3D Gaussian Splatting (3DGS) can reconstruct a captured scene photorealistically, but the resulting representation does not by itself support physical interaction. Robot simulation instead requires object-level change, \textit{i.e.}, objects must move independently, make contact, and reveal previously occluded surround...
Run-Yi Yang, De-Heng Zhang, Xiao-Ye Wang et al.· 0 citations
This paper analyzes the theoretical framework and mathematically demonstrate that only-latter timestep updates of diffusion model may be harmful for diversity contrary to the conclusions presented in a previous work, and proposes an incremental Feynman-Kac training based on strong theoretical foundations to achieve the...
iARCS is presented, an iterative agentic reinforcement learning framework that adapts a pretrained scene generator to naturallanguage task requirements and shows that data generated by iARCS improves a base generator, supporting its value as a practical synthetic data generation tool rather than only a controllable sce...