Introduce your mobile with Alibabaโs Mobile-Agent, an assistant to understand your screen accurately. Researchers at Beijing Jiaotong University and Alibaba Group presented this model. It is a smart helper that
Now you are getting a little more than detection and segmentation because Grounded SAM is here. A new model has been presented by International Digital Economy Academy (IDEA) & Community.
Discover the art of self-expression in pixels with avatar generation wizardry! Gaussian Head Avatarโdesign a visual identity that mirrors your expression, essence, sparking curiosity and connection in the online world.
AlphaGeometry is an incredible mathematical discovery which works without human assistance. The researchers from Google DeepMind and New York University are the minds behind this amazing discovery. It takes a theorem
Meet OMG-Seg: From images to videos, semantic to instances. It is not just a model but a unified segmentation tool. Researchers from S-Lab, Nanyang Technological University and Shanghai Artificial Intelligence
VideoCrafter2: A groundbreaking method that crafts videos from a given text prompt. Researchers from Tencent AI Lab presented this outstanding model. The model takes text prompt as an input and
SuperCluster: Unlocking the secrets of 3D realms having the ability of navigating and understanding industrial giants as well as entire cities. The researchers from CSAI, ENGIE Lab CRIGEN and other
InstantID: Transforming a single personalized image into multiple styles within seconds. The researchers from InstantX Team have presented this amazing and creative model. The model takes a single image and
Microsoft has launches Copilot for the users of android, independently. This means that Copilot will be accessible without the need of Bing, as it use to be. This model has
PhotoMaker, the game changer in personlized human text-to-image generation with high quality, flexibility and unparalleled efficiency. The researchers from VCIP, CS, Nankai University, ARC Lab, Tencent PCG and The University
