With the development of the Internet and intelligent education systems, the significance of cognitive diagnosis has become increasingly acknowledged. Cognitive diagnosis models (CDMs) aim to characterize learners’ cognitive states based on their responses to a series of exercises. However, conventional CDMs often struggle with less frequently observed learners and items, primarily due to limited prior knowledge. Recent advancements in large language models (LLMs) offer a promising avenue for infusing rich domain information into CDMs. However, integrating LLMs directly into CDMs poses significant challenges. While LLMs excel in semantic comprehension, they are less adept at capturing the fine-grained and interactive behaviours central to cognitive diagnosis. Moreover, the inherent difference between LLMs’ semantic representations and CDMs’ behavioural feature spaces hinders their seamless integration. To address these issues, this research proposes a model-agnostic framework to enhance the knowledge of CDMs through LLMs extensive knowledge. It enhances various CDM architectures by leveraging LLM-derived domain knowledge and the structure of observed learning outcomes taxonomy. It operates in two stages: first, LLM diagnosis, which simultaneously assesses learners via educational techniques to establish a richer and a more comprehensive knowledge representation; second, cognitive level alignment, which reconciles the LLM’s semantic space with the CDM’s behavioural domain through contrastive learning and mask-reconstruction learning. Empirical evaluations on multiple real-world datasets demonstrate that the proposed framework significantly improves diagnostic accuracy and underscoring the value of integrating LLM-driven semantic knowledge into traditional cognitive diagnosis paradigms. 

Researchers at the Nano Life Science Institute (WPI-NanoLSI), Kanazawa University, report in ACS Nano the successful creation of artificial synaptic vesicles that can be remotely controlled by near-infrared (NIR) light. By embedding a phthalocyanine dye into lipid bilayers, the team achieved local heating that modulates membrane permeability, enabling precise release of neurotransmitters such as acetylcholine. These findings demonstrate that nanoscale heating can control communication between nerve cells. The work opens new avenues for non-genetic modulation of neuronal activity, with potential applications in neuroscience, drug delivery, and bioengineering.

Using EUROSTAT data and double randomization, the co-led study improves the Benefit of the Doubt model through a novel Ensemble-DEA framework that mitigates the curse of dimensionality in SDG indicators. Published in Expert Systems with Applications, the method offers more reliable EU performance rankings and benchmarking tools for evaluating sustainability policies across member states.

In an exciting exploration of environmental sustainability, researchers at Zhaoqing University, China, have uncovered groundbreaking insights into the carbon dynamics of waterlogged pond fields. Led by Dr. Guodong Yuan from the Guangdong Provincial Key Laboratory of Eco-Environmental Studies and Low-Carbon Agriculture in Peri-Urban Areas and the Guangdong Technology and Equipment Research Center for Soil and Water Pollution Control, this study, titled "Unveiling Carbon Dynamics in Year-Round Waterlogged Pond Fields: Insights into Soil Organic Carbon Accumulation and Sustainable Management," offers a fresh perspective on how these unique ecosystems can contribute to carbon sequestration and sustainable land management.

Currently, the development of low-reflection electromagnetic interference (EMI) shielding composite materials for mitigating secondary electromagnetic wave pollution has become a major research focus. However, achieving thinness, high toughness, low reflectivity, and multifunctionality in flexible EMI shielding films remains a challenge. To address this issue, Benliang Liang and Luting Yan from Beijing Jiaotong University, in collaboration with Lan Zhang from Luoyang Institute of Science and Technology, have introduced a "magnetic-electric" Janus structure EMI shielding composite film composed of MXene nanosheets, carbonized ZIF67 (CZIF67) nanoparticles and aramid nanofibers (ANF), balancing thinness(80 μm), high-strength-toughness composite film (110±7 MPa tensile strength, 21% strain, 14.91±0.9 MJ·m⁻³ toughness), (4.3–4.5 dB in 8.2–9.6 GHz) with 44.8 dB SET in the X-band. In addition, This multifunctional material simultaneously integrates electrothermal/photothermal conversion, fire-alarm response, and infrared stealth capabilities, demonstrating exceptional potential for next-generation wearable electronics and harsh-environment applications.