Tag: denoising diffusion models
Browse our exclusive articles!
Frequency-Enhanced Diffusion for Zero-Shot Skeleton Action Recognition
Discover Frequency-Enhanced Diffusion Models with curriculum-guided semantic alignment for accurate zero-shot skeleton action recognition in computer visio...
PDE-Regularized Diffusion with Uncertainty for Long-Term Dynamics
Discover PDE-regularized diffusion and uncertainty-aware filtering for accurate, stable long-horizon dynamics prediction in spatiotemporal models.
Advantage-Guided Diffusion in Model-Based Reinforcement Learning
Enhance model-based reinforcement learning with advantage-guided diffusion to improve trajectory sampling and boost long-term returns in control tasks.
Data-Efficient Text-to-Video Generation with Sparse Data
Discover data-efficient methods for controllable text-to-video generation using sparse synthetic data to achieve superior results with less training data.
Efficient Diffusion RL with FP4 Quantization & Sol-RL
Discover Sol-RL: a two-stage FP4 and BF16 framework boosting diffusion RL efficiency and training speed by 4.64× for text-to-image models.