Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First, for dynamic context modeling, we propose MemoryPack, a learnable context-retrieval mechanism that leverages both textual and image information as global guidance to jointly model short- and long-term dependencies, achieving minute-level temporal consistency. This design scales gracefully with video length, preserves computational efficiency, and maintains linear complexity. Second, to mitigate error accumulation, we introduce Direct Forcing, an efficient single-step approximating strategy that improves training-inference alignment and thereby curtails error propagation during inference. Together, MemoryPack and Direct Forcing substantially enhance the context consistency and reliability of long-form video generation, advancing the practical usability of autoregressive video models.
Building similarity graph...
Analyzing shared references across papers
Loading...
Xiaofei Wu
Shandong University of Technology
Guozhen Zhang
XU Zhi-yong
University of Electronic Science and Technology of China
Building similarity graph...
Analyzing shared references across papers
Loading...
Wu et al. (Thu,) studied this question.
synapsesocial.com/papers/68e25385d6d66a53c2474de2 — DOI: https://doi.org/10.48550/arxiv.2510.01784
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: