The week in generative media · Oct 5 – Oct 12, 2026
Researchers from Caltech and World Labs have introduced LoGo, a post-training method designed to address a persistent failure mode in camera-controlled video generation: 3D inco...
Researchers have released Sphere Encoder 2, a follow-up to the original Sphere Encoder autoencoder that generates images by decoding random points sampled from a high-dimensiona...
·
Researchers from the University of Amsterdam and TNO have introduced Loop Flow Transformers (LiFT), a new family of generative model architectures that replaces stacking many di...
·
Midjourney is rolling out a "Thinking Mode" for image generation on its Alpha platform, applying extended reasoning to improve prompt accuracy, typography, and overall image coh...
·
DittoDub has released Native 6, its new default AI dubbing model, supporting 109 languages and 126 dialect options. The model is designed to preserve a creator's voice, energy, ...
·
BULLET Microdrama, backed by Zee Entertainment Enterprises, is rolling out a slate of more than 100 AI-powered microdramas using its proprietary Trinetra AI filmmaking platform,...
·
