Deep‐red/near‐infrared (DR/NIR) organic light‐emitting diodes (OLEDs) are promising for applications such as night‐vision readable marking, bioimaging, and photodynamic therapy. To tune emission spectra into the DR/NIR region, red emitters generally require assistance from intermolecular interactions. But such interactions generally lead to sharp efficiency declines resulting from unwanted quenching events. To overcome this challenge, herein, an advanced method via strategically managing the intermolecular interactions of thermally activated delayed fluorescence (TADF) emitters is proposed. The proof‐of‐concept molecule called DCN‐SPTPA exhibits impressive resistance to quenching while delivering controllable aggregation behavior for redshifting the emission by installing an end‐spiro group. Consequently, two emitters demonstrate similar photophysical properties and device performance at very low doping levels; while DCN‐SPTPA‐based OLEDs demonstrate a 1.3–1.4‐fold enhancement of the external quantum efficiencies (EQEs) with respect to the control molecule at 5–20 wt.% doping ratios, affording DR/NIR emission at 656, 688, 696, and 716 nm with record‐breaking EQEs of 36.1%, 29.3%, 28.2%, and 24.0%, respectively. Moreover, DCN‐SPTPA‐based nondoped NIR device also retains a state‐of‐the‐art EQE of 2.61% peaked at 800 nm. This work first demonstrates instructive guidance for accurately manipulating the intermolecular interactions of red TADF emitters, which will spur future developments in high‐performance DR/NIR OLEDs.

Neural network (NN) has been tentatively combined into multi-objective genetic algorithms (MOGAs) to solve the optimization problems in physics. However, the computationally complex physical evaluations and limited computing resources always cause the unsatisfied size of training set, which further results in the combined algorithms handling strict constraints ineffectively. Here, the dynamically used NN-based MOGA (DNMOGA) is proposed for the first time, which includes dynamically redistributing the number of evaluated individuals to different operators and some other improvements. Radio frequency cavity is designed by this algorithm as an example, in which four objectives and an equality constraint (a sort of strict constraint) are considered simultaneously. Comparing with the baseline algorithms, both the number and competitiveness of the final feasible individuals of DNMOGA are considerably improved. In general, DNMOGA is instructive for dealing with the complex situations of strict constraints and preference in multi-objective optimization problems in physics.

No abstract

No abstract

No abstract