Author and Submission Instructions
This document contains information about the process of submitting a paper to NIPS 2010. You can also find the Call for Papers, evaluation criteria for NIPS papers, a page with the style files, and a complete list of keywords on the NIPS website.
1. Paper Submission and Deadline
NIPS accepts only electronic submissions at https://cmt.research.microsoft.com/NIPS2010 starting Tuesday, May 25. The submission deadline is 23:59PM UTC (7:59PM Eastern Daylight, 4:59PM Pacific Daylight) on Thursday, June 3, 2010 -– please note the change of day to Thursday from the usual Friday deadline.
There will be absolutely no extensions given to the submission deadline.
All submissions must be in pdf format. As we do not accept paper submissions, particular care should be taken to ensure that your paper prints well; please consult Section 6 in the PDF example file. Note that the maximum file size for submissions is 10MB.
You can upload an early version of your paper well before the deadline. If you start registering your paper only a few minutes before the deadline, you may not have enough time to fill in all the forms. Replacing an earlier version later is no problem, and does not take as long, so "upload early and often."
The NIPS evaluation criteria form the basis for acceptance decisions. If your paper is accepted, there will be an opportunity to revise accepted manuscripts before the meeting.
If you are a reviewer as well as an author, please use the same email address to login to the CMT system. If your paper is registered by your co-author, tell them which of your email addresses to use (the same as the one you are using as a reviewer).
CMT FAQ: you can access FAQ information inside the CMT site by typing FAQ into the query box near the top of the page in the author console and then clicking on FAQs link.
2. Paper Format
Your submission must follow the style files that are available at this location. Papers are limited to eight pages, including figures and tables, in the NIPS style. However, an additional ninth page containing only cited references is allowed. Papers departing from the formatting guidelines, and all papers longer than nine (9) pages, or where the ninth page contains text other than references, will be rejected without review.
Note change this year:
The style files have changed this year. Make sure you are using the latest ones (named nips10submit_e.sty, nips10submit_09.sty or nips10.rtf). In the LaTeX files, \makeanontitle has been replaced by \maketitle and \nipsfinalcopy has been added.
3. Double Blind Submission
The NIPS reviewing process is double blind; please follow the style files provided and make sure the submission does not include author names and affiliations. The following are some guidelines for submitting double blind papers:
- Do not include any author name or affiliation in the title.
- Do not include any acknowledgments.
- Refer to your own published work in the third person. That is, use “In the previous work of Jones et al. [2]”, not “In our previous work [2]”.
- If you cite your other papers that are not widely available (e.g., a difficult-to-find technical report or a paper currently under review), use anonymous author names in the citation, e.g., an author of the form “A. Anonymous”.
Papers not satisfying these guidelines will not be reviewed.
4. Keywords
The purpose of the keywords is to assist assignment of papers to area chairs and reviewers. However, the separation between different areas does not play a major role, and authors should refrain from choosing keywords based on past rumors of what may increase their chances of acceptance. The keywords are hierarchically-structured, with each top-level area elaborated by more specific topics. If a low-level keyword (e.g., Gaussian processes) describes your paper well, use that; there is no need to also choose the top-level category to which it belongs (e.g., Probabilistic Models and Methods). Of course, you should still use all the keywords that are relevant to your paper (e.g., Gaussian Processes and Robotics). The list of keywords can be found on this site.
5. Submitting supplementary material
The deadline for supplementary material is the same as for papers, as given in section 1 above.
In addition to the submitted PDF paper, authors can additionally submit supplementary material for their paper. Please make sure that the supporting material is also anonymized, removing author names from any extra material, and referring to previous work in the third person.
Such extra material may include long technical proofs that do not fit into the paper, image, audio or video sample outputs from your algorithm, animations that describe your algorithm, details of experimental results, or even source code for running experiments.
Note that the reviewers and the program committee reserve the right to judge the paper solely on the basis of the 8 pages, 9 pages including citations, of the paper; looking at any extra material is up to the discretion of the reviewers and is not required.
To submit the supplementary material you should create an archive file. You will be given an opportunity to upload it to CMT after submitting the paper itself. This archive file can be in the .zip format (using WinZip or equivalent), or in .tar.gz or .tgz format (using tar and gzip). Alternatively, you can choose to upload a single PDF file as supplementary material. There is a strict upper limit of 10MB for the supplementary material. Archives larger than this will be rejected by CMT. Please be circumspect, and upload only files that are directly useful for evaluating your paper.
To reduce load on the server, we request that large files not be uploaded right at the time of the deadline. Please upload material that is ready early (e.g., videos or images) as soon as possible.
For your archive, for each extra file, use a file name that starts with a description of the extra material, such as “proof”, or “appendix”, or “video”, and ends with the appropriate extension.
Again, please ensure that the supporting material (including filenames) is anonymized.
6. Policy on dual submission
Submissions that are identical (or substantially similar) to versions that have been previously published, or accepted for publication, or that have been submitted in parallel to other conferences are not appropriate for NIPS. Exceptions to this rule are the following:
(1) Submission is permitted of a short version of a paper that has been submitted, but not yet accepted, to a journal.
(2) Papers presented or to be presented at conferences or workshops without proceedings, or with only abstracts published.
The rules only apply during the NIPS review period that begins June 14 and ends August 27, 2010. It is acceptable to submit to NIPS 2010 work that has been made available as a technical report (or similar, e.g. in arXiv) as long as the conditions above are satisfied. However, note that this could compromise the authors' anonymity.
7. Author feedback
Starting on August 3, authors will be given the chance to see the reviews and respond to their content.
Your feedback can be used by the Program Committee to alter their judgment about the paper, but giving a response is optional. Author responses should be limited to factual statements and corrections of specific claims in the reviews; they should not be used to plea for acceptance or make promises for a future revision. The maximum length of the response is 4000 characters.
Authors can submit one response per submission. Once author feedback is enabled, authors will see a link to "Author Feedback" from the author console. Any of the authors of a paper can enter/edit the rebuttal, and the rebuttal can be returned to and edited up to the deadline for author feedback.
Remember that reviewing is double-blind. Do not include any information in the response that can identify you or your co-authors. Please do not include any URLs in your response.
Finally, we recommend using the response judiciously. If a reviewer has expressed uncertainty about an issue, or is making an incorrect assumption, or has misunderstood a point in the paper, that is ideal to address in an author's response. There is no need to respond to every minor question or
suggestion for improvement. In any event, the best strategy is to be polite and professional.
8. Final version of paper
As was the case last year the final version of an accepted paper will be due by the end of October. This will mean that the conference proceedings will be available in time for the meeting.
Richard Zemel and John Shawe-Taylor
NIPS 2010 Program Co-chairs
nips10-program-chairs@cs.toronto.edu