News / January 22, 2027

Workshop at SSWR 2027: Multimodal AI for social work research

At the SSWR Annual Conference in San Francisco, Nari Yoo (University of Michigan), Cheng Ren (University at Albany, SUNY), and Gaurav Sinha (University of Georgia) will lead a workshop on analyzing image, audio, and video data using large language models.

The session is on Friday, January 22, 2027, from 8:00 to 9:30 AM in Union Station 21 at the Hilton San Francisco Union Square. It has three parts:

• Foundations of multimodal AI: how these models differ from text-only language models, which research tasks they support, and their current limitations
• Technical implementation: Python tutorials that run open-source models such as Gemma locally through Ollama or LM Studio
• Practical considerations: data privacy, informed consent for multimedia data, algorithmic bias, and when local models protect participant confidentiality better than cloud-based APIs

The workshop is designed for researchers and practitioners with no prior experience in multimodal AI. Basic familiarity with Python helps but is not required, since all code comes in ready-to-run Jupyter notebooks.