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.

A research team from Peking University and Peking University Shenzhen Graduate School have used artificial intelligence (AI) to quickly and accurately predict the properties of materials that could improve solar energy devices. Their algorithms were able to predictic important properties such as: conduction band minimum (CBM), valence band maximum (VBM), and bandgap of halide perovskites.

This work provides valuable insights into the rational design of halide perovskites with tailored properties. These findings can impulse the discovery of better-performing solar materials, paving the way for more affordable and efficient solar panels.

A research team led by Jiang Ma from Shenzhen University, China, has developed a novel technique to enhance the plasticity of metallic glasses. By leveraging a combination of controlled aging processes and ultrasonic vibrations, they have demonstrated the ability to reverse aging-induced property deterioration and significantly improve the capacity of these glasses to deform without breaking. The team demonstrated that aged samples completely lose their compressive plasticity, whereas UV treatment after aging not only restores it but enhances the plasticity beyond that of the as-cast one.

This finding breaks through the traditional perception of aging effects and opens up a new research direction for more durable and versatile applications of MGs in various industries.

Hybrid pepper breeding has long hinged on cytoplasmic male sterility (CMS) systems, but a lack of functional restorer genes has left a critical gap.