NeurIPS 2021
Mon Dec 6th through Tue the 14th
https://neurips.cc/Conferences/2021
Call For Papers
Abstract submission deadline: Friday, May 21, 2021 01:00 PM PDT

Full paper submission and co-author registration deadline: Friday, May 28, 2021 01:00 PM PDT

Supplementary material submission deadline: Friday, June 4, 2021 01:00 PM PDT

Author notification: Tuesday, September 28, 2021

Camera-ready final submission deadline: Tuesday, October 26, 2021 01:00 PM PDT

Submit at: https://openreview.net/group?id=NeurIPS.cc/2021/Conference

The site will start accepting submissions on April 19, 2021.



The Thirty-Fifth Annual Conference on Neural Information Processing Systems (NeurIPS 2021) is an interdisciplinary conference that brings together researchers in machine learning, computational neuroscience, statistics, optimization, economics, computer vision, natural language processing, computational biology, and other fields. We invite submissions presenting new and original research on topics including but not limited to the following:

General Machine Learning (e.g., classification, unsupervised learning, transfer learning)

Deep Learning (e.g., architectures, generative models, optimization for deep networks)

Reinforcement Learning (e.g., decision and control, planning, hierarchical RL)

Applications (e.g., speech processing, computational biology, computer vision, NLP)

Probabilistic Methods (e.g., variational inference, causal inference, Gaussian processes)

Optimization (e.g., convex and non-convex optimization)

Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)

Theory (e.g., control theory, learning theory, algorithmic game theory)

Infrastructure (e.g., datasets, competitions, implementations, libraries)

Social Aspects of Machine Learning (e.g., AI safety, fairness, privacy, interpretability)

Machine learning is a rapidly evolving field, and so we welcome interdisciplinary submissions that do not fit neatly into existing categories, as well as work that addresses the social impact of machine learning.

Significant recent changes to the reviewing process are described below. Please read them carefully:

There is a mandatory abstract submission deadline on May 19, 2021 01:00 PM PDT May 21, 2021 01:00 PM PDT, one week before full paper submissions are due. While it will be possible to edit the title and abstract until the full paper submission deadline, submissions with “placeholder” abstracts that are rewritten for the full submission risk being removed without consideration. This includes titles and abstracts that either provide little or no semantic information (e.g., "We provide a new semi-supervised learning method.") or describe a substantively different claimed contribution. Changes may be made to the author list until the full paper deadline. After that, authors may be reordered, but any additions or removals must be justified in writing and approved on a case-by-case basis by the program chairs.

We are using OpenReview to manage submissions this year, but the reviewing process will not be public. As in previous years, submissions under review will be visible only to their assigned program committee. We will not be soliciting comments from the general public during the reviewing process. After the notification deadline, accepted and opted-in rejected papers will be made public and open for non-anonymous public commenting. Their anonymous reviews, meta-reviews, and author responses will also be made public.

Authors of rejected papers will have two weeks after the notification deadline to opt in to make their deanonymized rejected papers public in OpenReview. These papers are not counted as NeurIPS publications and will be shown as rejected in OpenReview.

After the initial author response, we will allow for a rolling discussion with the authors. This discussion will be made public later for papers that become public.

Anyone who plans to submit a paper as an author or a co-author will need to create (or update) their OpenReview profile by the full paper submission deadline. The information entered in the profile is critical for ensuring that conflicts of interest are handled properly. Because of the rapid growth of NeurIPS, we request that all authors help with reviewing papers, if asked to do so. We need everyone’s help in maintaining the high scientific quality of NeurIPS.

There will be no summary rejections this year. However, papers may be rejected without considerations of their merits if they fail to meet the submission requirements, as described in this document.

Like last year, authors will need to declare if a previous version of their submission was rejected at any peer-reviewed venue, and, if so, summarize the changes made in the current version. This information should be entered into OpenReview during the submission process.

In order to improve the rigor and transparency of research submitted to and published at NeurIPS, authors are required to complete a paper checklist, which is included in the tex template. The paper checklist is intended to help authors reflect on a wide variety of issues relating to responsible machine learning research, including reproducibility, transparency, research ethics, and societal impact. The checklist must appear in the submitted PDF, immediately after references, but does not count towards the page limit.

We encourage authors to upload their code and data as part of their supplementary material in order to help reviewers assess the quality of the work. Check the policy as well as code submission guidelines and templates for further details.

As in past years, the program chairs will be measuring the quality and effectiveness of the review process via randomized controlled experiments. This year’s experiments have been independently reviewed and approved by an Institutional Review Board (IRB).


Authors will be asked to confirm that their submissions accord with the NeurIPS code of conduct.

