TTT2Reel: End-to-End Test-Time Training for Long Video Generation

Generating a long, coherent video requires preserving visual information about previously-generated frames in the window beyond a model's bounded context window. We present TTT2Reel, an end-to-end test-time training framework for chunk-wise autoregressive long video generation that stores evolving visual history in lightweight LoRA parameters. Before generating each new chunk of a video, the model updates these parameters by optimizing a flow-matching loss on the preceding chunk, while keeping the pretrained backbone frozen. We train the model through bilevel optimization, where an inner optimization loop updates the parametric memory through test-time training, and the outer loop optimizes its initial parameters to minimize subsequent prediction losses across the video. To withstand compounding errors in self-generated context at inference, we estimate model-dependent residuals online and replay them into both the memorization and prediction steps during training. Experiments on minute-long video generation show that TTT2Reel achieves the best average rank across six VBench-Long dimensions among the evaluated methods, balancing dynamic content with visual quality and consistency.