Multimodal Alignment for a Pluralistic Society (MAPS) Call for Papers
We are excited to announce the
Multimodal Alignment for a Pluralistic Society (MAPS)
workshop at CVPR 2026,
featuring an outstanding lineup of speakers. This workshop will bring
together researchers from CV, NLP, HCI, social sciences, and
humanities, recognizing that pluralistic multimodal AI systems demand
both technical expertise and an understanding of human values.
We invite you to:
Participate in our challenge. We host a challenge on Machine
Translation for Vision, which focuses on adapting images to fit
different cultures while keeping their meaning. We offer two
tracks: open (using open-sourced models only) and proprietary (any
use of proprietary models). More details on the dataset and the
task can be found in the paper, which won the Best Paper award at
EMNLP 2024! The challenge will be hosted on Hugging Face
challenges. The results of the challenges and winning entries will
be presented at the workshop. Participate here:
https://huggingface.co/spaces/cmu-lti/MachineTranslationforVision
Start date: March 3, 2026
End date: April 10, 2026
Submit your papers of up to 4 pages that discuss but are not
limited to identifying effective evaluation tasks, benchmarks, and
metrics to assess cultural awareness and alignment in VLMs; new
methodology for improving cultural authenticity, pluralism, and
fairness of AI systems; and new techniques for capturing multiple
cultural perspectives and building multimodal models that can
amplify underrepresented communities and handle low-resource data
at scale.
Start date: March 3, 2026
End date: April 10, 2026
Submit via OpenReview:
https://openreview.net/group?id=thecvf.com/CVPR/2026/Workshop/MAPS
For more details see the Call for Papers:
https://sites.google.com/view/maps-cvpr/call-for-papers.
Useful links:
Workshop Website: https://sites.google.com/view/maps-cvpr
Call for Papers: https://sites.google.com/view/maps-cvpr/call-for-papers
Challenges: https://sites.google.com/view/maps-cvpr/challenges
Please feel free to share this with colleagues who may be
interested. We look forward to your participation.
For any workshop-related queries including the challenge, please drop
an email at maps.cvpr@gmail.com.
Yours sincerely,