Seunghwan Jang

Research interests lie in safety-critical generative AI. Beyond integrating formal safety guarantees (e.g., control barrier functions) into generative models, I focus on designing generative architectures (diffusion, flow matching, discrete diffusion) that are inherently amenable to safety certification. Primary application domains include robotics and language models.

I am always open to discussing research and enjoy exchanging new ideas. Please feel free to reach out to me anytime!

Education

Experience

Research

• Integrating formal safety guarantees (e.g., CBF) into generative models (diffusion, flow matching, discrete diffusion)
• Designing generative architectures inherently amenable to safety certification
• Applications to robotics and language models

Keywords: safety-critical AI, safe generation, diffusion models, flow matching, discrete diffusion, safety-critical control, control barrier functions, robotics, language models