This is vector space. Tesla’s head of AI @aelluswamy did an in depth presentation at last year’s computer vision conference about how the system works. https://
youtu.be/jPCV4GKX9Dw
MULTIMODAL AI
-
Tesla AI Head Presents Vector Space Computer Vision System
By
–
-
Connecting GPT to animals via neural interfaces
By
–
I can’t wait to see someone hook a mouse up to GPT so you can talk to it. 🙂
-
Transformers in Diffusion Models for Image Processing Since 2022
By
–
Plus, since ~2022, Diffusion models also use transformers for the image processing. E.g.,
-
Text-to-Image Diffusion Models Use Transformers
By
–
Fun fact: common text-to-image Diffusion models actually use Transformers
-
Improving reflective pose in diffusion models
By
–
Increasing the accuracy of reflective pose in diffusion models and estimating radiance fields. Also to see what kind of phone people have when they take a selfie.
-
AI reconstructs 3D scenes from eye reflections
By
–
AI reconstructs 3D scenes from reflections in the human eye
— AI Breakfast (@AiBreakfast) 16 juin 2023
From the paper: Seeing the World through Your Eyes
"Using this insight, we train the radiance field on the eye reflections by shooting rays from the camera, and reflecting them off the approximated eye geometry. To… pic.twitter.com/qp4ao3imkzAI reconstructs 3D scenes from reflections in the human eye From the paper: Seeing the World through Your Eyes "Using this insight, we train the radiance field on the eye reflections by shooting rays from the camera, and reflecting them off the approximated eye geometry. To
-
AI ML Expert Profile Following 70000 Sources
By
–
You should check out my profile, I follow 70,000 in AI and retweet the best stuff I find. Almost wholly AI/ML with a bit of visual stuff for AR/VR too.
-
Voicebox: Generative AI Speech Model Advancement
By
–
This work represents an important step forward for this field of research. Just as other work has done for images + text, we believe the generalization & scalability of Voicebox could usher in a new era of generative AI for speech — we're excited to continue pushing it forward.
-
Voicebox Outperforms Specialized AI Models with In-Context Learning
By
–
Voicebox generalizes across tasks and outperforms single-purpose AI models through in-context learning. It beats the previous state of the art in a number of ways. Better word error rates Improved audio similarity Up to 20x faster performance
-
Meta AI Introduces Voicebox Generative Speech System
By
–
Introducing Voicebox, a new breakthrough generative speech system based on Flow Matching, a new method proposed by Meta AI. It can synthesize speech across six languages, perform noise removal, edit content, transfer audio style & more. More details on this work & examples