Similar Items: MARBLE: Multi-Aspect Reward Balance for Diffusion RL
- Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy
- MoCoTalk: Multi-Conditional Diffusion with Adaptive Router for Controllable Talking Head Generation
- Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
- Continuous Latent Diffusion Language Model
- Computer-Aided Design Generation by Cascaded Discrete Diffusion Model
- Continuous-Time Distribution Matching for Few-Step Diffusion Distillation