This is blog post based on my recent Twitter thread. It addresses "Peer Review, Plagiarism, and Authorship in the Age of Large Language Models: How do we retain public trust in science when it becomes easy to cheat?" #LLM #Galactica #science #publishing https://perceiving-systems.blog/en/news/peer-review-plagiarism-and-authorship-in-the-age-of-large-language-models

Neural avatars come to the World Cup! The New York Times is using our #ICON method from #CVPR 2022 to reconstruct #3D football players from images and visualize plays in 3D. ICON takes an image of a person in any pose and any clothing and reconstructs a 3D model of the person using. It combines the advantages of neural implicit shape models with those of traditional 3D articulated meshes like #SMPL-X. Project: https://icon.is.tue.mpg.de/ #avatar #deeplearning #computervision
https://www.nytimes.com/interactive/2022/11/21/sports/world-cup/wales-usmnt-world-cup-goal-pulisic.html