[CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
An official implementation of Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
[ICLR 2026] An official implementation of PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
[ICLR 2026] The official implementation of Dichotomous Diffusion Policy Optimization (DIPOLE) in RL bench
Official implementation of "TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment"
[arXiv 2026] FlowBP: Exploring the Design Space of Reward Backpropagation for Flow Matching
Add a description, image, and links to the diffusion-rl topic page so that developers can more easily learn about it.
To associate your repository with the diffusion-rl topic, visit your repo's landing page and select "manage topics."