← All Research Tracks

Alignment & Safety in T2I and T2V Models

Working on safety alignment of Text-to-Image & T2V diffusion and flow matching models using a neurosymbolic approach called scene graphs.

  • Developing a novel methodology to reduce hate content in T2I Diffusion models using a safety potential-guided rectified flow matching in the CLIP embedding space.
  • Benchmarked debiasing and safety methodologies — TRCE, CURE, SAEUron, and DoCo — on lab's DETONATE dataset.

TRCE Paper Presentation

CSD 722 Project presentation: Depth Conditioned Video Generation

Calendly - Let's meet!