本文最新研究成果MVP (Mean Velocity Policy)：提出了一种建模均值速度场（Mean Velocity Field）的新型生成式策略。该方法通过引入瞬时速度约束（IVC）作为关键的边界条件，解决了均值流学习中的解不唯一性问题，并且设计了复合生成与选择机制，确保在线强化学习过程中策略 “步步变强”。MVP 实现了极致的单步生成 —— ...

This course provides a comprehensive introduction to diffusion models and flow models for generative AI, covering both theoretical foundations and methodological advancements. The course is divided ...

Aromatic molecules adsorb onto carbon nanotube walls via pi-pi interactions, slowing supercritical water flow and reducing gasification efficiency, a new simulation study finds.

A novel FlowViT-Diff framework that integrates a Vision Transformer (ViT) with an enhanced denoising diffusion probabilistic model (DDPM) for super-resolution reconstruction of high-resolution flow ...

This efficiency makes it viable for enterprises to move beyond generic off-the-shelf solutions and develop specialized models that are deeply aligned with their specific data domains ...

A novel FlowViT-Diff framework that integrates a Vision Transformer (ViT) with an enhanced denoising diffusion probabilistic model (DDPM) for super-resolution reconstruction of high-resolution flow ...