展望未来:自回归视频生成中的未来演化建模
TLDR
提出未来块预测(FCP)辅助目标,使自回归视频扩散模型预测未来块,提升物理合理性且不改变推理。
评分理由
The paper proposes a clean, compute-efficient auxiliary objective that directly targets future evolution, with no extra encoder and unchanged inference. Strengths include empirical gains in physical plausibility and structured representations, but the abstract lacks explicit benchmark details and positions world-model benefits as speculative.
Read-first 评分解释
综合优先阅读分 22.8,由主题、引用、图谱、方法、可复现性和近期性等信号加权得到。 原始总分保留为 23。
研究版图角色
前沿论文
排序敏感性
稳定性:volatile;排名波动范围:175。