ICLR 2022 Blog Track


Important Information

  • The track has concluded and accepted blogposts are viewable here!
  • We’ve released a video talking about this track in more detail

We would like to thank everyone who took part in this experiment and for making it a success!


Accepted Posts

An Understanding of Learning from Demonstrations for Neural Text Generation
Kantharaju, Pavan, Smart Information Flow Technologies; Sankar, Aiswarya, Independent
Auction Learning as a Two Player Game: GANs (?) for Mechanism Design
Curry, Michael J., University of Maryland; Reusche, Daniel
Deep Neural Nets: 33 years ago and 33 years from now (Invited Post)
Karpathy, Andrej
A Deeper Look at Zero-Cost Proxies for Lightweight NAS
White, Colin; Khodak, Mikhail; Tu, Renbo; Shah, Shital; Bubeck, Sébastien; Dey, Debadeepta
Discovering Non-Monotonic Autoregressive Ordering for Text Generation Models using Sinkhorn Distributions
Kumar, Ashutosh
Does Adam Converge and When?
Zhang, Yushun; Chen, Congliang; Luo, Zhi-Quan
Euclidean geometry meets graph, a geometric deep learning perspective
Wang, Zichen, Amazon Web Services; Shi, Yunzhi, Amazon Web Services; Chen, Xin, Amazon Web Services
Generating Molecular Conformations via Normalizing Flows and Neural ODEs
Mukundh Murthy, Nikhil Devraj
Knowledge Graph Papers @ ICLR 2021
Galkin, Mikhail (Mila & McGill University)
Learning to Coarsen Graphs with Graph Neural Networks
Suri, Karush
Looking at the Performer from a Hopfield Point of View
Brandstetter J. and Ramsauer H. and Holzleitner M. and Hochreiter S. and Schäfl B.
Normalization is dead, long live normalization!
Hoedt, Pieter-Jan; Hochreiter, Sepp; Klambauer, Günter
On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections
Subramonian, Arjun
PPLM Revisited: Steering and Beaming a Lumbering Mammoth to Control Text Generation
Nguyen, Van Bach; Trienes, Jan; Nauta, Meike; Pathak, Shreyasi; Youssef, Paul; Imangaliyev, Sultan; Schlötterer, Jörg; Seifert, Christin
Recent Advances in Deep Learning for Routing Problems
Joshi, Chaitanya K.; Anand, Rishabh
Representation Change in Model-Agnostic Meta-Learning
Goerttler, Thomas (TU Berlin); Müller, Luis (TU Berlin); Obermayer, Klaus (TU Berlin)
Rethinking ValueDice - Does It Really Improve Performance?
Ziniu, Li, CUHKSZ; Tian, Xu, NJU; Yang, Yu, NJU; Zhi-Quan, Luo, CUHKSZ
Symbolic Binding in Neural Networks through Factorized Memory Systems
Ameya Daigavane, Ansh Khurana, Shweta Bhardwaj, Gaurav Aggarwal
The 37 Implementation Details of Proximal Policy Optimization
Huang, Shengyi; Dossa, Rousslan Fernand Julien; Raffin, Antonin; Kanervisto, Anssi; Wang, Weixun
The Annotated S4
Rush, Alexander; Karamcheti, Sidd
Understanding Few-Shot Multi-Task Representation Learning Theory
Bouniot, Quentin; Redko, Ievgen


The Machine Learning community is currently experiencing a reproducibility crisis and a reviewing crisis [Littman, 2021]. Because of the highly competitive and noisy reviewing process of ML conferences [Tran et al., 2020], researchers have an incentive to oversell their results, slowing down the progress and diminishing the integrity of the scientific community. Moreover with the growing number of papers published and submitted at the main ML conferences [Lin et al., 2020], it has become more challenging to keep track of the latest advances in the field.

