Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
Jaemoo Choi, Wei Guo, Yuchen Zhu +4
Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing methods largely inherit policy-gradie…
cs.CV2025
MFM-point: Multi-scale Flow Matching for Point Cloud Generation
Petr Molodyk, Jaemoo Choi, David W. Romero +2
In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds wi…