Skip to content
@AIM-SCU

AIM @ SCU

Inclusive & Multimodal AI Research Laboratory @ SCU

AIM Lab

Santa Clara University | Led by Dr. Oana Ignat

The AIM Lab builds equitable AI systems for people — across languages, cultures, and modalities.

We work at the intersection of:

  • 🌐 Cross-cultural & multilingual AI
  • 🤝 Multi-agent and pluralistic alignment
  • 🖼️ Multimodal generation (text, image, video)
  • 🎓 AI for education and mentorship
  • ⚖️ Fairness, ethics, and representation

Our research combines dataset creation, AI model design, and comprehensive evaluation to develop practical AI solutions that are both accurate and socially grounded.

🔬 Recent Projects

  • MentorQA — multilingual mentorship-focused QA beyond factual correctness. 📄 https://arxiv.org/pdf/2601.17173
  • MemeXGen — cross-cultural meme transcreation (Chinese ↔ US), studying how multimodal humor adapts across cultures while preserving intent and meaning. 📄 https://arxiv.org/pdf/2602.02510
  • MosAIG — multicultural text-to-image generation benchmark evaluating how well generative models represent diverse cultural identities. 📄 https://arxiv.org/pdf/2502.15972

Ultimately, research is for people and can enable demographic-aware technologies that make a lasting positive impact on society.Why AI is WEIRD

📍 Santa Clara University, Silicon Valley
🌐 https://oanaignat.github.io/aim/
🏫 https://www.scu.edu/engineering/faculty/ignat-oana/

Popular repositories Loading

  1. MentorQA MentorQA Public

    A comprehensive end-to-end pipeline for transforming long form videos and podcasts into educational Question-Answer pairs using a multi-agent AI approach and simplifying the long form content.

    Python 3 2

  2. MemeXGen MemeXGen Public

    We present a novel approach to cross-cultural meme transcreation using vision-language models, focusing on preserving communicative intent while adapting cultural references.

    Python 3

  3. WhenCulturesMeet WhenCulturesMeet Public

    This repository contains the code and data for our paper on muticultural text to image generation and evaluation.

    Jupyter Notebook 1

  4. MAVEN MAVEN Public

    A Multi-Agent Framework for Multicultural Text-to-Video Generation in Chinese, Romanian and American

    Jupyter Notebook 1

  5. GRADE GRADE Public

    GRADE: Generalizable Reasoning-Aware Dialogue Evaluation for AI Tutors

    Python 1

  6. .github .github Public

Repositories

Showing 7 of 7 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…