Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical memory. However, as memory sequences grow longer and their structures become increasingly complex, managing long-range spa...
Ying Yang, Gui-Yu Zhang, Liang-Hua Huang et al.· 0 citations
High-fidelity closed-loop simulation for autonomous driving increasingly relies on dense multi-view 3D reconstruction. While recent feed-forward geometric foundation models have revolutionized per-scene optimization, applying them to continuous, long-horizon driving sequences is computationally intractable due to GPU m...
Tian-Yi Yang, Hao-Jun Yang, Ji-Peng Xiao et al.· 1 citation
OptiGeo is introduced, a bias-aware training framework that rehabilitates biased real supervision using a clean-geometry teacher and residual-trimmed alignment and outperforms substantially larger 300M-scale monocular models and billion-scale multi-view baselines on transparent-scene benchmarks, while remaining competi...
Mu-Xin Liu, Tian-Bo Liu, Jing Xia et al.· 1 citation
SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference, is introduced, providing a reproducible and extensible foundation for interactive world-model research.
Jun-Chao Huang, Guian Fang, Sheng-Ju Qian et al.· 12 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.