BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models
Po, Ryan, Chan, Eric Ryan, Chen, Changan, Wetzstein, Gordon
原文摘要
Autoregressive video models are promising for world modeling via next-frame prediction, but they suffer from exposure bias: a mismatch between training on clean contexts and inference on self-generated frames, causing errors to compound and quality to drift over time. We introduce Backwards Aggregation (BAgger), a self-supervised scheme that constructs corrective trajectories from the model's own rollouts, teaching it to recover from its mistakes. Unlike prior approaches that rely on few-step distillation and distribution-matching losses --which can hurt quality and diversity -- BAgger trains with standard score or flow matching objectives, avoiding large teachers and long-chain backpropagation through time. We instantiate BAgger on causal diffusion transformers and evaluate on text-to-video, video extension, and multi-prompt generation, observing more stable long-horizon motion and better visual consistency with reduced drift.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表