Learning humanoid loco-manipulation from human demonstrations rests on observing how locomotion, posture, and object interaction evolve together as tasks unfold. Scaling collection across diverse environments, in turn, favors lightweight, portable capture systems. Yet, existing datasets provide only partial views of th...
Yun-Song Zhou, Xue-Kun Jiang, Hai-Qi Shen et al.· 0 citations
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
Vision-language navigation requires agents to follow natural-language instructions to reach target locations, making high-quality language supervision essential. Since human annotation is costly, prior work has explored scalable data synthesis methods. However, existing methods typically either use separate models for...
Song-Ze Li, Hao-Ming Gu, Zi-Yang Gong et al.· 0 citations
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.
This work dissects advantage-guided VLA post-training through a controlled empirical study that separates these design choices while accounting for their distinct estimands, and develops stage-specific offline evaluation methods to screen alternative choices efficiently, without requiring extensive real-robot policy ev...
Jia-Hang Cao, Han-Ye Zhao, Hang Lai et al.· 0 citations
This work introduces InternW0, the first instantiation of the InternW physical world model series from Shanghai AI Laboratory, built around omnimodal interfaces, asynchronous multi-frequency processing, and local physical modeling under partial observations and external influences.
Ji-Song Cai, Yao Mu, Gan-Lin Yang et al.· 0 citations
InternVLA-A1.5 is presented, which builds the policy on a native VLM backbone that keeps training on VQA and subtask prediction, and attaches a lightweight unified expert for continuous action generation, and achieves the best overall results on all six simulation benchmarks.
