Will 2023 be “THE YEAR” for XR?
Will it be a better year for the metaverse?
Or will generative AI be the main trend of 2023?
A question I see everywhere.
My thoughts: solid narrative fueled by generative AI, delivered in an XR medium is where the metaverse should be in 2023
New paper alert 📢📢
A Rubric for Human-like Agents & NeuroAI
https://arxiv.org/abs/2212.04401
Cog, neuro, & comp sciences increasingly reference human-like agents & neuroAI w no consensus on scope/use. Some import progress in 1 discipline another &assume it automatically translates.
1/n
ChatGPT is incredibly limited, but good enough at some things to create a misleading impression of greatness.
it's a mistake to be relying on it for anything important right now. it’s a preview of progress; we have lots of work to do on robustness and truthfulness.
, for building something amazing that we can now share with everyone!
P.S. Y'all are already building SUPER cool stuff with AI + Zapier.
Here are a few of our favorites ⬇️
This is the 1st large-scale mixed reality event to bring together “The Chosen Ones” - global leaders, influencers and innovators into the phygital world of
as the Downtown District ambassador!
Don’t miss the amazing lineup of and the chance to catch a glimpse of this amazing project
Join the event from anywhere in the world:
https://xclusiverse.com/eventregistration…
We’re excited to announce Varjo XR-3 Focal Edition, our latest addition to the Varjo product range, offering ultimate visual precision for advanced training.
Learn more and sign up to the launch event:
GPT3 is powerful but blind. The future of Foundation Models will be embodied agents that proactively take actions, endlessly explore the world, and continuously self-improve. What does it take? In our NeurIPS Outstanding Paper “MineDojo”, we provide a blueprint for this future:🧵
These shots aren't real.
This next-gen imaging tech is SO POWERFUL and yet... most people still don't get it.
So I made a video to give you EVERYTHING you need to know about why #NeuralRadianceFields are a big deal.
#NeRF@LumaLabsAI
These shots aren't real.
This next-gen imaging tech is SO POWERFUL and yet... most people still don't get it.
So I made a video to give you EVERYTHING you need to know about why #NeuralRadianceFields are a big deal.
🧵#NeRF
How to get started with #VR development ?
TIPS for anyone 👇 at any level !
📌 Pick your OS (macOS / Windows) there is better tooling for Windows 😉📌 Pick a headset (Standalone or PCVR)
📌 Learn a game engine (Unity or Unreal)
📌 Pick a SDK (XR Toolkit, ISDK, MRTK)
🧵 Thread
Generative AI is the biggest thing to happen to the game industry since 3D. If you're in games, and you're not experimenting with it, then you're already behind.
Some observations and predictions on just how revolutionary it's going to be. 👇
At ITW 2022, we have curated experiences that you will definitely love. Presenting one such amazing experience called Timmy’s Top Selection! Scroll to find out what it is 🙌#VRDays#ImmersiveTechWeek
Oh, NBD - Just a $100k prize to fight climate change with #AR & #VR — The XR Prize: Fight Climate Change. ALL welcome, ALL may enter. Don't wait to apply.
Non-technical groups encouraged to apply - we can match you with tools & mentors!
https://awexr.com/global/xrprize
Prototype05 has landed!
This prototype introduces four major features that push SoftspaceAR from fun toy 🧸 toward real tool 🖌️.
More on this, and how to get Prototype05 running on your
A lot of Machine Learning (ML) I learned during my Ph.D. was from youtube. I didn't have a guide to do this effectively and thus here it is:
A complete guide to studying ML from youtube: 13 best and most recent ML courses available on YouTube. 👩🏫🧵⤵️
1/ As soon as StableDiffusion landed we dropped everything to build a GENIE! 🧞♂️🎙 Voice UI
🖼 AI Art
😎 AR previews
🤑 Instant purchasing
📦 On-demand production
Could AI make every shopper’s wish come true? 🤔👇#ai#aiart#stablediffusion#dalle#dalle2#vui
Voice-to-3D animation is COMINGGGG
We advocated for Multimodal in 2018 but now we advocate for Multidimensional - get out of the 2D treadmill to 3D - voice to THREEEEE DDDDDDDD is the future.
Transformers are Sample Efficient World Models
“With the equiv. of 2 hours of gameplay…our approach sets a new SOTA for methods without lookahead search, and even surpasses MuZero.”
Love the simplicity of this approach!
pdf https://arxiv.org/abs/2209.00588
code https://github.com/eloialonso/iris
Text-to-3danimation is going to come very very quickly. Text-to-image and text-to-video are cool but 3D is the next big step to the HOLODECK!
Excited by some of these internal experiments of generative animation from just a text prompt.
Stable Diffusion imagines otherworldly images. But what if it could create videos? 🤔
There’s a new model on Replicate that animates between two prompts. Try it out here: https://replicate.com/andreasjansson/stable-diffusion-animation…
Here’s some stuff you can make with it... 🧵
ETHICS
"How can we ensure that artificial intelligence provides the greatest benefit to all of humanity? By that, we don’t necessarily mean to ask how we c…https://lnkd.in/ekVD_ns3
DALL-E 2 vs Midjourney vs StableDiffusion mega thread: photography, illustration, painters, abstract
these image synths are like instruments - it's amazing we'll get so many of them, each with a unique "sound" 🤯
rules: same prompt, 1:1 aspect ratio, no living artists
However many times the marketing will rebrand alternate realities, in the end we are going to walk through many digital layers at the same time. That revolution starts in your home.
Experiment made with