CVPR 2026 Area Chair Guidelines

Area Chairs play a critical role in curating the technical program for CVPR. Use this as a resource for any questions related to your role as an Area Chair. Thank you for your contribution!

Contact Info

If you have questions that are not answered by the information below, please first contact your senior area chair.

Timeline

Here are the key dates, focused on AC duties, that we expect to work towards for CVPR 2026:

Date	Milestone	Your Key Actions
Nov 6, 2025	Abstract deadline
Nov 13, 2025	Paper submission deadline
Nov 27 - Dec 5, 2025	ACs suggest reviewers	Monitor AC reviewer suggestions
Dec 15, 2025	Papers assigned to reviewers
Jan 8, 2026	Reviews due
Jan 8-22, 2026	Emergency review period	Ensure ACs secure emergency reviews
Jan 22, 2026	Reviews released to authors
Jan 29, 2026	Author rebuttals due
Jan 30 - Feb 5, 2026	AC-reviewer discussions & triplet meeting scheduling	Ensure discussions happen & meetings scheduled
Feb 5, 2026	Final reviewer recommendations due
Feb 11, 2026	Initial AC consolidation reports due	Verify AC reports completed
Feb 6-16, 2026	Virtual AC triplet meeting week	Ensure meta-reviews written
Feb 17, 2026	Final AC meta-review due	Ensure meta-review quality
Feb 20, 2026	Final decisions to authors
Feb 21-26, 2026	Oral/spotlight/award decisions	Review special category decisions

Main Tasks

Suggest reviewers (Nov 27 - Dec 5)

ACs will suggest reviewers for each paper that is assigned to them. For this, we recommend first browsing the paper. Think about related work that is cited and also closely related work that you are aware of. Suggest a diverse group of reviewers from multiple institutions and geographic regions. Do not only suggest the top-ranked reviewers listed by OpenReview.
During this time, ACs will also flag papers for desk rejection, e.g., if papers exceed the length restrictions even by a single character, or if an incorrect template was used to write the paper.
After PCs have released the assignment of reviewers to papers, please check whether you spot any irregularities (e.g., conflicts of interest). We intend to follow suggestions given by ACs where possible, but we expect that this may not always be possible.

Ensure that all papers have at least 3 quality reviews (Jan 8 - Jan 22)

Reviews are due on Jan 8 and will be released to the authors on Jan 22. Prior to Jan 20, ACs should ensure that the reviewers have completed their reviews, send reminder emails if needed, find emergency reviewers potentially by emailing them personally if needed, assign emergency reviewers if needed, and read all reviews to ensure they are high-quality reviews. You are responsible for making sure the reviews are all available and high-quality. It is common to contact emergency reviewer candidates via a personal email prior to assigning them as emergency reviewers. Emergency reviewers should be assigned no later than Jan 12. If you want reviewers to expand on their arguments, share your feedback with reviewers early on. It is also your responsibility to escalate concerns to the senior area chair in a timely manner, e.g., if you face difficulties in finding emergency reviewers.

Author response period (Jan 22 - Jan 29)

During this period, reviews will be available to authors. If any reviews are still missing, it is urgent to track them down or invite additional reviewers. Otherwise, no action should be needed from you during this period.

Initiate reviewer-author discussions, oversee the discussions, schedule AC triplet meetings if you are the LeadAC and respond promptly to emails from your AC triplet peers, ensure that final reviewer recommendations are in on Feb 5 (Jan 30 - Feb 5)

As soon as the author response is entered in the system, ACs should lead a discussion via OpenReview for each submission and make sure the reviewers engage in the discussion phase.
The reviewers should interact with the AC and among themselves. Please make sure there is active engagement, especially for the papers where there are both positive and negative reviews. We strongly recommend that each AC go through all borderline papers (where there is not unanimous agreement among the reviewers) and engage with the reviewers in a discussion.
Please encourage reviewers to comment specifically on which of their concerns were addressed, and which ones were not. Also, when you initiate the discussion, summarize the critical concerns and ask reviewers to comment on whether they share the concern. Identifying these concerns will be important for the meta-review, so it is helpful to pinpoint them early on and make the most of the discussion period.
As an AC, please flag extremely delayed reviews, low-quality reviews, or papers with significant LLM usage not disclosed in the paper.
As a LeadAC for a triplet, during this period, initiate the scheduling of meetings to discuss borderline papers. The meetings should happen Feb 6 - Feb 16, i.e., after the final recommendations by the reviewers are due on Feb 5.

Virtual AC Triplet meeting week (Feb 6 - Feb 16)

Complete the initial AC consolidation report by Feb 11. AC Triplet meetings may or may not have happened yet.
In the AC triplet, focus on discussing borderline papers but don’t forget to check clear accepts and rejects.
We recommend that every AC prepare a spreadsheet which you can present to your triplet peers. For each paper, summarize its contributions, the reviewer assessments, and your recommendation.
We suggest handling borderline papers as follows. Read the paper carefully prior to the triplet meeting and highlight key points of the paper. During the meeting, first present a borderline paper, its claimed contributions, and the reported results to your peers. Then discuss the key strengths and weaknesses that the reviewers identified. Ask for feedback from your triplet members, share your thoughts, and aim to find a consensus recommendation among the ACs in the triplet. If a consensus is not possible, involve your senior area chair for additional feedback.

