#generative-models
- Asymmetric Flow Models: SOTA 1.57 FID on ImageNet via Rank-Asymmetric Velocity Parameterization Stanford University research
- AlayaWorld: Long-Horizon and Playable Video World Generation (Open-Source) AlayaWorld Team research
- AnyFlow: Any-Step Video Diffusion with On-Policy Flow Map Distillation MIT / NVIDIA research
- DomainShuttle: Subject-Driven Text-to-Video Across In-Domain and Cross-Domain Scenarios research
- DanceOPD: On-Policy Generative Field Distillation for Unified Image Generation ByteDance Seed research
- GenFirst: generation-first training makes end-to-end latent generative models stable ByteDance Seed research