Tag
Explores a storyboard-planned approach for AI cinematics that builds sequence structure before generating shots individually, resulting in more coherent video compared to single-prompt generation, while noting current weaknesses like identity drift and interaction physics.
This paper introduces the Structured Recurrent Mixer (SRM), an architecture enabling algebraic conversion between parallel training and recurrent inference without specialized kernels. Experiments show SRMs achieve significantly higher throughput and concurrency compared to Transformers, with effective performance in reinforcement learning tasks.