Call For Papers

We invite authors to submit anonymized papers of up to 4 pages that discuss identifying effective evaluation tasks, benchmarks, and metrics to assess cultural awareness and alignment in VLMs; and new methodology for improving cultural awareness of AI systems. Below, we provide a non-exhaustive list of topics we hope to cover. We also broadly welcome any submissions that are relevant to cultural awareness in AI systems.

New tasks, benchmarks, and evaluation metrics:

• • Designing assessments to measure cultural understanding in VLMs

  • Developing benchmarks and metrics for evaluating fairness and inclusivity

Improving cultural awareness in VLMs:

• • Ensuring diverse training data and mitigating biases

  • Enhancing fairness in multimodal models

Cultural value alignment:

• • Aligning VLMs with diverse cultural norms using human-in-the-loop and preference-based techniques

  • Addressing ethical considerations in adapting AI to global values

Multilingual Vision-Language Models:

• • Building VLMs that understand multiple languages

  • Addressing challenges in multilingual representation learning

Submission Instructions:

We invite authors to submit anonymized papers of up to 4 pages, excluding references and appendices, in PDF format through the OpenReview submission portal. Submissions must follow the CVPR 2025 template. We welcome works in progress, position papers, policy papers, and academic research papers.

Timeline

• Call for workshop papers: March 14, 2025

• Paper submission deadline: April 22, 2025 April 28, 2025

• Notification of acceptance: May 5, 2025

• Workshop date: June 12, 2025

All accepted papers will be available on the workshop website but considered non-archival.

The OpenReview link to submit papers can be found here: VLMs-4-All OpenReview

Dual Submission

We encourage submissions of relevant work that has been previously published, is in progress, or is to be presented at the main conference. The accepted papers are non-archival and will not appear in official CVPR proceedings. 

Contact

For any queries please drop an email at vlms4all@gmail.com