6 papers
AquaCap: A Training-Free Underwater Embodied Agent with Code-as-Policy
Xiaoshi Li, Yule Xu, Chunghiu Kong +5
Recent advances in vision-language-action models have stimulated growing interest in underwater embodied intelligence. However, their reliance on large-scale interaction data limit…
Magnetic Quadrupole Lens and Current-Induced Quadrupolar Dynamics of Antiskyrmion
Linfeng Du, Yang Liu, Peng Yan +1
We demonstrate that antiskyrmions can serve as magnetic quadrupole lenses that focus or defocus electric currents traversing them. We showcase the antiskyrmion core as a focal poin…
Adaptive Scaffolding Needs Contingency: An AI Tutor That Escalates and Fades on What the Learner Does
Xinmeng Hou, Yuxuan Weng, Chin Hsien Yeh +5
Coding assistants raise task performance, but learners plan and monitor less. Giving less away, the usual fix, conflates two things: how much work a system carries (cognitive load)…
Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling
Yu Sha, Junqi Tao, Dixin Zhou +10
Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. We develop…
PileBelief: Persistent Physical State for Interaction-Driven World Modeling
Hongyi Lin, Song Zhang, Haiquan Liu +3
World models allow robots to anticipate action consequences before execution. This capability is especially valuable in excavation, where each scoop reshapes the terrain and affect…
Physical-Touch Observability from Wrist Wrench in Granular Scooping
Hongyi Lin, Song Zhang, Xubo Liu +1
Mining and earthmoving are important real-world deployment settings for embodied intelligence. Autonomous transport and driving systems have improved substantially, but loading and…