There is an urgent need to measure the impacts of COVID-19 among gay men and other men who have sex with men (MSM). We conducted a cross-sectional survey with a global sample of gay men and other MSM (n = 2732) from April 16, 2020 to May 4, 2020, through a social networking app. We characterized the economic, mental health, HIV prevention and HIV treatment impacts of COVID-19 and the COVID-19 response, and examined whether subgroups of our study population are disproportionately impacted by COVID-19. Many gay men and other MSM not only reported economic and mental health consequences, but also interruptions to HIV prevention and testing, and HIV care and treatment services. These consequences were significantly greater among people living with HIV, racial/ethnic minorities, immigrants, sex workers, and socioeconomically disadvantaged groups. These findings highlight the urgent need to mitigate the negative impacts of COVID-19 among gay men and other MSM. Keywords COVID-19 • Economic impact • Mental health • HIV • AIDS • Gay • Men who have sex with men Resumen Existe una necesidad urgente para medir los impactos de COVID-19 entre hombres gay y otros hombres que tienen sexo con hombres (HSH). Hemos conducido una encuesta multifuncional con una prueba mundial de hombres gay y otros HSH (n = 2732) desde el 16 de Abril hasta el 4 de Mayo del 2020, a través de una aplicación de red social. Nosotros caracterizamos los impactos económicos, de salud mental, prevención del VIH y tratamiento del VIH e impactos a COVID-19 y la respuesta de COVID-19, y examinamos si subgrupos de nuestra población de estudio fueron impactados desproporcionadamente por COVID-19. Muchos hombres no tan solo reportaron consecuencias económicas y de salud mental, sino también interrupciones de prevención y de pruebas de VIH, y cuidado del VIH y servicios de tratamiento. Encontramos consecuencias más significantes entre personas viviendo con VIH, grupos raciales/etnicos, migrantes, sexo servidores, y groupos socioeconomicamente disfavorecidos. Los resultados subrayan la necesidad crucial de mitigar los impactos multifacéticos de COVID-19 entre los hombres homosexuales y otros HSH, especialmente para aquellos con vulnerabilidades entrelazadas.

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a recurrent neural network grammar encoder with a novel atten-tional RNNG decoder and applying policy gradient reinforcement learning to induce unsupervised tree structures on both the source and target. When trained on character-level datasets with no explicit segmentation or parse annotation, the model learns a plausible segmentation and shallow parse, obtaining performance close to an attentional baseline.

Deep learning has made substantial breakthroughs in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final performance. However, the design of the neural architecture heavily relies on the researchers’ prior knowledge and experience. And due to the limitations of humans’ inherent knowledge, it is difficult for people to jump out of their original thinking paradigm and design an optimal model. Therefore, an intuitive idea would be to reduce human intervention as much as possible and let the algorithm automatically design the neural architecture. Neural Architecture Search ( NAS ) is just such a revolutionary algorithm, and the related research work is complicated and rich. Therefore, a comprehensive and systematic survey on the NAS is essential. Previously related surveys have begun to classify existing work mainly based on the key components of NAS: search space, search strategy, and evaluation strategy. While this classification method is more intuitive, it is difficult for readers to grasp the challenges and the landmark work involved. Therefore, in this survey, we provide a new perspective: beginning with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then providing solutions for subsequent related research work. In addition, we conduct a detailed and comprehensive analysis, comparison, and summary of these works. Finally, we provide some possible future research directions.

We present VideoCLIP, a contrastive approach to pre-train a unified model for zeroshot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-ofthe-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/ fairseq/tree/main/examples/MMPT.

There is an urgent need to measure the impacts of COVID-19 among gay men and other men who have sex with men (MSM). We conducted a cross-sectional survey with a global sample of gay men and other MSM (n= 2732) from April 16, 2020 to May 4, 2020, through a social networking app. We characterized the economic, mental health, HIV prevention and HIV treatment impacts of COVID-19 and the COVID-19 response, and examined whether subgroups of our study population are disproportionately impacted by COVID-19. Many men not only reported economic and mental health consequences, but also interruptions to HIV prevention and testing, and HIV care and treatment services. Consequences were significantly greater among people living with HIV, racial/ethnic minorities, immigrants, sex workers, and socio-economically disadvantaged groups. Findings underscore the crucial need to mitigate the multifaceted impacts of COVID-19 among gay men and other MSM, especially for those with intersecting vulnerabilities.