[ML News] GPT-3 learns to edit | Google Pathways | Make-A-Scene | CLIP meets GamePhysics | DouBlind
#mlnews #gpt3 #pathways
Your updates on the latest and greatest from the depths of Machine Learning!
Sponsor: Weights & Biases
https://wandb.me/yannic
OUTLINE:
0:00 – Intro
0:15 – Weights & Biases Report about Reports
2:45 – GPT-3 learns to edit
6:30 – Make-A-Scene: Text-to-Image with Human Priors
8:00 – Pathways: Google’s new High-Performance ML scheduler
10:45 – DouBlind: Open Peer-Review
12:45 – CLIP meets GamePhysics
14:40 – Residual Quantization pushes Image Generation SOTA
16:15 – Helpful Things
References:
Weights & Biases Report about Reports
https://wandb.ai/wandb/wandb_example/reports/How-many-discoveries-were-lost-because-they-weren-t-written-down—VmlldzoxMjY3MDk5
GPT-3 learns to edit
https://openai.com/blog/gpt-3-edit-insert/?utm_source=pocket_mylist
https://beta.openai.com/playground?model=code-davinci-002
Make-A-Scene: Text-to-Image with Human Priors
https://arxiv.org/pdf/2203.13131.pdf
Pathways: Google’s new High-Performance ML scheduler
https://arxiv.org/pdf/2203.12533.pdf
DouBlind: Open Peer-Review
https://doublind.com/#web-intro
https://doublind.com/search?query=kilcher
CLIP meets GamePhysics
https://arxiv.org/pdf/2203.11096.pdf
[Red Dead Redemption 2] Things you find in RDR2 from GamePhysics
https://asgaardlab.github.io/CLIPxGamePhysics/
Residual Quantization pushes Image Generation SOTA
https://arxiv.org/pdf/2203.01941.pdf
https://github.com/kakaobrain/rq-vae-transformer
Helpful Things
https://github.com/TDAmeritrade/stumpy
https://github.com/linkedin/fasttreeshap
https://github.com/vopani/jaxton
Introducing NovGrid: a testbed for experimenting with RL agents facing novel environmental changeshttps://t.co/P6q45hWvuvhttps://t.co/fQy7iA6xkI
Novelty is a sudden change to the world dynamics at test time, after an agent’s policy has converged and learning is turned off. pic.twitter.com/cmEnWaJ9YX
— Mark Riedl (@mark_riedl) March 25, 2022
https://github.com/eilab-gt/NovGrid
https://developer.nvidia.com/isaac-gym
https://github.com/NVIDIA-Omniverse/IsaacGymEnvs
Links:
Merch: http://store.ykilcher.com
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191
If you want to support me, the best thing to do is to share out the content 🙂
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n
