Hematopoietic stem cells (HSCs), which give rise to all blood cell types, are essential for regenerative medicine and gene therapy. However, predicting their long-term quality remains a challenge. Now, researchers from Japan have developed a novel system combining live-cell imaging and machine learning to predict HSC quality based on real-time behavior. This approach reveals hidden cellular diversity and enables accurate prediction of cell stemness and quality, advancing basic biology and offering promise for clinical applications.

Diffusion probabilistic models (DPMs) have achieved impressive success in high-resolution image synthesis, especially in recent large-scale text-to-image generation applications. An essential technique for improving the sample quality of DPMs is guided sampling, which usually needs a large guidance scale to obtain the best sample quality. The commonly-used fast sampler for guided

sampling is denoising diffusion implicit models (DDIM), a first-order diffusion ordinary differential equation (ODE) solver that generally needs 100 to 250 steps for high-quality samples. Although recent works propose dedicated high-order solvers and achieve a further speedup for sampling without guidance, their effectiveness for guided sampling has not been well-tested before. In this work, researchers demonstrate that previous high-order fast samplers suffer from instability issues, and they even become slower than DDIM when the guidance scale grows larger. To further speed up guided sampling, researchers propose DPM-Solver++, a high-order solver for the guided sampling of DPMs. DPM-Solver++ solves the diffusion ODE with the data prediction model and adopts thresholding methods to keep the solution matches training data distribution. Researchers further propose a multistep variant of DPM-Solver++ to address the instability issue by reducing the effective step size. Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs.

Scientists have been able to recreate the extreme conditions found on icy moons in deep space - and revealed the unstable behaviour of water.