– https://
x.com/sedielem/statu
s/1597401529920520192
…
– https://
x.com/du_yilun/statu
s/1597618021342023680
…
– https://
x.com/ai_fast_track/
status/1594158623059574785
…
– https://
x.com/tingchenai/sta
tus/1580574210631426048
…
– https://
x.com/poolio/status/
1575576632068214785
…
– https://
x.com/huggingface/st
atus/1597248942353584131
…
among only a few of the recent examples
MACHINE LEARNING
-
Recent Examples of AI and Machine Learning Developments Shared
By
–
-
Sparse Pre-training Dense Fine-tuning Reduces GPT Training FLOPs
By
–
At @NeurIPSConf
, we introduced Sparse Pre-training and Dense Fine-tuning to reduce the computational FLOPs of training GPT models using weight sparsity without significant loss in downstream task metrics Read more here: https://
hubs.li/Q01twKNt0 #NeurIPS2022 #sparsity #ai #ml -
CICERO by Meta AI: Diplomacy Champion Discusses Strategic Coordination
By
–
⌨️ Making moves, aiding others: 3X Diplomacy World Champ @thegoffy and @adamlerer discuss how #CICERObyMetaAI coordinates moves during gameplay.
— AI at Meta (@AIatMeta) 29 novembre 2022
Watch the full video for a deeper look at #CICERObyMetaAI 📺 ➡️ https://t.co/Lk4R4xEXhj pic.twitter.com/p9WweH3QFrMaking moves, aiding others: 3X Diplomacy World Champ @thegoffy and @adamlerer discuss how #CICERObyMetaAI coordinates moves during gameplay. Watch the full video for a deeper look at #CICERObyMetaAI https://
youtu.be/kexYmcu1Zro -
NeurIPS 2022 Workshop on Fast Diffusion Model Sampling via Operator Learning
By
–
Join us at #NeurIPS2022 workshop on diffusion models. We will be presenting our work fast sampling of diffusion models using operator learning https://
arxiv.org/abs/2211.13449 -
Fast Diffusion Model Sampling Achieves SOTA with Single Evaluation
By
–
Fast sampling of diffusion models. Only one model evaluation achieves SOTA! Check out poster at #NeurIPS22 SBM workshop on Friday 2:30pm-4pm at Room 293 – 294. @Kay12400259 @wn8_nie @ArashVahdat @Azizzadenesheli @nvidia @caltech x.com/_akhaliq/statu…
-
Fast Diffusion Model Sampling Achieves SOTA with Single Evaluation
By
–
Fast sampling of diffusion models. Only one model evaluation achieves SOTA! Check out poster at #NeurIPS22 SBM workshop on Friday 2:30pm-4pm at Room 293 – 294. @Kay12400259 @wn8_nie @ArashVahdat @Azizzadenesheli @nvidia @caltech
-
TorchMultimodal: PyTorch Library for Multimodal Multi-Task Models
By
–
TorchMultimodal is a @PyTorch library for training state-of-the-art multimodal multi-task models at scale. You can learn more and get started here https://
bit.ly/3XalYlA 6/6 -
Open Atlas of 617M Predicted Metagenomic Protein Structures Released
By
–
We announced some of our latest work in protein folding earlier this month. You can explore the open atlas of 617M predicted metagenomic protein structures here ➡️ https://t.co/DX2ysKsuFf
— AI at Meta (@AIatMeta) 29 novembre 2022
5/6https://t.co/NFe6Qy7I8hWe announced some of our latest work in protein folding earlier this month. You can explore the open atlas of 617M predicted metagenomic protein structures here https://
esmatlas.com 5/6 -
Latest Self-Supervised Learning Demos Now Available
By
–
Want to see the latest on our self-supervised learning work? We have a set of demos available here https://
ssl-demos.metademolab.com/home 2/6 -
NeurIPS 2022 Interesting Findings Accessible to All
By
–
interesting things we’re sharing at #NeurIPS2022 this week and how you can see them even if you’re not at the conference. /6