Shap·E is a conditional generative model for 3D assets, and you can read the full paper here: https://arxiv.org/pdf/2305.02463.pdf … GitHub: https://github.com/openai/shap-e
INNOVATION
-
OpenAI prepares Text-to-3D with SHAP-E
By
–
Yes. OpenAI releasing Text-to-3D soon: SHAP-E They dropped a research paper and Github code for a model called SHAP-E for creating 3D models through text prompts. We are probably 1-2 months away from seeing Text-to-3D printers, as in text-to-object.
-
Cerebras Demonstrates Sparse Neural Network Hardware at ICLR2023
By
–
Cerebras sponsored the #ICLR2023 workshop on Sparsity in Neural Networks and presented "Sparse Pre-training and Dense Fine-tuning." Our hardware natively supports structured/dynamic sparsity, and we welcome collaboration on sparsity research!
-
Companies Should Prioritize User Interaction Quality
By
–
This kind of interaction with users is awesome. Other companies should take note.
-
Why 65% of New Businesses Fail: Podcast Insights
By
–
65% de los Nuevos Negocios fallan: Esta es la razón #podcast https://
podcasters.spotify.com/pod/show/negoc
ios-en-crecimiento/episodes/ep-e23hn8m
… -
US Government Spending and AI Model Parameters Scale to Trillions
By
–
US Govt spending and AI model parameters appear to be moving in lockstep. A few years back a billion dollars, and a billion parameters used to be cool. Now, a billion is not cool. Do you know what is cool? A TRILLION dollars and parameters.
-
Knowledge Without Action Is Incomplete Understanding
By
–
I still regularly use a phrase that I learned in mine: "to know and not yet to do is not yet to know."
-
SSL Cookbook: Practical Guide for Self-Supervised Learning Research
By
–
Self-supervised learning is a key ingredient in recent AI breakthroughs. To lower barriers + help democratize access to this research, we compiled The SSL Cookbook: a practical guide for researchers navigating the intricacies of this research space.
-
Dr. Sahin Defends Ph.D. on Learning Control Systems
By
–
So proud of Dr. @SahinLale for his successful Ph.D. defense on "learning and control". He has derived regret guarantees for partially observed systems and deployed them on turbulent airfoil stabilization. His slides: http://
tensorlab.cms.caltech.edu/users/anima/sl
ides/sahin_defense_slides.pptx
… @caltech -
Early OSS lightweight models testing formats private beta
By
–
As a funny aside, one of the early private beta stories I circulated among friends a few months ago as I was testing formats was literally titled “a model in your pocket” and about low-param OSS models. Whoops.