This work introduces Asking the World (ATW), a generalist agent that constructs and interrogates task-relevant executable worlds through two adaptive stages: World Modeling calibrates a world from video, while World Probing queries, simulates, and intervenes on it to obtain question-relevant evidence.
Shen-Xiang Zeng, Chen Yang, Pei-Yao Chen et al.· 0 citations
Topology is established as a distinct generalization axis beyond arbitrary-geometry compatibility and influence extends across the Hodge spectrum rather than remaining confined to the harmonic kernel, and global, low-frequency structural priors may help organize predictions in the faster-decaying complementary componen...
Pei-Yao Chen, Zhou-Yuan Xu, Ran Ding et al.· 0 citations
BlueprintAgent (BPA), a constraint-triggered multimodal agent for simulation-ready frame extraction from scanned blueprints, is presented, which treats the MLLM as the primary reader and decision maker, with OCR and computer vision supplying localized evidence.
Zhou-Yuan Xu, Chen Yang, Lin-Hao Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.