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
MACHINE LEARNING
-
NeurIPS 2022 Workshop on Fast Diffusion Model Sampling via Operator Learning
By
–
-
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
-
GeLU, LayerNorm and Mathematical Operations in Neural Networks
By
–
A lot of fun in the Appendix, e.g. how GeLU can be used for multiplication / bypassing it as identity, use of LayerNorm for division, or bypassing that as identity, etc.
-
Transformer Equations as Low-Level Microcode and Assembly Instructions
By
–
Nice! Like the track of work. Equations of Transformer are a bit like low-level microcode, this track tries to "go up" to uncover an implied assembly instruction set (e.g. RAW "read-arithmetic-write" operator?), and implemented algorithms on top of that for e.g. ridge regression.
-
MLCommons Algorithms Benchmark Standardizes Neural Network Training Comparison
By
–
Today at 3:30pm, come by the #NeurIPS2022 Google booth to hear @zacharynado talk about the @MLCommons Algorithms benchmark, an effort to standardize how researchers compare training algorithms for neural networks. https://
github.com/mlcommons/algo
rithmic-efficiency
…