何恺明（Kaiming He）教授带领的麻省理工学院团队，联合哈佛大学研究者，发布了一项名为 Drifting Models（漂移模型）的新研究。这项工作最核心的突破在于：它打破了扩散模型（Diffusion）或流匹配模型（Flow Matching）必须在推理时进行多次迭代的“魔咒”，仅需一次前向计算（1-NFE），就能在 ImageNet 256×256 任务上跑出令人惊叹的性能。

像素扩散模型虽然避开了 VAE，但它要面对的是一个极其复杂的高维空间。在这个空间里，除了我们关心的物体形状、颜色，还充斥着大量的“无效信息”，比如相机的噪声、肉眼不可见的细节。让模型去逐个像素地死磕这些无效信号，不仅浪费算力，还会让训练变得异常困难。

Following a string of controversies stemming from technical hiccups and licensing changes, AI startup Stability AI has announced its latest family of image-generation models. The new Stable Diffusion ...

Diffusion models generate incredible images by learning to reverse the process that, among other things, causes ink to spread through water. Ask DALL·E 2, an image generation system created by OpenAI, ...

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Black Forest Labs, a startup founded by the original creators of Stable ...

AI startup Stability AI continues to refine its generative AI models in the face of increasing competition — and ethical challenges. Today, Stability AI announced the launch of Stable Diffusion XL 1.0 ...

Membership Inference Authors, Creators & Presenters: Yan Pang (University of Virginia), Tianhao Wang (University of Virginia) PAPER Black-box Membership Inference Attacks against Fine-tuned Diffusion ...