# What papers are you reading? What's your process for reading papers? **URL:** \ **Category:** Show the Community!\ **Created:** [August 18, 2021, 5:33am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76 "2021-08-18T05:33:24Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![lavanyashukla](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/lavanyashukla/32/19_2.png) [@lavanyashukla](https://community.wandb.ai/u/lavanyashukla)\ **Post date:** [August 18, 2021, 5:33am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/1 "2021-08-18T05:33:24Z")
Would love to know what papers people are into at the moment. Also, have you found techniques to help you digest papers efficiently? ---
**Author:** ![diganta](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/diganta/32/30_2.png) [@diganta](https://community.wandb.ai/u/diganta)\ **Post date:** [August 18, 2021, 5:36am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/2 "2021-08-18T05:36:33Z")
I’m reading the following papers by [Kamalika Chaudhuri](http://cseweb.ucsd.edu/~kamalika/index.html): 1. [https://arxiv.org/pdf/2102.07048.pdf](https://arxiv.org/pdf/2102.07048.pdf) 2. [https://arxiv.org/pdf/2003.02460.pdf](https://arxiv.org/pdf/2003.02460.pdf) I will be integrating computing the statistics on these papers into my W&B dashboard. Super excited for the results. ---
**Author:** ![lavanyashukla](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/lavanyashukla/32/19_2.png) [@lavanyashukla](https://community.wandb.ai/u/lavanyashukla)\ **Post date:** [August 18, 2021, 5:41am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/3 "2021-08-18T05:41:23Z")
Interesting! How do you pick the papers you want to read Diganta? Do you skim a bunch and commit to a few? ---
**Author:** ![diganta](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/diganta/32/30_2.png) [@diganta](https://community.wandb.ai/u/diganta)\ **Post date:** [August 18, 2021, 5:44am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/4 "2021-08-18T05:44:21Z")
For these 2 papers, I actually watched her [talk](https://www.youtube.com/watch?v=mkPQwN94VoA&ab_channel=MTLMLOpt) and it struck a cord since I was ideating with a colleague on an idea which is correlated to her work. I also read papers based on the trending reports at W&B, especially those under the [Reproducibility Challenge](https://wandb.ai/fully-connected/reproducibility-challenge). ---
**Author:** ![\_scott](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/_scott/32/95_2.png) [@\_scott](https://community.wandb.ai/u/_scott)\ **Post date:** [August 20, 2021, 10:58am UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/5 "2021-08-20T10:58:11Z")
I just read “[Omnimatte: How to Detect Objects and Their Effects](https://omnimatte.github.io)” and wrote a [blog post](https://wandb.ai/_scott/omnimatte/reports/Omnimatte-How-to-Detect-Objects-and-Their-Effects--Vmlldzo5MDQxNTc) about it. My process for reading papers depends on why I’m reading it. Looking for an interesting read: 1. Read Abstract, Introduction & Conclusion 2. Check online if someone has made a blog, YouTube video etc. Looking to learn about new field / approach: 1. Follow Google Scholar citations to like find around 5 largely cited papers 2. Read Abstract, Introduction & Conclusion, in the most cited ones, read the Methodology & Results sections. 3. Find the best, more recent Related Works section which paints a good picture of the field 4. Choose a few to spend more time with ⬇ Looking to implement / deeply understand a paper: 1. Read Abstract, Introduction & Conclusion 2. Read Related Works 3. Read Methodology, Results & any blog posts / explainers online 4. Read the source code if available / any open source implementation I love hearing about how people find and read research papers. ---
**Author:** ![saiamrit](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/saiamrit/32/85_2.png) [@saiamrit](https://community.wandb.ai/u/saiamrit)\ **Post date:** [August 21, 2021, 7:54pm UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/6 "2021-08-21T19:54:31Z")
I am currently reading papers around semisupervised learning. To be specific, reading the [SimCLR series](https://ai.googleblog.com/2020/04/advancing-self-supervised-and-semi.html). I have written a [blog](https://saiamrit.github.io/technical-blog/research/reading_papers/2021/07/31/read-papers.html) recently on how to read papers and I specifically read papers using the same approach. It resonates a lot with what @scott shared depending on the level of interest, going about different passes. Hope others find it useful too. ---
**Author:** ![dealer56](https://avatars.discourse-cdn.com/v4/letter/d/4bbf92/32.png) [@dealer56](https://community.wandb.ai/u/dealer56)\ **Post date:** [September 25, 2021, 10:33pm UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/7 "2021-09-25T22:33:03Z")
I select papers to read by browsing the trending section at paperswithcode. For example, the most recent papers I’ve been reading in depth are: - [Multiplying Matrices Without Multiplying | Papers With Code](https://paperswithcode.com/paper/multiplying-matrices-without-multiplying) - [Instance-Conditioned GAN | Papers With Code](https://paperswithcode.com/paper/instance-conditioned-gan) My reading process can be roughly summed up as: - I read the abstract online - If my interest is roused, I download the paper, read the introduction, skim over the method, and take a look at the figures and result tables - Unless I plan on reproducing the paper, I’ll stop at this point. - I typically want to reproduce papers when: - If I do decide to implement the paper: ---
**Author:** ![karoly](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/karoly/32/439_2.png) [@karoly](https://community.wandb.ai/u/karoly)\ **Post date:** [October 26, 2021, 5:18pm UTC](https://community.wandb.ai/t/what-papers-are-you-reading-whats-your-process-for-reading-papers/76/8 "2021-10-26T17:18:08Z")
I loved Morgan McGuire’s guide. This is from the view of a computer graphics researcher, however, I feel that many of the key lessons generalize quite well. Recommended! 😃 > **[reading-research.pdf](https://morgan3d.github.io/advanced-ray-tracing-course/reading-research.pdf)** > > 3.40 MB