We welcome all contributions related to understanding and explaining the inner workings of foundation models. Potential areas of interest include, but are not limited to
Understanding of foundation models. Empirical and theoretical analysis of the inner workings of foundation models. Probing techniques to shed light on internal representations and their effect on downstream performance.
Interventions. Activation engineering, mechanistic interventions, and methods for targeted editing of model knowledge and/or behaviour.
Parameter-efficient fine-tuning. Low rank adaptations for efficient model customisation, strategies for maintaining general capabilities whilst specialising for specific tasks.
To submit your paper, please consider the following instructions and guidelines.
All contributions should be made via OpenReview. We welcome submissions of original, unpublished material, as well as work that is currently under review (i.e. has been submitted but not yet accepted elsewhere).
Page limit: Papers should be up to 4 pages, excluding references and supplementary materials.
Template: Please use the NeurIPS 2024 style files.
Double blind reviews: authors should anonymize their submissions to ensure a double blind review process.
LLMs policy: In the preparation of your contributions, the use of LLMs is allowed only as a general-purpose writing assist tool.
Publication. The workshop is non-archival. By default, accepted papers will be made publicly available on OpenReview. Authors can choose to opt out if they do not wish for their work to be shared publicly.
Reviewing. Authors should nominate at least one person per contribution as a reviewer. The expected reviewing load is 2-3 papers. If you'd like to nominate someone as a reviewer or self-nominate, please fill in this form.
Attending the workshop. Our workshop is primarily an in-person event, and authors are asked to present a poster at the workshop if possible. A subset of papers will be selected for presentation in short spotlight talks.
Dual Submission policy. We accept dual submission with other workshops that do not happen during the same date.
Submission open : 1 August, 2024, AoE.
Submission deadline: 13 September, 2024, AoE.
Submission deadline: 6 September, 2024, AoE.
Reviews due: 4th October, 2024, AoE.
Reviews due: 30 September, 2024, AoE.
Decision notification: on or before 9 October, 2024.
NEW! Camera-ready deadline: 29 November AOE.
For any questions, please contact mint2024-workshop@googlegroups.com.
Camera-ready papers are allowed maximum of 6 pages, excluding references and appendices.
All papers must follow the NeurIPS 2024 style files.
We will be giving an iPad for the best paper award.
Thank you for serving on the program committee as a reviewer. Your commitment and time investment is crucial for the success of the MINT workshop, and we are deeply grateful for your effort!
Below we summarize some key dates and instructions for the reviewing process:
You should expect to be assigned between 2-3 papers of 4 pages maximum length each for review.
The reviewing period starts on September 16th and ends on September 30th 2024. Please make sure to submit all reviews for your assigned papers by the end of the reviewing period.
When writing your review, please keep in mind that after decisions have been made, reviews and meta-reviews of accepted papers will be made public.
When writing your review, please provide your thoughts on the following aspects:
Summary: Briefly summarize the paper and its contributions in 2-3 sentences. This is not the place to critique the paper; the authors should generally agree with a well-written summary.
Strengths and Weaknesses: Please provide an assessment of the strengths and weaknesses of the paper, touching on each of the following dimensions:
Alignment to theme of workshop and interest to workshop audience (see cfp here: https://sites.google.com/view/mint-2024/call-for-papers)
Originality and significance
Clarity of writing
Reproducibility
Rating: Based on your assessment of strengths and weaknesses, please provide an assessment as to whether this paper should be accepted to the workshop.
We thank you again for being a part of the program committee. Should you have any questions or concerns, please reach out to us via mint2024-workshop@googlegroups.com.