Pseudo Label Is Better Than Human Label
abs: https://t.co/3MJ83kfbe0 pic.twitter.com/1R6I6xpFVt

— AK (@ak92501) March 25, 2022

Global Tracking Transformers
abs: https://t.co/5WnYWJ828P
github: https://t.co/T6pRUuDV0H pic.twitter.com/t03qi0jKFt

— AK (@ak92501) March 25, 2022

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training
abs: https://t.co/WiP9Y4fw9n
github: https://t.co/VP1VviW5q1 pic.twitter.com/fJ1FIQzUmi

— AK (@ak92501) March 25, 2022

Do you use (or want to use) #Docker and #rstats for model deployment? The vetiver package can help you generate a Dockerfile to deploy your model as an API, and we would love feedback from early users! 💜https://t.co/oxaVXTNFR3 pic.twitter.com/K8vuSn72x4

— Julia Silge (@juliasilge) March 24, 2022

Since it's a super helpful library for computing metrics in deep learning, and since there are a few common questions about it, I just wrote a short post on
"TorchMetrics -- How do we use it, and what's the difference between .update() and .forward()?" https://t.co/RtxIPRvHTv

— Sebastian Raschka (@rasbt) March 24, 2022

The longer I work on open-source ML tools, the more convinced I become in decoupling libraries.

Crafting simple, delightful, and composable user-facing APIs is *endlessly difficult*; you shouldn't also have to have a PhD in distributed systems in order to make those APIs scale.

— 👩‍💻 Paige Bailey #BlackLivesMatter (@DynamicWebPaige) March 23, 2022

From transformers is all we need to transformers is all we care about 🙃 pic.twitter.com/sgHDDI3YFi

— Sebastian Raschka (@rasbt) March 23, 2022

GradViT: Gradient Inversion of Vision Transformers
abs: https://t.co/IlinGOlMvD pic.twitter.com/TDTKPA2Xym

— AK (@ak92501) March 23, 2022

Do Deep Networks Transfer Invariances Across Classes?
abs: https://t.co/t1eiONg0VM
github: https://t.co/vmZm2Lo7kS pic.twitter.com/mMh0oJ2AEV

— AK (@ak92501) March 21, 2022

I noticed that DistilBERT loves movies filmed in India, but not in Iraq, so I plotted the result for each country: the resulting map is scary. #aibias pic.twitter.com/ayMjYEcOz6

— Aurélien Geron (@aureliengeron) March 20, 2022

.@Gradio demo for MMOCR, an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction on @huggingface Spaces
demo: https://t.co/iXutKDQcDO
github: https://t.co/2CxDTVslSJ pic.twitter.com/v5BFh8xItw

— AK (@ak92501) March 18, 2022

Memorizing Transformers
abs: https://t.co/T4xmmbcOMI

extension to Transformer architecture, called kNN-augmented attention, which dramatically increases the length of the context that a language model can attend to by using k-nearest-neighbor lookup into a large external memory pic.twitter.com/IKLNTvKols

— AK (@ak92501) March 18, 2022