下一强制：基于多块预测的因果世界建模

摘要

自回归视频生成已成为世界动作模型（World Action Models, WAMs）的一种强大范式。然而，现有方法存在训练收敛慢、收敛精度有限的问题，尤其是在高帧率下——因为训练监督仅限于当前块，缺乏关于未来动态的明确信号；同时，迭代视频去噪也导致推理速度缓慢。本文提出Next Forcing，一种用于因果世界建模的多块预测（MCP）框架，可实现更快的训练、更高的精度和加速的推理。受大语言模型中多词元预测的启发，Next Forcing引入了MCP训练目标，通过为骨干模型添加轻量级辅助MCP模块，使其能够同时去噪多个未来时间视界（下一个、下两个、下三个块）的视频块。这些MCP模块跨预测深度形成因果链，其中融合了骨干模型多层中间特征的结果被用于预测未来动态，使得近期预测能够为更远期预测提供信息，并向骨干模型反馈密集的多尺度时间监督。在训练中，MCP模块显著加速收敛并提升收敛精度，尤其是在高帧率下：在50帧/秒条件下，Next Forcing在5000训练步时相对于LingBot-VA实现了93.1%的相对提升，收敛速度提升2.3倍，并在RoboTwin基准上创下新纪录（Clean/Random上分别为94.1%/93.5%）。在推理时，保留MCP模块可并行预测当前块与下一视频块，实现2倍推理加速。Next Forcing在评估视频生成中物理规律遵循性的PhyWorld基准上也展现出显著改进，并在通用视频预训练中实现超过50%的FVD降低。

English

Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow training convergence and limited converged accuracy, particularly at high frame rates, as the training supervision is confined to the current chunk without explicit signals about future dynamics; they also suffer from slow inference due to iterative video denoising. In this paper, we present Next Forcing, a multi-chunk prediction (MCP) framework for causal world modeling that enables faster training, higher accuracy, and accelerated inference. Inspired by multi-token prediction in large language models, Next Forcing introduces an MCP training objective that augments the main model with lightweight auxiliary MCP modules to simultaneously denoise video chunks at multiple future temporal horizons (next^1, next^2, next^3 chunks). These MCP modules form a causal chain across prediction depths, where intermediate features fused from multiple layers of the main model are leveraged to predict future dynamics, allowing near-future predictions to inform farther-future ones and providing dense multi-scale temporal supervision back to the main model. During training, the MCP modules significantly accelerate convergence and improve converged accuracy, especially at high frame rates: at 50 fps, Next Forcing achieves a 93.1% relative improvement over LingBot-VA at 5k training steps and 2.3x faster convergence, and establishes new state-of-the-art results on the RoboTwin benchmark (94.1/93.5% on Clean/Random). At inference, the MCP modules can be retained to predict the next video chunk in parallel with the current one, achieving 2x inference acceleration. Next Forcing also demonstrates significant improvements on PhyWorld, a benchmark evaluating adherence to physical laws in video generation, and over 50% FVD reduction on general video pretraining.