GitHub

Agent-to-Sim: Learning Interactive Behavior from Casual Videos

Follow this to install lab4d in a new conda environment. bash scripts/download_unzip.sh "https://www.dropbox.com/scl/fi/3my433p62szmbat3bj94m/log-human-2024-05 ...

‘Maybe it's a video game, maybe it's a movie, maybe it's both’: How an indie filmmaker wound up making Zelda by way of David Lynch

Shot in black and white and evoking David Lynch more than NES classics, Obex is already the year's most unique video ...
IEEE

Improving Vision-Language Models With Attention Mechanisms for Aerial Video Classification

Abstract: Vision-language models (VLMs), particularly contrastive language-image pretraining (CLIP), have recently demonstrated great success across various vision tasks. However, their potential in ...

AI Models Are Starting to Learn by Asking Themselves Questions

An AI model that learns without human input—by posing interesting queries for itself—might point the way to superintelligence ...