Next Forcing accelerates video generation with multi-chunk prediction

By PulseAugur Editorial · [1 sources] · 2026-06-09 17:59

Researchers have introduced "Next Forcing," a novel framework for causal world modeling in autoregressive video generation. This multi-chunk prediction (MCP) approach enhances training speed and accuracy by predicting multiple future video chunks simultaneously. The method has demonstrated state-of-the-art results on benchmarks like RoboTwin and PhyWorld, and offers a 2x inference acceleration. AI

IMPACT Accelerates video generation training and inference, potentially enabling more complex real-time simulations and applications.

RANK_REASON This is a research paper detailing a new method for video generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

arXiv cs.CV TIER_1 English(EN) · Yinghao Xu · 2026-06-09 17:59

Next Forcing: Causal World Modeling with Multi-Chunk Prediction

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 c…

COVERAGE [1]

Next Forcing: Causal World Modeling with Multi-Chunk Prediction

RELATED ENTITIES

RELATED TOPICS