Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

Ruopeng Gao, Yukun Huang, Jiarui Hu, wangshuai, Wenbo Hu, Ying Shan, Limin Wang

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation: 174 upvotes on Hugging Face Daily Papers, #4 of 58 papers on 2026-10-22. Day-by-day upvote history.

Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes evolve. Under teacher forcing, strong temporal redundancy may allow local visual continuity to serve as a shortcut for current-chunk denoising, reducing the pressure to model visual evolution. We introduce Future Chunk Prediction (FCP), an auxiliary objective jointly optimized with teacher-forced denoising that predicts temporally separated chunks without access to the intervening visual context. Drawing supervision directly from training videos, FCP requires no additional pretrained visual encoder and leaves autoregressive inference unchanged. Our method achieves superior physical plausibility over standard teacher-forced autoregressive training with a lower overall training compute budget, highlighting the effectiveness and efficiency of future-chunk supervision for modeling visual evolution. Intriguingly, our visualizations suggest that FCP fosters a more structured representation space, which may be valuable for building autoregressive world models.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.