Meta review due (Feb 17)

During the AC triplet meeting week and prior to Feb 17, submit a high-quality meta-review. A good meta-review summarizes the paper’s contribution, highlights the main points of the reviewers’ initial assessment, discusses the arguments of the rebuttal, summarizes the reviewers’ reason for their final recommendation, and concludes with the recommendation of the AC and its underlying rationale.
Beyond the accept-reject recommendation, for CVPR 2026, ACs are also asked to recommend papers for the findings workshop. We suggest ACs recommend technically sound papers with solid experimental validation and contributing valuable insights, even if their technical novelty is more incremental. These are likely papers that ACs discussed in the AC triplet meeting but eventually didn’t receive an accept recommendation, and papers that reviewers viewed as having incremental novelty but solid experimentation.
Secondary ACs need to approve the decision and meta review of the primary AC by the meta review deadline.

Review special category decisions (Feb 21 - Feb 26)

ACs respond to PC and SAC requests to recommend spotlight papers, oral papers, and award candidates.

Your Roles and Action Items

Reviewing Process Manager

Your first role is to help the Program Chairs manage the reviewing process for the thousands of submissions we expect to receive. When you are assigned a batch of papers to handle based on your research profile, please recommend a set of appropriate reviewers, and when some of those reviewers are delinquent or not responsive, please assign alternate reviewers in a timely manner so that every submission gets a chance to be judged fairly and expertly. We are looking for 3 quality reviews per paper.

This year we are also introducing stricter policies for LLM usage for authors as well as new policies around low-quality and delinquent reviewers. Reviewers are required to submit timely and high-quality reviews. Your duty in this regard is to flag egregious violations of these policies on behalf of either the author or the reviewer to the SAC.

Decision Maker

From the moment all papers are submitted, perhaps the most important role as AC is making decisions for the CVPR program. For every submission that goes through the reviewing process, please recommend whether it should be accepted or rejected. The recommendation should be accompanied by a metareview summarizing the reviews and the discussion of the paper. If there is any disagreement among reviewers, the AC triplet meeting should be used for those borderline papers to provide solid ground for assessing the disagreement. Please do not hesitate to contact your SAC or the PCs if you find the need to discuss any submission assigned to you. In short, we ask you to

Flag papers for desk reject
Engage in discussion with the reviewers to ultimately help you reach an informed decision (see next section)
Participate in or lead the AC triplet meeting
Write metareviews with recommendations for accept/reject

Among the important responsibilities of ACs is to ensure reviewers’ judgments are in line with the CVPR 2026 reviewer guidelines.

Also, it is important to make sure that the language used in the reviews (including the AC metareviews) are constructive and polite.

Discussion Moderator

Each submission is considered a forum on its own, and you as an AC have full responsibility in encouraging and moderating active discussions. When a submission does not receive the amount of attention that it deserves or requires, you should actively engage with the assigned reviewers and ask for clarification or argument. You should also “moderate” discussion by discouraging participation in any discussion that is irrelevant to the scientific claims and merits of a submission.

Encourage reviewers to consider author rebuttals. Considering rebuttal comments is a core part of the reviewer’s responsibilities. If reviewers do not do this, it will make the task of finalizing the recommendation much more difficult.
Moderate the discussions so that they are not toxic and focus on the scientific merits, limitations, and clarifications.
Pinpoint critical issues and ask how the rebuttal addresses these concerns.

Discussion Participant

We have invited you to serve as an AC because of your expertise and reputation. In other words, your assessment of a submission is a critical factor behind the entire decision-making process, and we ask you to actively participate in discussions not only as a moderator but also as a scientific expert.

Confidential Comments

As an AC, you may receive confidential comments from authors and reviewers during the review, rebuttal and discussion process. Please pay attention to these comments and acknowledge that you received them if appropriate so that the authors (or reviewers) know that you are taking them into account.

Meta-Review Guideline

As an AC, we trust you to make an informed recommendation based on sufficient knowledge and justified analysis of the paper and to clearly and thoroughly convey this recommendation and reasoning behind it to the authors. To this end, you have full freedom in writing your meta-reviews, although we list below a few items that have been found useful by authors when they were presented with meta-reviews. Aim to write a meta-review of at least 60 words.

1. A concise description of the submission’s main content (scientific claims and findings) based on your own reading and reviewers’ characterization, including the paper’s strengths and weaknesses. Ideally this description should contain both what is discussed in the submission and what is missing from the submission.

