zdhNarsil / Diffusion-Generative-Flow-SamplersLinks
PyTorch implementation for our ICLR 2024 paper "Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization"
☆26Updated 2 years ago
Alternatives and similar repositories for Diffusion-Generative-Flow-Samplers
Users that are interested in Diffusion-Generative-Flow-Samplers are comparing it to the libraries listed below
Sorting:
- Neural Diffusion Processes☆81Updated last year
- Flow Annealed Importance Sampling Bootstrap (FAB). ICLR 2023.☆66Updated last year
- Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)☆70Updated 9 months ago
- Implementation of Action Matching☆49Updated 2 years ago
- ☆35Updated 8 months ago
- [ICML 2024] Official implementation for "Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling".☆41Updated last year
- Implementation of Action Matching for the Schrödinger equation☆25Updated 2 years ago
- Official implementation of Deep Momentum Schrödinger Bridge☆27Updated 2 years ago
- NeurIPS'23: Energy Discrepancies: A Score-Independent Loss for Energy-Based Models☆17Updated last year
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆57Updated 6 months ago
- Collecting research materials on neural samplers with diffusion/flow models☆59Updated 5 months ago
- ☆14Updated 2 years ago
- Stochastic Normalizing Flows☆78Updated 4 years ago
- ☆35Updated this week
- Source code for Large-Scale Wasserstein Gradient Flows (NeurIPS 2021)☆40Updated 3 years ago
- Generative Equilibrium Transformer☆26Updated 2 years ago
- ☆27Updated 2 years ago
- ☆18Updated 3 years ago
- Likelihood Training of Schrödinger Bridge using FBSDEs Theory, ICLR 2022☆88Updated 3 years ago
- Code release for "Stochastic Optimal Control Matching"☆39Updated last year
- Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling☆36Updated 4 years ago
- ☆24Updated 3 years ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆50Updated 5 months ago
- Entropic Optimal Transport Benchmark (NeurIPS 2023).☆27Updated last year
- Score-based generative models for compact manifolds☆117Updated last year
- code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).☆84Updated last year
- Deep Generalized Schrödinger Bridge, NeurIPS 2022 Oral☆52Updated 3 years ago
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆74Updated 2 years ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- Implementation of papers in 101 lines of code.☆18Updated 2 years ago