Vision-language-action (VLA) models achieve strong performance across embodied manipulation tasks by unifying visual understanding, language conditioning, and action generation. However, long-horizon tasks can involve non-Markovian dependencies: successful decisions may require retaining task progress and past interact...
Ting-Wen Du, Hao-Yu Guo, Han-Xue Zhang et al.· 1 citation
This monograph seeks to define physical AI, present its technical landscape, and examine each key technical subfield in depth, and establishes a unified framework for Physical AI: artificial systems that perceive, model, and act upon the physical world through continuous feedback under real-world constraints.
Wei-Nan Zhang, Chun-Hua Shen, Tian-Fan Xue et al.· 0 citations
Real-world videos provide rich demonstrations of manipulation, but turning them into reusable robot skills requires visually aligned environments, executable physical interactions, and mechanisms for learning from experience. We introduce Real2Gym, an agentic Real2Sim2Real framework that turns human and robot demonstra...
Ke-Rui Ren, Ying Xu, Kai-Wen Song et al.· 4 citations
GeoVerse is a framework that synthesizes world-consistent novel views by performing generation within the geometric latent space of a pretrained 3D foundation model and injecting appearance priors from a video generative model via a ControlNet-style adapter.
Ke-Rui Ren, Tao Lu, Lin-Ning Xu et al.· 0 citations
InfiniHand is an end-to-end streaming feed-forward framework that jointly estimates MANO parameters, camera trajectories, and hand locations directly from uncalibrated egocentric video, achieving a 21% reduction in ARCTIC PA-p compared to ViDiHand while substantially mitigating world-space drift.
Causal Imprint is introduced, which learns future-relevant scene changes from training-only future supervision and provides predictive representations directly to the action expert without future-video rollout at inference.
An efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions and demonstrate strong perceptual quality, semantic fidelity, and temporal consistency on unseen videos, as well as improved robustness in downstream 3D reconstruction under severe motion blur.