VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations and a statically validated execution plan before any frame is observed, is presented.
Wenzhuo Xu, Yu-Chen Zhu, Chongjian Ge et al.· 0 citations
This work establishes a novel theoretical analysis: DDPO is an implicit form of score/flow matching with noisy targets, which increases variance and slows convergence, and introduces Advantage Weighted Matching (AWM), a policy-gradient method for diffusion.
This work introduces Latent Dynamics Reasoning (LDR), the first video world model that extrapolates learned dynamics beyond its training distribution and can even generalize under severe shift.
Haodong Li, Shao-Teng Liu, Tian-Yu Wang et al.· 0 citations
Chimera, a hybrid visual diffusion backbone with a principled scaling recipe that combines Kimi Delta Attention for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for direct global interaction, and modality-aware short convolutions for local spatiotemporal context is int...
Chongjian Ge, Hanwen Jiang, Tianyu Wang et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.