G

Gyusang Cho

Postdoctoral Researcher ยท AI/ML

I am a postdoctoral researcher working on reasoning in diffusion language models and safety in vision-language models. My research aims to understand and improve the generative capabilities of diffusion-based architectures on language, multimodal data, and to develop robust safety mechanisms for multimodal AI systems.

Research Interests

Diffusion Language Models

Enabling reasoning capabilities in diffusion-based language models, including distillation of AR reasoning traces and investigating semantic superposition in continuous token spaces.

VLM Safety

Concept erasure in text-to-image diffusion models, safety classification for generated content, and understanding differential erasure difficulty across concept types.

Generative Models

Diffusion processes, masked diffusion, flow matching, and their mathematical foundations for both language and vision domains.

AI Alignment

RL-based fine-tuning for diffusion models, and developing evaluation frameworks for safety and robustness in multimodal systems.

Publications

Paper Title Here
Gyusang Cho, Co-Author Name, Co-Author Name
Conference / Journal Name, 2025
Another Paper Title Here
Co-Author Name, Gyusang Cho, Co-Author Name
Conference / Journal Name, 2024

Notes

Note
Gyusang Cho, Co-Author Name, Co-Author Name
Conference / Journal Name, 2025
Another Note Title Here
Co-Author Name, Gyusang Cho, Co-Author Name
Conference / Journal Name, 2024