Multi-modal Controllable Neural Generation Project

How should creative AI know how to collaborate with human, while learning to take multi-modal inspirations?

Projects

Zhiyu Lin, Mark O Riedl

Oral at The 17th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-21)

Plug-and-blend is a human-aware text generating framework that supports both fine-grained weighted topics and area-of-effect narrative goals, and is still relevant thanks to its minimal requirement of... "any GPT model works with it"!

Zhiyu Lin, Kyle Xiao, Mark Riedl

Oral at The 15th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-19)

GenerationMania is the first keysounded rhythm action game stage generator, that knows how to interpret the semantics of music and incorporate design goals from creators!