Video diffusion models generate visually compelling short-term sequences but often struggle to preserve scene geometry and object structure over time. In this paper, we first demonstrate that current video attention cannot identify reliable correspondences across frames, with responses dispersed across multiple regions...
Jun-Feng Ni, Zi-Yu Zhu, Fan Jiang et al.· 0 citations
WorldRoamBench is introduced, an open-world benchmark for long-horizon stability across four dimensions, each with innovations, steps toward IWMs that are stable, physically grounded, memory-faithful, and deployable in real-world applications.
This work progressively distill a bidirectional action-conditioned teacher into a causal student through teacher forcing and ODE distillation, and introduces LongForcing to align long student self-rollouts with an extended-horizon teacher, mitigating accumulated distribution shift and autoregressive drift.
Fan Jiang, Zhaoxu Sun, Mengchao Wang et al.· 6 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
