All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL
— AK (@ak92501) February 25, 2022
abs: https://t.co/3oojMrwFuv
github: https://t.co/rTA0BH3QmA pic.twitter.com/lc3Uey4bW0
All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL
— AK (@ak92501) February 25, 2022
abs: https://t.co/3oojMrwFuv
github: https://t.co/rTA0BH3QmA pic.twitter.com/lc3Uey4bW0
Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis
— AK (@ak92501) February 24, 2022
abs: https://t.co/apd0do8HZH pic.twitter.com/d4zfL8wMlO
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
— AK (@ak92501) February 24, 2022
abs: https://t.co/FotRPtnsBG
project page: https://t.co/ZoNZrniFcX pic.twitter.com/i3XqB53uCZ
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
— AK (@ak92501) February 24, 2022
abs: https://t.co/hSzS6MkjDx pic.twitter.com/Qd5KcKksVB
Visual Attention Network
— AK (@ak92501) February 22, 2022
abs: https://t.co/K0tUUFx3qk
github: https://t.co/wPaXMoXVwL pic.twitter.com/rjMYHrrWgF
SGPT: GPT Sentence Embeddings for Semantic Search
— AK (@ak92501) February 21, 2022
abs: https://t.co/zLqojUmqwl
github: https://t.co/Rj3H5waw2t pic.twitter.com/lNAESbFASS
Machine learning has a hallucination problem
— Gary Marcus (@GaryMarcus) February 20, 2022
new review from @pascalefung and others: https://t.co/P71maYqOhc pic.twitter.com/cvpI6zmq6T
How Do Vision Transformers Work?
— Jeremy Howard (@jeremyphoward) February 19, 2022
"...we propose AlterNet, a model in which Conv blocks at the end of a stage are replaced with MSA blocks. AlterNet outperforms CNNs not only in large data regimes but also in small data regimes." https://t.co/edPXnu0cn8
Anomalib: A Deep Learning Library for Anomaly Detection
— AK (@ak92501) February 18, 2022
abs: https://t.co/iZOYvkTkvR
github: https://t.co/1UHqWHhbnl pic.twitter.com/5aPKTumalB
On the record: BitFit is a perfect short paper https://t.co/ZKtfz5zLXs and should have 100x more citations. If you're excited about prompt tuning, please also give this a read.
— Sasha Rush (@srush_nlp) February 17, 2022
Locating and Editing Factual Knowledge in GPT
— AK (@ak92501) February 11, 2022
abs: https://t.co/vHG000sAP0
project page: https://t.co/wa8S6oTkdH pic.twitter.com/adFjKHoyev
NLP & vision transformers are very expensive to train, so we now focus more on fine-tuning. But should we select by model size, data size, upstream accuracy? Turns out that (maybe intuitively) upstream accuracy is the best predictor for downstream acc: https://t.co/mR8Y8HNmAe pic.twitter.com/o3JD20b750
— Sebastian Raschka (@rasbt) February 10, 2022