The advancement of sophisticated smart windows exhibiting superior thermoregulation capabilities in both solar spectrum and long-wave infrared range maintains a prominent objective for researchers in this field. In this study, a Janus window is proposed and prepared based on polymer-stabilized liquid–crystal films/thermochromic materials. It can achieve switchable front long-wave infrared emissivity (ε_Front) and solar modulation ability (ΔT_sol) through dynamic flipping, making it suitable for different seasonal energy-saving requirements. Outdoor experiments show that under daytime illumination, the indoor temperature decreases by 8 °C, and the nighttime temperature drops by 5 °C. MATLAB simulation calculations indicate that the daytime cooling power is 93 W m^-2, while the nighttime cooling power reaches 142 W m^-2. Interestingly, by modifying the conductive layer, it can effectively shield electromagnetic radiation (within the X-band frequency range (8.2–12.4) GHz). Energy simulation reveals the substantial superiority of this device in energy savings compared with single-layer polymer-stabilized liquid crystal, poly(N-isopropyl acrylamide), and normal glass when applied in different climate zones. This research presents a compelling opportunity for the development of sophisticated smart windows characterized by exceptional thermoregulation capabilities.

Research team offers a comprehensive review of cognitive strategy-enhanced persuasive dialogue agents (CogAgent). They formalized cognitive strategies from cognitive psychology, summarized research, and analyzed benchmarks and evaluation metrics to advance the field.

Research team proposed POGs, providing containers with individual log configuration, storage, and view to enhance isolation, security, and efficiency with negligible performance overhead.

Research team proposed MDIDCN, a dual-channel network model for predicting miRNA-drug interactions (MDIs). Using TCN and BiLSTM, their model achieved high accuracy.

Research team proposed new data placement algorithms for scratch-pad memory (SPM) in embedded systems. Their fine-grained and multi-granularity algorithms effectively reduce data transfer and access latency, addressing inconsecutive array access and memory activation overhead.

Research team proposed an efficient algorithm for model diagnostics. Their method approximates the ranking of failure probabilities for components, achieving high accuracy and significant runtime improvements over existing algorithms.

Research team from Shandong University introduced MetaGIN, a lightweight deep learning framework for molecular property prediction. MetaGIN achieves SOTA performance with fewer parameters, using a “3-hop convolution” technique and MetaFormer architecture to balance efficiency and accuracy.