Adobe Research Advances Long-Term Memory in Video Generation

Adobe Research proposes a method using State-Space Models and dense local attention to enable long-term memory in video generation models, addressing a key challenge in video world models.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementMay 28, 2025, 09:31 AM 76%

   Adobe Research introduces State-Space Models to enable long-term memory in video world models

   Adobe Research proposes a method using State-Space Models and dense local attention to enable long-term memory in video generation models, addressing a key challenge in video world models.

   Read the full story →