Focusing on the spatial cognitive capabilities of large language models (LLMs), researchers led by Prof. Danhuai Guo from Beijing University of Chemical Technology have introduced SRT4LLM, a standardized framework for testing the spatial cognition of LLMs. The framework systematically assesses LLMs across three key dimensions—spatial object types, spatial relations, and prompt engineering strategies—and establishes a unified testing process to support the development of native geographic LLMs.

The Martian atmosphere has been unexpectedly discovered to be nearly a perfect working medium and unique work patterns of its thermoelectric conversion on Mars have been reported. The inherent advantages of in-situ resource utilization significantly enhance the sustainability of efficient thermoelectric conversion; The inertness, High specific heat capacity, and large molecular characteristics contribute to increased efficiency and power density. Compared to mainstream rare gases, efficiency could improve by 7.4% to 20.0%, and power-density could increase by 1.0% to 14.2%. Notably, conversion efficiency (>22%) can be achieved even at relatively low hot-end temperatures (<973K); Reviewing current space thermoelectric conversion technology, it can achieve higher power-density and efficiency, particularly above 100 kW, it offers significant advantages of lightweight compared to mature technologies; The high-grade waste heat from Martian gas can be utilized for combined oxygen production and heating Mars colony.

An Osaka Metropolitan University team has developed Boccia XR, a rehabilitation program using extended reality technology that can be introduced even in environments with limited space.