Video foundation models now reach human-level accuracy on physical-reasoning benchmarks, yet such tasks require predicting unobserved physical outcomes. Do these models perform human-like forward simulation, or do they exploit statistical regularities in visible scenes? Accuracy alone cannot distinguish these strategie...
Fan-Hong Li, Shu-Rui Zheng, Zi Yin et al.· 0 citations
SimpleMemVLA, a VLA without a dedicated memory module that uses the backbone's native video context directly as memory, achieves state-of-the-art results on four memory benchmarks without loss on general-purpose control, and with the same backbone and training setup it outperforms retrieval, compression and recurrent-s...
PhyAI, a Physical AI inference engine with a single runtime that keeps architecture-specific conditioning, solver, cache, and output logic in model adapters while sharing graph execution, kernels, memory management, and parallel services, is built.
Cheng-Hua Wang, Daliang Xu, Dongqi Cai et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
