BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs
Graph neural networks (GNNs) on text--attributed graphs (TAGs) typically encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation. However, the repr…
Graph LearningFederated Learning Under Temporal Drift -- Mitigating Catastrophic Forgetting via Experience Replay
Federated Learning struggles under temporal concept drift where client data distributions shift over time. We demonstrate that standard FedAvg suffers catastrophic forgetting under seasonal drift on Fashion-MNIST, with a…
Federated LearningFedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging
Federated learning (FL) is severely hindered by statistical heterogeneity due to variations in scanners, acquisition protocols, and patient populations. Such non-IID data induces client drift during local optimization, l…
Federated LearningMitigating Compounding Error via Video Representation Regularization
Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation tha…
Autonomous DrivingVideo GenerationBidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics
This work presents a new bidirectional autoregressive latent diffusion approach for predicting the evolution of multiple fields (mass density, pressure, velocity, and magnetic field components) for magnetohydrodynamics. …