Araachie / river
Efficient Video Prediction via Sparsely Conditioned Flow Matching. In ICCV, 2023.
☆13Updated 8 months ago
Alternatives and similar repositories for river:
Users that are interested in river are comparing it to the libraries listed below
- ☆23Updated 6 months ago
- ☆10Updated 5 months ago
- ☆20Updated last year
- NF-Layers for constructing neural functionals.☆82Updated last year
- Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"☆66Updated 2 months ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- ☆23Updated 10 months ago
- Code release for "Stochastic Optimal Control Matching"☆30Updated 6 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆87Updated this week
- A repo where I play with conditional flow approaches for learning time-varying vector-fields.☆14Updated 8 months ago
- Neural Diffusion Processes☆76Updated 6 months ago
- Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)☆56Updated 5 months ago
- ☆51Updated 8 months ago
- ☆21Updated 2 months ago
- Official PyTorch implementation for "Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data"☆25Updated 5 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆28Updated 4 months ago
- Educational implementation of the Discrete Flow Matching paper☆76Updated 5 months ago
- code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).☆57Updated 10 months ago
- ☆24Updated last year
- ☆23Updated 4 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆25Updated last year
- Code for the paper: Rotating Features for Object Discovery☆50Updated 6 months ago
- ☆116Updated last year
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆95Updated 4 months ago
- [ICLR'23 Spotlight] gDDIM: analyze and accelerate general diffusion models, isotropic and non-isotropic☆49Updated last year
- SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all…☆19Updated 7 months ago
- Code for https://arxiv.org/abs/2406.04329☆58Updated 2 months ago
- ☆39Updated 8 months ago
- A Tutorial for Diffusion Models☆45Updated last year
- PyTorch implementation for our ICLR 2024 paper "Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory…☆23Updated last year