I am Payam Jome-Yazdian, a Ph.D. candidate, and research & teaching assistant in Computing Science at Simon Fraser University. I work with Dr. Angelica Lim in the ROSIE Lab and collaborate with the MARS Lab under the supervision of Dr. Mo Chen, conducting collaborative Ph.D. research with HUAWEI on generative and multimodal methods that ground expressive human behavior in AI systems. My work spans computer vision and machine learning, from self-supervised representations and diffusion models to multimodal language alignment, applied to digital humans, robotics, and interactive media.

During my Ph.D., I interned with the Digital Humans team at Netflix Eyeline Studios – Powered by Netflix as a machine learning researcher, working with Jim Su, Ahmet Levent Taşel, and Paul Debevec on controllable motion and video generation. I later joined Electronic Arts SEED as a machine learning research intern, collaborating with Konrad Tollmar, Han Liu, Hau Nghiep Phan, and Ray Phan to advance panoramic video diffusion pipelines.

Research interests include:

• Video diffusion and generative models for immersive media
• Multimodal learning for human motion, gestures, and style transfer
• LLM-driven pipelines that connect language, perception, and action