Chenshuo Wang

[Tanishq Mathew Abraham, Ph.D. @iScienceLuvr]

This is currently the most important network in deep learning!

From helping to power search for billions of users to better understanding proteins, it does it all!

Here are 10 of the best resources to help you learn about the attention mechanism & Transformer network ⬇⬇⬇

[Dr. Alana Rister | Science Grad School Coach (she) @scigradcoach]

Every research article introduction should have these key elements!

Answer these questions before you write your research introductions to make the process easier.

#AcademicChatter #PhD @PhD_Genie @yourPhDpal @AcademicChatter @OpenAcademics

[Dr. Alana Rister | Science Grad School Coach (she) @scigradcoach]

Here are 4 simple steps to writing your research article conclusions!

Don't feel stuck on how to write your research article!

#AcademicTwitter #Research @OpenAcademics @PhD_Genie @AcademicChatter

[Alan Nichol @alanmnichol]

ML startups

2016: we'll help you tune your hyperparameters!
2021: we'll help you create a decent dataset

[Jia-Bin Huang @jbhuang0604]

How to write a paper that looks like a good one?

You worked super hard and did great research, but somehow the reviewer 2 just doesn't buy it. Why? 🤔

It's probably because your paper does not look like a good paper *visually*. 🙄

How? 👇👇👇 #AcademicTwitter

[Artsiom Sanakoyeu @artsiom_s]

The shortest guide for pytorch training on GPUs

[Jia-Bin Huang @jbhuang0604]

How to keep track with the literature?

Getting started with research but overwhelmed by THOUSANDS of papers each year? How could one stay sane keeping track of the literature? 😱

Here are some tricks I found useful. 🧵

[Jannik Kossen @janundnik]

🗞New Paper🗞

🤖🧪Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning 🧪🤖

Huge thanks to @neilbband* as well as @clarelyle, @AidanNGomez, @tom_rainforth, @yaringal, and @OATML_Oxford !

Introducing 🚀Non-Parametric Transformers🚀 1/

[Jia-Bin Huang @jbhuang0604]

So You Think You Want to Apply for a PhD

The application cycle is coming up. How do I maximize my chance of getting admitted to my dream program? 🤔

Check out the thread below for resources/advices/tips!

[Jia-Bin Huang @jbhuang0604]

How to do research with my mentors effectively?

I get this question frequently in my open office hours. I am still learning as well but I hope sharing my ✌💰 may be helpful to some.

Key idea ➡️ **Help them help you!**

How? Check out the thread 🧵

[Shuiwang Ji @ShuiwangJi]

New paper on SSL for Graphs:
Group Contrastive Self-Supervised Learning on Graphs

Paper link: https://t.co/jew3RpCXu1

[Jonathan Bragg @turingmusician]

📢New preprint:
*FLEX: Unifying Evaluation for Few-Shot NLP*
- rigorous FSL/meta-learning #NLProc benchmark measuring 4 transfer types
- simple baseline w/out heavy prompt engineering / complex meta-learning methods
w/@armancohan,@kylelostat,@i_beltagy
https://t.co/6rW3SewqJl
1/n

[Philip Vollet @philipvollet]

Awesome Explainable Graph Reasoning

A collection of research papers and software related to explainability in graph machine learning.

@benrozemberczki

https://t.co/M4282JDZm7

[Omar Sanseviero @osanseviero]

Welcome Chef Transformer, a model that generates recipes based on given ingredients trained in the @huggingface +Flax community event!

🍲😋

Try it out!
https://t.co/o1BccKjC72

👩‍🍳👨‍🍳

#model_of_the_day

[Lilian Weng @lilianweng]

Diffusion models are another type of generative models, besides GAN, VAE, and flow models. The idea is quite smart and clean. It is flexible enough to model any complex distribution while remains tractable to evaluate the distribution.

https://t.co/3eaekDiUOU

[Sahil Bloom @SahilBloom]

Storytelling is a superpower.

A key to unlocking growth in your writing, startups, marketing, business, or career.

THREAD: 10+ principles of effective storytelling (that you can start using today):

[Jay Clouse @jayclouse]

Today is my 30th birthday!

In my first 30 years of life, I've had two exits, worked at a startup now valued at $4B, gotten engaged, bought a house, created a TON of content, and built a great little following of readers and listeners.

Here are 30 lessons learned (thread) 🧵...

[labml.ai @labmlai]

Annotated Implementation of "Graph Attention Networks" (GAT) in @PyTorch

📝 Code with notes: https://t.co/NRjbFgZNW2

🖥 Github: https://t.co/ELiIhpWEqz

📄 Paper: https://t.co/MSJprnxqW5 by @PetarV_93 @g_cucurull @arcp_8 @adri_romsor @pl219_cambridge Yoshua Bengio

🧵👇

[ACL Mentorship @aclmentorship]

🎉 Glad to launch the ACL Year-Round Mentorship program, open to all students worldwide!
You're welcome to apply as a mentor/mentee/volunteer, info at: https://t.co/sPFmCTDPIH

(big thanks to our organizers @radamihalcea @mohitban47 @vinodkpg @ZhijingJin @ashkankazemi @lbauer119)