# Next Forcing：基于多块预测的因果世界建模

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-09 08:00
- AIHOT 分数：68
- AIHOT 链接：https://aihot.virxact.com/items/cmq84tlzt04isslepb1xmghwn
- 原文链接：https://arxiv.org/abs/2606.11187

## AI 摘要

Next Forcing 提出多块预测（MCP）框架，受大语言模型多 token 预测启发，在主模型上添加轻量级辅助 MCP 模块，同时对多个未来时间步的视频块去噪。50fps 下训练 5k 步时相对 LingBot-VA 提升 93.1%，收敛速度加快 2.3 倍；在 RoboTwin 基准上达 94.1%（Clean）/93.5%（Random）新 SOTA。推理时保留 MCP 模块可实现 2 倍加速。在物理规律基准 PhyWorld 上也有显著提升，通用视频预训练 FVD 降低超 50%。

## 正文

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.