Bringing Still Pictures to Life with Neural Motion Textures Google researchers published a new technique to animate still photos by predicting how each pixel should move over time
New Research Says LLMs Are Surprisingly Good at Compressing... Images and Audio? New research shows LLMs like GPT-3 have excellent compression capabilities, able to shrink down text, images, audio and more.
Contrastive Decoding: A Promising New Technique for Boosting Reasoning in Large Language Models How using an "expert" and an "amateur" LLM can improve performance with the contrastive decoding method.
A New Multilingual Dataset for Training AI Models in 167 Languages How can the CulturaX dataset help people who don't speak English access the benefits of AI?
ControlVideo: New Method Generates High-Quality Videos from Text Without Training A brief summary of ControlVideo, a tool that allows users to great video directly from text.
The Art of Prompt Engineering: A Deep Dive into the CLIP Interrogator The CLIP Interrogator AI model is a powerful prompt engineering tool.
AI Models Demystified: Your Guide to a World of Creativity and Innovation What is an AI model? How does one work? How do you use one online for free?