Call for Papers

Poster session information:

The workshop poster sessions will be held in the Arch Building Exhibit Hall (poster boards: #48 - 123) on June 18th, from 9:40 to 11:00. Poster boards will be provided and arranged inside the room. Materials for attaching posters will also be provided. The poster panel size, and therefore, the maximum poster size is 8 feet x 4 feet (WxH, aspect ratio 2:1, landscape format), which is the same as the poster panel size for the main conference. The poster room will have tables but no power outlets.

There is also an onsite poster printing option (not mandatory) provided by ARC Document Solutions, offering a cost-effective poster printing solution that includes delivery of your workshop poster to the event by June 17th: https://cvprworkshop.myprintdesk.net/DSF/SmartStore.aspx#!/Storefront

More information about poster printing can be found here: https://cvpr2023.thecvf.com/Conferences/2024/PosterPrintingInformation

Important Dates:

🐈‍⬛ CMT for submissions: https://cmt3.research.microsoft.com/MMFM2024/ 

• Full-length papers with proceedings Track (CVPR format)

  • Paper Submission Deadline: March 14, 2024 March 19, 2024 

  • Notification to Authors: April 07, 2024

  • Camera-ready deadline: April 14, 2024

• Non-archived Track
  Extended abstracts (4 pages) & Papers accepted to CVPR (8 pages)

  • Paper Submission Deadline: March 21, 2024 April 1, 2024 

  • Notification to Authors: April 20, 2024

  • Camera-ready deadline: May 05, 2024

All deadlines are until 11:59 pm Pacific Standard Time (PST).

For any questions, please contact Nina Shvetsova at shvetsov@uni-frankfurt.de

Accepted papers (archived or non-archived) will be presented at the poster session.

Topics:

We invite contributions on the topic of multimodal foundation models (MMFMs). Topics of interest include, but are not limited to:

• Vision / Sound / Speech / Language tasks using Foundation Models in any possible combination 

• Data and model scaling properties of MMFMs

• Self/semi/weakly supervised training of MMFMs

• Multimodal grounding in foundation models

• Generative MMFMs (e.g., text-to-image/video/3D generation)

• Ethics, risks, and fairness of MMFMs

• Efficient training and inference of MMFMs

• Parameter-efficient fine-tuning, prompting, and adapters for MMFMs 

•  Generalization of MMFMs to other domains

• Multi-task and continual learning for MMFMs

• Compositionality and Reasoning Approaches for MMFMs

Submission Guidelines:

• Full-length papers with proceedings (CVPR format). 

Accepted papers in this track will be published in the CVPR workshop proceedings. The work should be original and 4-8 pages long (excluding references). For this track, we follow the CVPR 2024 dual submissions policy. Thus, the work should be sufficiently original and not under review in other venues.

• Extended abstracts (non-archived). 

The minimum page limit is two pages, and the maximum is four pages (including references).  We encourage the submission of work in progress and work that has been previously published on topics relevant to the workshop. Note that these submissions will not be published in the proceedings. For authors who want to submit their accepted work at this workshop to a different journal or conference, please check their double submissions policy. 

• Papers accepted to CVPR 2024 (non-archived)

Full-length papers (up to 8 pages, excluding references) accepted to the main CVPR 2024 conference on topics relevant to the workshop. 

Supplementary material can be added to the same file after the references. For papers with proceedings, the full file size should be under 5MB. 

Manuscripts should follow the CVPR 2024 paper template and should be submitted through the CMT link below.

Review process: single-blind (i.e., submissions need not be anonymized)

🐈‍⬛ CMT for submissions: https://cmt3.research.microsoft.com/MMFM2024/