One of the unfortunate consequences of Kaggle's inability to host tabular data competitions any more will be that the fine art of feature engineering will slowly fade away. Feature engineering is rarely, if ever, covered in ML courses and textbooks. 1/
— Bojan Tunguz (@tunguz) December 18, 2020
Taming Transformers for High-Resolution Image Synthesis
— AK (@ak92501) December 18, 2020
pdf: https://t.co/fRwnXjKahS
abs: https://t.co/s9e42zZrrV
project page: https://t.co/aiA2PlSODq pic.twitter.com/emVvlP2vcg
Aviral Kumar and I have posted our NeurIPS offline reinforcement learning tutorial on YouTube for your enjoyment :)
— Sergey Levine (@svlevine) December 17, 2020
Slides, colab exercise, etc.: https://t.co/S639WkAroh
Part 1: https://t.co/OozPaXLVhF
Part 2: https://t.co/MPLhyipS1K
🤗Transformers are starting to work with structured databases!
— Hugging Face (@huggingface) December 17, 2020
We just released 🤗Transformers v4.1.1 with TAPAS, a multi-modal model for question answering on tabular data from @googleAI.
Try it out through transformers or our inference API: https://t.co/cJWxi7mB68 pic.twitter.com/s0oU0UFwW8
"Transformer are .. more effective at machine translation than RNN models, but ... most of these quality gains were from the transformer encoder, and that the transformer decoder was not significantly better than the RNN decoder."https://t.co/lGiWB9abZN
— Sasha Rush (@srush_nlp) December 17, 2020
(not sure this is CW)
[XLSR-53: Multilingual Self-Supervised Speech Transformer]
— Alexis Conneau (@alex_conneau) December 17, 2020
We're happy to release XLSR-53: a wav2vec 2.0 model pre-trained on 56k hours of speech in 53 languages from MLS, CommonVoice and BABEL datasets!
Model: https://t.co/WjOOO8k3yd
Updated paper: https://t.co/zyz4Z35lKn
1/N
Learning Continuous Image Representation with Local Implicit Image Function
— AK (@ak92501) December 17, 2020
pdf: https://t.co/7vbPTVlZ4J
abs: https://t.co/S01c0mVUOj
project page: https://t.co/fzclFcwg73
github: https://t.co/B2HyUqNDXG pic.twitter.com/NkCdtuApo1
https://t.co/xsd8cXH4tD is releasing a large travel dataset as part of a machine learning challenge (part of WSDM 2021 WebTour Workshop)
— hardmaru (@hardmaru) December 16, 2020
The prize for the top 3 teams will be @bookingcom travel credits.🤔https://t.co/SvC9i4uzN1
⚡️ Slides from my super-speed-lightning talk: “What's new in dbplyr 2.0.0?” (the most important part, obvi, being @allison_horst's new logo)https://t.co/dLhheLcehK pic.twitter.com/FXT5glnSaC
— Mara Averick (@dataandme) December 15, 2020
New Preprint: Diff Pruning (https://t.co/c4yTd7s47W) by Demi Guo / Yoon Kim Lab (😀)
— Sasha Rush (@srush_nlp) December 15, 2020
How many BERT parameters do you really need to change during fine-tuning? Turns out the answer is 0.5%
Allows new task adaption by shipping extremely small param diff's pic.twitter.com/ZkSQfvBUvg
Online meta-learning methods learn to learn continually, becoming better at learning new tasks with each task. In new work, we demonstrate incremental online meta-learning, which learns one datapoint and task at a time @TianheYu, X. Geng, @chelseabfinn https://t.co/LWbH2hUHnB pic.twitter.com/PtwlTNR5Pp
— Sergey Levine (@svlevine) December 15, 2020
pystiche is a PyTorch framework for Neural Style Transfer. It is one of the winners of 2019 PyTorch Summer Hackathon. Since then, it is peer-reviewed by pyOpenSci and published in the Journal of Open Source Software (JOSS). Learn more: https://t.co/L7KopmDVPA
— PyTorch (@PyTorch) December 14, 2020
