Somehow I’m already nostalgic for that early dalle2 patina
MULTIMODAL AI
-
Video-to-video adversarial networks advance generative AI capabilities
By
–
video2video adversarial https://
x.com/StrangestMedia
/StrangestMedia/status/1715436402215997851
… -
DALL-E 3 Paper: OpenAI Improves Image Generation Captions
By
–
DALL·E 3 Explained: Improving Image Generation with Better Captions This week's video focuses on huge news: the release of the DALLE 3 paper by OpenAI! I dissected it and gave you all the cool insights to get from this super interesting research paper! Spoiler: they tell us
-
GEN:48 creative AI challenge begins on Runway ML
By
–
GEN:48 has begun. Good luck everyone. http://
gen48.runwayml.com/welcome -
Neural Networks Inherit Cold War Era Biases and Worldviews
By
–
"Today’s most advanced neural networks & sophisticated image-analysis methods come from 1950s and ’60s Cold War culture—& many biases & ways of understanding the world from that era persist along with them."
-
Runway GEN:48 Text-to-Image and Gen-2 Video Generation Launch
By
–
Get ready for the start of GEN:48 tomorrow morning at 9 AM EST with this new Runway Academy walking through the newly updated Text to Image model, and how to combine it with Gen-2 Image to Video for incredible results. pic.twitter.com/X5f2LxpVRt
— Runway (@runwayml) 20 octobre 2023Get ready for the start of GEN:48 tomorrow morning at 9 AM EST with this new Runway Academy walking through the newly updated Text to Image model, and how to combine it with Gen-2 Image to for incredible results.
-
T2I-Adapters Enable Efficient Controllable SDXL Image Generation
By
–
Efficient Controllable Generation for SDXL with T2I-Adapters https://
bit.ly/3t5cMEt #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Habitat 3.0 Virtual Environment Released with Open-Source Code
By
–
Habitat 3.0 is released!
— Yann LeCun (@ylecun) 20 octobre 2023
Virtual environment with humanoid sims under human control, robots, realistic indoor environments, physics, …
Paper, open-source code, and datasets. https://t.co/GBu4HtFRrFHabitat 3.0 is released!
Virtual environment with humanoid sims under human control, robots, realistic indoor environments, physics, …
Paper, open-source code, and datasets. -
AI’s Impact on Memory: Google Photos Shifts From Documentation to Creation
By
–
A lot of concern around AI focuses on the future but I’ve been thinking a lot about how it might alter our understanding of the past. I wrote about how Google Photos is going all in on AI photo editing and their shift from ‘photos’ to ‘memories’
-
Meta Exploits Hollywood Strike to Train AI Cheaply
By
–
Meta hired actors during the Hollywood strike to train AI with their expressions & movements, paying as little as $300 to use the data “in perpetuity.” Nuanced story from @eileenguo illustrating how the AI industry profits from precarious labor conditions.