STKD: Distilling Knowledge From Synchronous Teaching for Efficient Model Compression.

Knowledge distillation (KD) transfers discriminative knowledge from a large and complex model (known as teacher) to a smaller and faster one (known as student). Existing advanced KD methods, limited to fixed feature extraction paradigms that capture teacher's structure knowledge to guide the training of the student, often fail to obtain comprehensive knowledge to the student. Toward this end, in this article, we propose a new approach, synchronous teaching knowledge distillation (STKD), to integrate online teaching and offline teaching for transferring rich and comprehensive knowledge to the student.

Weak interactions but potent effect: tunable mechanoluminescence by adjusting intermolecular C-H···π interactions.

A new mechanoluminescent material (4-(diphenylamino)phenyl)(4-(diphenylphosphanyl)phenyl)methanone (CDpP), which displays tunable mechanoluminescent emission colors, has been designed and successfully synthesized. CDpP shows two distinct mechanoluminescent colors (blue and green) in different crystalline states. Single-crystal analyses and femtosecond transient emission studies reveal that the striking tunable mechanoluminescence properties of CDpP mainly originate from the different C-H···π interactions in the crystal structures.