Learning task progress from robot demonstrations provides a practical way to construct dense shaping rewards for robotic reinforcement learning. A common approach uses normalized demonstration time as progress labels, implicitly assuming monotonically increasing task progress. During policy exploration, however, actual...
Jun Nie, Zi-Tian Fan, Jia-Chen Zhang et al.· 0 citations
Simulation-ready world reconstruction demands physical interactivity beyond visual realism, which existing black-box 3D generation fails to deliver. We present NeoWorld-3, a coding-agent framework that reconstructs interactive 3D worlds from visual observations via tunable, executable programs. At its core, NeoSDK prov...
Eachen Soong, Zi-Jian Niu, Hao Xu et al.· 1 citation
Time-series question answering (TSQA) requires grounding linguistic queries and diverse answer formats in complex numerical observations. However, existing methods heavily overfit to specific datasets and struggle to generalize when input series, question contexts, and answer requirements shift simultaneously. To addre...
VPTwin is proposed, a Real-Sim-Real video prediction framework that anchors real-world future prediction using real-synchronized simulation twins and establishes a predictive planning loop using VPTwin to visually verify VLM-proposed actions and guide reliable real-world execution.
Zheng-Hao Xiao, Min-Ting Pan, Nan-Tian He et al.· 0 citations
NeoWorld-Pro is proposed, a framework that reformulates monocular scene reconstruction as procedural programming for interactive 3D environments and outperforms open-loop and prior monocular reconstruction methods, while enabling complex downstream tasks such as stable stacking and fine-grained manipulation.
Yu-Meng He, Eachen Soong, Xiao-Tian Yang 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.