Blog posts are becoming an increasingly popular and useful way to talk about science [Brown and Woolston, 2018]. They offer substantial value to the scientific community by providing a flexible platform to foster open, human, and transparent discussions about new insights or limitations of a scientific publication. However, because they are not as recognized as standard scientific publications, only a minority of researchers manage to maintain an active blog and get visibility for their efforts. Many are well-established researchers (Francis Bach, Ben Recht, Ferenc Huszár, Lilian Weng) or big corporations that leverage entire teams of graphic designers designer and writers to polish their blogs (Facebook AI, Google AI, DeepMind, OpenAI). As a result, the incentives for writing scientific blog posts are largely personal; it is unreasonable to expect a significant portion of the machine learning community to contribute to such an initiative when everyone is trying to establish themselves through publications.

You can read more on our about page.

A Blog Post Conference Track

Our goal is to create a formal call for blog posts at ICLR to incentivize and reward researchers to review past work and summarize the outcomes, develop new intuitions, or highlight some shortcomings. A very influential initiative of this kind happened after the second world war in France. Because of the lack of up-to-date textbooks, a collective of mathematicians under the pseudonym Nicolas Bourbaki [Halmos 1957], decided to start a series of textbooks about the foundations of mathematics [Bourbaki, 1939]. In the same vein, we aim at providing a new way to summarize scientific knowledge in the ML community.

Due to the large diversity of topics that can be discussed in a blog post, we decided to restrict the range of topics for this call for blog posts. We identified that the blog posts that would bring to most value to the community and the conference would be posts that distill and discuss previously published papers.

A call for blog posts discussing work previously published at ICLR

The format and process for this blog post track is as follows:

  • Write a post about a paper previously published at ICLR, with the constraint that one cannot write a blog post on work that they have a conflict of interest with. This implies that one cannot review their own work, or work originating from their institution or company. We want to foster productive discussion about ideas, and prevent posts that intentionally aim to help or hurt individuals or institutions.

  • Blogs will be peer-reviewed (double-blind, see Section 2.5) for quality and novelty of the content: clarity and pedagogy of the exposition, new theoretical or practical insights, reproduction/extension of experiments, etc.

  • The posts will be published under a unified template (see Section 2.4 and Section 2.5) and hosted on the conference website or our own Github page.


Note: The track has concluded and we are not accepting any more submissions!

Our goal is to avoid heavily engineered, professionally-made blog-posts—Such as the “100+ hours” mentioned as a standard by the Distill guidelines—to entice ideas and clear writing rather than dynamic visualizations or embedded javascript engines.

As a result, we restrict submissions to the Markdown format. We believe this is a good trade-off between complexity and flexibility. Markdown enables users to easily embed media such as images, gifs, audio, and video as well as write mathematical equations using MathJax, without requiring users to know how to create HTML web pages. This (mostly) static format is also fairly portable; users can download the blog post without much effort for offline reading or archival purposes. More importantly, this format can be easily hosted and maintained through GitHub.

Please checkout the submitting section for a detailed overview on the process of creating and submitting a blog post.



  • Gauthier Gidel

    gidelgau [ at ] mila.quebec

  • Charlier Gauthier

    charlie.gauthier [ at ] umontreal.ca

  • David Dobre

    david-a.dobre [ at ] mila.quebec

  • Sébastien Bubeck

    sebubeck [ at ] microsoft.com

  • Claire Vernade

    vernade [ at ] deepmind.com


Michael L Littman. Collusion rings threaten the integrity of computer science research. Communications of the ACM, 2021.

David Tran, Alex Valtchanov, Keshav Ganapathy, Raymond Feng, Eric Slud, Micah Goldblum, and Tom Goldstein. An open review of openreview: A critical analysis of the machine learning conference review process. arXiv, 2020.

Hsuan-Tien Lin, Maria-Florina Balcan, Raia Hadsell, and Marc’Aurelio Ranzato. What we learned from neurips2020 reviewing process. Medium https://medium.com/@NeurIPSConf/what-we-learned-from-neurips-2020-reviewing-process-e24549eea38f, 2020.

Eryn Brown and Chris Woolston. Why science blogging still matters. Nature, 2018.

Paul R Halmos. Nicolas bourbaki. Scientific American, 1957.

Nicolas Bourbaki. Elements of mathematics. Éditions Hermann, 1939.