Double-blind reviewing: All submissions must be anonymized and may not contain any identifying information that may violate the double-blind reviewing policy. This policy applies to any supplementary or linked material as well, including code. If you are including links to any external material, it is your responsibility to guarantee anonymous browsing. Please do not include acknowledgements at submission time. If you need to cite one of your own papers, you should do so with adequate anonymization to preserve double-blind reviewing. For instance, write “In the previous work of Smith et al. [1]…” rather than “In our previous work [1]...”). If you need to cite one of your own papers that is in submission to NeurIPS and not available as a non-anonymous preprint, then include a copy of the cited submission in the supplementary material and write “Anonymous et al. [1] concurrently show...”).

Formatting instructions: All submissions must be in PDF format. Submissions are limited to nine content pages, including all figures and tables; additional pages containing the NeurIPS paper checklist and references are allowed. The page limit was increased to ensure that authors have space to address the checklist questions. You must format your submission using the NeurIPS 2021 LaTeX style file which includes a “preprint” option for non-anonymous preprints posted online. The maximum file size for submissions is 50MB. Submissions that violate the NeurIPS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. If your submission is accepted, you will be allowed an additional content page for the camera-ready version.

Supplementary material: Authors may submit up to 100MB of supplementary material, such as appendices, proofs, derivations, data, or source code; all supplementary materials must be in PDF or ZIP format. Supplementary material should be material created by the authors that directly supports the submission content. Like submissions, supplementary material must be anonymized. Looking at supplementary material is at the discretion of the reviewers.

Ethics review: Reviewers and ACs may flag submissions for ethics review. Flagged submissions will be sent to an ethics review committee for comments. Comments from ethics reviewers will be considered by the primary reviewers and AC as part of their deliberation. They will also be visible to authors, who will have an opportunity to respond. Ethics reviewers do not have the authority to reject papers, but in extreme cases papers may be rejected by the program chairs on ethical grounds, regardless of scientific quality or contribution.

Preprints: The existence of non-anonymous preprints (on arXiv or other online repositories, personal websites, social media) will not result in rejection. If you choose to use the NeurIPS style for the preprint version, you must use the “preprint” option rather than the “final” option. Reviewers will be instructed not to actively look for such preprints, but encountering them will not constitute a conflict of interest. Authors may submit anonymized work to NeurIPS that is already available as a preprint (e.g., on arXiv) without citing it.

Dual submissions: Submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to other peer-reviewed venues with proceedings may not be submitted to NeurIPS. (Work that has appeared in non-archival workshops, such as workshops at NeurIPS/ICML, may be submitted.) NeurIPS coordinates with other conferences to identify dual submissions. The NeurIPS policy on dual submissions applies for the entire duration of the reviewing process. Slicing contributions too thinly is discouraged. The reviewing process will treat any other submission by an overlapping set of authors as prior work. If publishing one would render the other too incremental, both may be rejected.

Author responses: Authors will have one week to view and respond to initial reviews. Author responses must not contain external links. After the initial response period, authors will be able to respond to any further reviewer/AC questions and comments by posting on the submission’s forum page. The program chairs reserve the right to solicit additional reviews after the initial author response period. These reviews will become visible to the authors as they are added to OpenReview, and authors will have a chance to respond to them.

Publication of accepted submissions: Reviews, meta-reviews, and any discussion with the authors will be made public for accepted papers (but reviewer, area chair, and senior area chair identities will remain anonymous). Camera-ready papers will be due in advance of the conference. All camera-ready papers must include a funding disclosure. We strongly encourage accompanying code and data to be submitted with accepted papers when appropriate, as per the code submission policy. Authors will be allowed to make minor changes for a short period of time after the conference.

As an additional step to make NeurIPS content accessible to those attending the virtual conference, authors of accepted submissions will be required to provide a 3-minute video summarizing the paper and a PDF of the poster to be presented.

Toronto Paper Matching System and OpenReview: NeurIPS may use the Toronto Paper Matching System (TPMS) in order to assign submissions to reviewers and area chairs. During the submission process, you may be asked to agree to the use of TPMS for your submission.

Competitions, Demonstrations, Datasets and Benchmarks, Tutorials, and Workshops: There are separate tutorial, workshop, competition, datasets and benchmarks (new this year), and demonstration tracks at NeurIPS 2021. Authors who wish to submit to these tracks should consult the appropriate calls for submission.

Frequently asked questions can be found here.


Alina Beygelzimer, Yann Dauphin, Percy Liang, and Jennifer Wortman Vaughan
NeurIPS 2021 Program Chairs

Marc'Aurelio Ranzato
NeurIPS 2021 General Chair