Text-to-video (T2V) generation has achieved strong visual fidelity, yet its ability to represent multiple cultures within a single scene remains largely unexplored, a gap with real consequences as generative video becomes a mainstream medium for cultural storytelling. We introduce multicultural text-to-video generation as a new task and present the first benchmark designed to study this setting: 243 culturally grounded prompts and 972 videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Using this benchmark, we analyze how current T2V models represent culture with CLIP-based metrics, VLM-as-judge assessments, and video quality measures. As one strategy for improving cultural fidelity, we explore MAVEN, which decomposes prompts into person, action, and location dimensions, each handled by a culturally specialized agent in parallel or sequentially. In our controlled setting, parallel specialization achieves the strongest cultural relevance while maintaining visual quality and temporal consistency, suggesting that structured prompt refinement is a promising direction for multicultural T2V generation. We release our dataset and code at: https://github.com/AIM-SCU/MAVEN.

Question answering systems are usually evaluated for factual correctness, but many real world settings such as education and career guidance require mentorship responses that offer reflection, context, and guidance. We introduce MENTORQA, the first multilingual dataset and evaluation framework for mentorship focused question answering from long form videos, with nearly 9,000 QA pairs from 180 hours of content across four languages. We define evaluation dimensions that measure fluency, clarity, alignment, and mentorship value, and use them to compare Single Agent, Dual Agent, RAG, and Multi Agent QA pipelines under controlled conditions. Multi Agent pipelines produce the strongest mentorship responses, with larger gains for complex topics and lower resource languages. We also study LLM based evaluation and find substantial variation in alignment with human judgments. Overall, MENTORQA establishes mentorship focused QA as a distinct research problem and provides a benchmark for studying agentic architectures and evaluation design in educational AI. The dataset and evaluation framework are released at https://aim-scu.github.io/MentorQA/.

Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes—where people and landmarks originate from different cultures—remains largely unexplored. We introduce multicultural text-to-image generation as a new task and present the first benchmark designed to study this setting. Our dataset contains 9,000 images spanning five countries, three age groups, two genders, 25 historical landmarks, and five languages. Using this benchmark, we analyze the behavior of state-of-the-art text-to-image models across multiple dimensions, including alignment, image quality, aesthetics, knowledge, and fairness. As one strategy for composing cultural and demographic information, we explore MosAIG, a Multi-Agent framework that enhances multicultural image generation by leveraging large language models with distinct cultural personas. Our analysis shows that richer prompt composition can improve image quality and cultural grounding compared to simple prompts, while also revealing substantial disparities across languages and demographic groups. We release our dataset and code at https://github.com/AIM-SCU/MosAIG