks
Official implementation of Metric Flow Matching (NeurIPS 2024)
☆36Updated 6 months ago
Alternatives and similar repositories for metric-flow-matching
Users that are interested in metric-flow-matching are comparing it to the libraries listed below
Sorting:
- ☆32Updated last year
- Official implementation of Deep Momentum Schrödinger Bridge☆25Updated last year
- Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold☆55Updated 3 months ago
- ☆109Updated last year
- ☆19Updated 4 months ago
- Flow Annealed Importance Sampling Bootstrap (FAB). ICLR 2023.☆58Updated last year
- Likelihood Training of Schrödinger Bridge using FBSDEs Theory, ICLR 2022☆84Updated 3 years ago
- Implementation of Action Matching☆44Updated 2 years ago
- Official implementation of the NeurIPS 24 paper of statistical flow matching (SFM) for discrete generation.☆26Updated 6 months ago
- Code for the paper https://arxiv.org/abs/2402.04997☆78Updated last year
- ☆28Updated last week
- Educational implementation of the Discrete Flow Matching paper☆88Updated 9 months ago
- GP Sinkhorn Implementation, paper: https://www.mdpi.com/1099-4300/23/9/1134☆22Updated 3 years ago
- Code release for "Stochastic Optimal Control Matching"☆35Updated 9 months ago
- Collecting research materials on neural samplers with diffusion/flow models☆48Updated last week
- Official implementation of Fisher-Flow Matching (NeurIPS 2024).☆21Updated 7 months ago
- code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).☆69Updated last year
- Implementation of Action Matching for the Schrödinger equation☆24Updated last year
- Score-based generative models for compact manifolds☆110Updated last year
- Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)☆62Updated 2 months ago
- A demo shows how to combine Langevin dynamics with score matching for generative models.☆38Updated 4 years ago
- ☆13Updated last year
- ☆146Updated last year
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆45Updated 4 months ago
- ☆17Updated last year
- Stochastic Normalizing Flows☆76Updated 3 years ago
- A set of tests for evaluating large-scale algorithms for Wasserstein-2 transport maps computation (NeurIPS 2021)☆41Updated 2 years ago
- Official Repository for "Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation" [ICLR 2024]☆15Updated last year
- The Superposition of Diffusion Models Using the Itô Density Estimator☆45Updated 2 months ago
- Aligned Diffusion Schroedinger Bridges (UAI 2023)☆32Updated last year