Jaemin Cho

Recently, DALL-E, a multimodal transformer language model, and its variants, including diffusion models, have shown high-quality text-to-image generation capabilities. However, despite the realistic image generation results, there has not been a detailed analysis of how to evaluate such models. In this work, we investigate the visual reasoning capabilities and social biases of different text-to-image models, covering both multimodal transformer language models and diffusion models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. For this, we propose PaintSkills, a compositional diagnostic evaluation dataset that measures these skills. Despite the high-fidelity image generation capability, a large gap exists between the performance of recent models and the upper bound accuracy in object counting and spatial relation understanding skills. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images across various professions and attributes. We demonstrate that recent text-to-image generation models learn specific biases about gender and skin tone from web image-text pairs. We hope our work will help guide future progress in improving text-to-image generation models on visual reasoning skills and learning socially unbiased representations. Code and data: https://github.com/j-min/DallEval

In order to realize both efficient and stable perovskite solar cells, designing electron transport layer (ETL) is of crucial importance to withstand constant light illumination and thermal stress while maintaining high charge extractability. Herein, commonly used SnO₂ nanoparticle‐based ETL for perovskite solar cells is modified by ionic‐salt ammonium chloride (NH₄Cl) and tin chloride dihydrate (SnCl₂∙2H₂O) as additives, which is easily fabricated by simple one‐step spin coating of single precursor solution. With the presence of these dual additives at the ETL, the crystallinity of the upper perovskite layer is clearly enhanced. Defect analyses on the devices suggest that these modifications can effectively passivate trap sites that reside within the ETL and at the perovskite interfaces with the carrier‐transport layers. As a result, the modified SnO₂ ETL results in an improvement of device stability under thermal or light stress condition, maintaining over 80% of its initial efficiency after ≈2000 h storage under elevated temperature (85 °C) and after ≈2400 h of operation under 1 sun illumination.

Because of the facile formation of defects in organometal halide perovskites, the defect passivation has become an important prerequisite for the stable and efficient perovskite solar cell (PSC). Regarding that ionic defects of the perovskites play a significant role on the performance and stability of PSCs, we introduce lithium fluorides as effective passivators based on their strong ionic characteristics and small ionic radii. Both Li⁺ and F^– are observed to successfully incorporate within the perovskite layer, improving the device performances with the best efficiency over 20%, while the hysteresis effects are significantly reduced, confirming the passivation of perovskite defects. Moreover, LiF restrains both thermal degradation and photodegradation of PSCs, where over 90% of the initial efficiencies have been retained by LiF-incorporated devices for more than 1000 h under either 1 sun illumination or 85 °C thermal condition. As the trap density of states is analyzed before and after the thermal stress, not only the mitigation of electronic traps as fabricated but also the dramatic relaxation of traps during the postannealing step is observed with the LiF incorporation. From this work, LiF has shown its potential as a promising ionic passivator, and the phenomenal achievement of device stability by LiF provides a clear insight to overcome the stability issues of PSCs, a key to the commercialization of next-generation photovoltaics.

High-mobility inorganic CuCrO₂ nanoparticles are co-utilized with conventional poly(bis(4-phenyl)(2,5,6-trimethylphenyl)amine) (PTAA) as a hole transport layer (HTL) for perovskite solar cells to improve device performance and long-term stability. Even though CuCrO₂ nanoparticles can be readily synthesized by hydrothermal reaction, it is difficult to form a uniform HTL with CuCrO₂ alone due to the severe agglomeration of nanoparticles. Herein, both CuCrO₂ nanoparticles and PTAA are sequentially deposited on perovskite by a simple spin-coating process, forming uniform HTL with excellent coverage. Due to the presence of high-mobility CuCrO₂ nanoparticles, CuCrO₂/PTAA HTL demonstrates better carrier extraction and transport. A reduction in trap density is also observed by trap-filled limited voltages and capacitance analyses. Incorporation of stable CuCrO₂ also contributes to the improved device stability under heat and light. Encapsulated perovskite solar cells with CuCrO₂/PTAA HTL retain their efficiency over 90% after ~900-h storage in 85 °C/85% relative humidity and under continuous 1-sun illumination at maximum-power point.

교육과정평가연구는 초·중등교육 분야의 전문 학술지로서 연 4회(2/5/8/11월) 발간되고 있는 한국연구재단(구 한국학술진흥재단의 '등재학술지'입니다. (등재년월:2005년 8월) 초․중등교육과 관련된 미발표 연구 논문으로 학술지를 발간하며, 세부 주제는 교육과정ㆍ교과서, 교수학습ㆍ교사교육, 교육평가로 나눌 수 있습니다. 모집 논문 주제에 적합한 논문을 대상으로 본원의 학술지 투고 논문 심사 기준에 따라 분야별 전문가 3인의 심사위원 심사결과를 토대로 학술지 편집위원회에서 최종 선정됩니다. 투고하는 논문은 학술지 「교육과정평가연구」 연구윤리 규정을 준수하여 작성하며, 편집위원회에서는 유사성 여부를 점검합니다.