SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback
Paper • 2602.05380 • Published
xxh
shreddedpork
·
AI & ML interests
Diffusion Model, MLLM
Recent Activity
authored a paper about 8 hours ago
SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback authored a paper 1 day ago
WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens authored a paper 1 day ago
World-R1: Reinforcing 3D Constraints for Text-to-Video GenerationOrganizations
None yet
authored a
paper about 8 hours ago
authored 3
papers 1 day ago
WeMMU: Enhanced Bridging of Vision-Language Models and Diffusion Models via Noisy Query Tokens
Paper • 2512.02536 • Published
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Paper • 2604.24764 • Published • 118
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Paper • 2605.15980 • Published • 29
authored a
paper 9 months ago