Autoregressive Video Generation
PulseAugur coverage of Autoregressive Video Generation — every cluster mentioning Autoregressive Video Generation across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
History Forcing enhances long-horizon video generation consistency
Researchers have developed a new technique called History Forcing to improve the long-range consistency of autoregressive video generation models. This method uses historical context residuals to correct distillation ta…
-
AI research tackles long-video memory with novel weight-internalization techniques · 7 sources tracked
Researchers are developing novel methods to enhance the memory capabilities of AI models, particularly for processing long video streams. Several papers introduce techniques that internalize historical data into model w…
-
New research tackles long-term memory in autoregressive video generation · 3 sources tracked
Three new research papers address challenges in autoregressive video generation, focusing on improving long-term memory and scene consistency. Stream4D introduces a 4D reconstruction reward and motion prior to reduce ge…