在一个阳光明媚的周末，张小姐和朋友们在公园里尽兴拍照，然而拍下的照片却因光线不足、对焦不准而变得模糊。面对这样遗憾的结果，她一度感到失落，不知如何补救。正当她准备删除这些照片时，通过社交媒体得知了一款AI工具——搜狐简单AI，能够将模糊图片转变得更加清晰。在抱着试试的心态下，她上传了这些照片，没想到只需几秒钟，AI就完美还原了图片的细节。张小姐欣喜若狂，再次体会到了科技的魔力。这个案例展示了AI如 ...

Meta 发布开源数据集 OMat24 以及预训练模型 EquiformerV2。其中 OMat24 数据集包含超过 1.1 亿以结构和成分多样性为重点的 DFT 计算结果。

It is always worth paying attention when someone wins a Nobel Prize for their life’s work, but a couple of awards this year ...

Disney's Research arm is offering a new method of compressing images, leveraging the open source Stable Diffusion V1.2 model ...

Yet the rank-abundance curve of the common taxa can reduce the computational expense of denoising. Empirical rank-abundance curves of actual microbial communities tend to be dominated by a ...

CyberLink's PhotoDirector combines the workflow features of Adobe Lightroom with the functions of Photoshop while providing ...

The PS5 Pro is arriving in just a few days, and based on some comments made by Sony, it might outclass a PC in one way.

▎药明康德内容团队编辑（来源：中国科学技术大学）近日，中国科学技术大学生命科学与医学部刘海燕教授、陈泉教授团队开发了一种不依赖于预训练结构预测网络的蛋白质主链去噪扩散概率模型SCUBA-D，可自动从头设计主链结构，或指定功能位点生成主链结构。大量的实 ...

2024年，随着人工智能生成内容（AIGC）技术的快速发展，扩散生成模型作为一种新兴的AI技术，正重新定义我们对图像、视频、音频等内容的生产方式。日前，在国际知名的NeurIPS ...

The latest FSR 3.1 release this year brought significantly improved stability over previous versions. However, there's still ...