This paper proposes a new architectural primitive for multimodal generative AI by combining MLLMs, Diffusion Transformers, and a Relation-Adaptive Mixture-of-Experts. This innovative architecture offers a foundational approach for integrating diverse data types and structured knowledge more effectively within generative models, particularly for complex multimodal tasks.
Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube
Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram