Very proud to see the many ways that @GoogleResearch contributed to the many announcements at the recent Google IO event. PaLM 2 in dozens of uses, Imagen, Phenaki, Chirp, MusicLM, flood forecasting, Green Light, fair and inclusive ML work, and more!
MULTIMODAL AI
-
MIT ML Model Identifies Materials in Images for Robot Interaction
By
–
MIT researchers develop ML model that can identify all the pixels & highlight similar materials in an image, potentially helping robots interact with objects in the real world: http://
bit.ly/3ODmYNp -
Visual Language Models Enhance Reasoning on Charts and Plots
By
–
Visual language uses pictorial symbols outside of text to convey info & is common in both digital life & the real world. Learn about two models that enhance reasoning on visual language data, such as charts and plots, for state-of-the-art performance → https://
goo.gle/3OHZred -
Stable Diffusion’s Impact: Data’s Role in Generative AI
By
–
Stable Diffusion has brought joy and unleashed the creativity of millions around the . @EMostaque – @StabilityAI will share insights into data's pivotal role in creating this groundbreaking model at https://
future.snorkel.ai. Join the conversation -
Generative AI transforms how we edit and remember collective memories
By
–
Lovely piece by @LaurenGoode on the way generative AI image and video editing will transform our collective memories.
-
AI Art Develops Its Own Unique Artistic Style
By
–
Art made by artificial intelligence is developing a style of its own
#ai #ArtificialIntelligence #machinelearning #deeplearning #GenerativeAI #art https://
buff.ly/426z6td -
Combining LLMs with Text-to-Image Diffusion Models
By
–
New BAIR Blog post on combining LLMs like GPT-4 with text-to-image diffusion models. https://
bair.berkeley.edu/blog/2023/05/2
3/lmd/
… -
AI Photoshop generates face reconstruction from eye image
By
–
I gave AI Photoshop a picture of my eye. This is what it thinks my face looks like: Not too bad considering it's the first version.
-
Midjourney: AI Image Generator for Sci-Fi and Fantasy
By
–
Midjourney is the AI image generator for sci-fi and fantasy lovers. Just type a prompt and watch your imagination come to life. Learn more about this amazing tool and how it works. #Midjourney #AI #BBC #ArtificialIntelligence #MachineLearning https://
buff.ly/45sOu66 -
Vid2Player3D: AI System Learning Tennis Skills from Video
By
–
Vid2Player3D https://
bit.ly/3Orjmhd A system that learns diverse, physically simulated tennis skills from large-scale demonstrations of tennis play harvested from broadcast videos. #AI #MachineLearning #DeepLearning #LLMs #DataScience