2. A concise summary of the discussion. In particular, it is advised that the AC lists the points that were raised by the reviewers, how each of these points was addressed by the authors in the rebuttal, whether reviewers have remaining concerns, and whether you as the AC found each point worth consideration in decision making.

3. Your recommendation and justification. The meta-review should end with a clear indication of your recommendation. Your recommendation must be justified based on the content and discussion of the submission (i.e., the points you described above). For your recommendation consider the following acceptance criteria:

Award: major advances that will heavily impact the field; will be used by many people, create new capabilities, etc.

Oral: potential to be very significant; worthwhile for the whole community to hear about.

Poster: incremental steps that expand the sum of the community’s knowledge or add bricks to the cathedral of knowledge; papers introducing useful tools; papers of interest to a subcommunity.

Also, creative ideas that are hard to judge but could be promising -- no one knows the future, so we should give the benefit of the doubt to plausible ideas.

Reject: unlikely to be significant or already known. Provide clear evidence.

FAQ for CVPR 2026 Area Chairs

Q: What are the borderline papers?

A: Once we receive all reviews, we will let you know which papers fall into the borderline papers bucket. We’ll primarily use the spread of the review scores to identify borderline papers. While the scores aren’t the perfect measure of borderline-ness, it is a good proxy to catch most of the borderline papers among a few thousand submissions that we expect ACs to discuss in their triplet meetings.

Q: When do we seek emergency/additional reviewers?

A: In two cases:

Assigned reviewers are unresponsive and the initial review deadline has passed.
Additional reviews could improve the confidence in your recommendation. This is an important part of your responsibility, as we strive to provide timely feedback to the authors so that they can appropriately and fairly respond to the feedback.

Especially if a review had not been submitted by the review deadline and the paper lacks 3 informed reviews, immediately start looking for and recruiting an emergency reviewer.

Q: How do we assign emergency /additional reviewers?

A: When you find an emergency reviewer (e.g., confirm via a personal email first), you will be able to assign them to the paper using the links in your AC console. If you struggle to find an emergency reviewer, please get in touch with the Senior AC paired with you as soon as possible. If all fails, reach out to the program chairs. Keep in mind, it is your responsibility to ensure that all papers have three reviews. This responsibility includes escalating concerns in a timely manner.

Q: When authors directly message ACs via OpenReview, are ACs obliged to respond?

A: Authors may leave a comment directed to their corresponding ACs using OpenReview (shown as a comment on the paper page). This is often done to flag concerns. ACs are expected to respond to reasonable inquiries promptly, and bring the question to the corresponding SACs if the answer requires further discussions.

Q: Are authors expected to cite and discuss very recent work?

A: We consider papers contemporaneous if they are published within the last four months.

Q: Are authors expected to cite non peer-reviewed (e.g., ArXiv) papers?

A: Authors are encouraged to cite and discuss all relevant papers, but they may be excused for not knowing about papers not published in peer-reviewed conference proceedings or journals.

Q: Will the PCs share the review score distributions? How do I make a decision without knowing the curve?

A: We do not plan to share the rating curve. The goal of CVPR is to accept quality papers, and not be constrained by review scores. Please base your recommendations for accept/reject on the reviews as well as the contributions and merits of papers. Your SAC’s job is to help you calibrate if needed.

Best Practices for Area Chairs

Judge each paper on its own merits:
- Do NOT normalize decisions within your own batch. Even with 15k submissions (lower bound estimate), a batch of 30 papers represents just 0.2% of the total -- far too small to reflect overall acceptance rates. Even a triplet batch of ~100 papers would constitute only 0.67%, so overall acceptance statistics cannot be applied in such small sample sizes.
Your aim is to get at least 3 quality reviews for each paper. Selecting good reviewers at the beginning will help out significantly later on!
Lead discussions: when the discussion period begins, post the highlights of the reviewer claims, and highlight any major points or disagreements. Ask reviewers targeted/individual questions to move the conversation forward! (e.g., R2 mentioned unclear novelty. Could R2 point to the most relevant works that overlap?)
Follow reviewer consensus for unanimous decisions, unless there are extraordinary unusual circumstances
- For example, to accept a paper with unanimously negative reviews, there should be significant referee error, or a very convincing rebuttal; to reject a paper with unanimously positive reviews, there should be exceptional circumstances such as significant previously undetected technical errors, or undetected fraud or plagiarism.
- You should be checking reviews as they are submitted, and catching fundamental errors at that time, not during the triplet discussion period.
For mixed reviews, you should analyze all reviews critically, and see if you agree with their claims. Make sure to get help within your triplet!
Keep your discussions within triplets. If you need a conflict-free outside opinion, reach out to your SAC.
Write a standalone meta-review
- This is a decision rationale, it should contain an argument why the paper should be accepted or rejected
- Avoid: “all reviewers said reject, so the paper is rejected” - this is not acceptable if a rebuttal was provided
Authors may not agree with your decision, but they should understand it (i.e., sufficient and clear arguments should be provided for why the decision was made).