GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
— AK (@_akhaliq) December 23, 2022
abs: https://t.co/7jEmtNaRzT pic.twitter.com/bhCrtjJYFH
GENIE: Large Scale Pre-training for Text Generation with Diffusion Model
— AK (@_akhaliq) December 23, 2022
abs: https://t.co/7jEmtNaRzT pic.twitter.com/bhCrtjJYFH
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM https://t.co/hpKlpbDiLE #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #PyTorch
— PyTorch Best Practices (@PyTorchPractice) December 22, 2022
X-Decoder: Generalized Decoding for Pixel, Image and Language
— AK (@_akhaliq) December 22, 2022
Hugging Face demo: https://t.co/TanVA1vBow
abs: https://t.co/3AtipzRWJT
project page: https://t.co/aqVdA3akGY
github: https://t.co/GNWGTBKd65 pic.twitter.com/0o03447dqy
Deep Learning won't replace radiologists any time soon, but it sure looks like it's helping them and their patients. https://t.co/QB141zS292
— Yann LeCun (@ylecun) December 21, 2022
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
— AK (@_akhaliq) December 21, 2022
abs: https://t.co/tUqIq7xpg7 pic.twitter.com/G2j8qmFAfV
Holidays' reading list 📚🎁 Part 2
— Fermat's Library (@fermatslibrary) December 20, 2022
"The more comfortable we become with being stupid, the deeper we will wade into the unknown and the more likely we are to make big discoveries."
"The importance of stupidity in scientific research", an insightful read: https://t.co/iE404kMDkI pic.twitter.com/VF2vENr1fq
Blog Post (w/ @gail_w): On "Thinking Like Transformers"
— Sasha Rush (@srush_nlp) December 20, 2022
In which, I get a bit obsessed with learning how to code in Transformer lang🤖. https://t.co/Nb6G52vuiK
(You can follow along or do the exercises yourself in a colab notebook.) pic.twitter.com/Hk4aIxQr7l
Optimizing Prompts for Text-to-Image Generation
— AK (@_akhaliq) December 20, 2022
abs: https://t.co/RIagcSFRgx
github: https://t.co/aqvAKuyryJ
Hugging Face: https://t.co/L0tuCre89O pic.twitter.com/lNrKKhiUBN
Scalable Diffusion Models with Transformers
— AK (@_akhaliq) December 20, 2022
abs: https://t.co/RlOulZLZ1U
largest DiT-XL/2 models outperform all prior diffusion models on the class conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter pic.twitter.com/lGVFXn9keN
Pretty eery: AI models learn to reflect user views back at them (since I figure getting low loss rewards monitoring the _context_ of whatever emitted the input tokens). Pretty weird to see it in the wild. LLMs seek to reflect the views of people that talk to them. https://t.co/gD5qbAwRUb
— Jack Clark (@jackclarkSF) December 19, 2022
Teaching Small Language Models to Reason
— AK (@_akhaliq) December 19, 2022
abs: https://t.co/FVIko6wVez pic.twitter.com/bhU8maOlVk
ALERT: Adapting Language Models to Reasoning Tasks
— AK (@_akhaliq) December 19, 2022
abs: https://t.co/fC9hNJpKvc pic.twitter.com/TSbYLZYO2n