The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a diverse underlying generative model, hence the latest works utilize diffusion models, which were shown to surpass GANs in terms of diversity. One major drawback of diffusion models, however, is their relatively slow inference time. In this paper, we present an accelerated solution to the task of local text-driven editing of generic images, where the desired edits are confined to a user-provided mask. Our solution leverages a recent text-to-image Latent Diffusion Model (LDM), which speeds up diffusion by operating in a lower-dimensional latent space. We first convert the LDM into a local image editor by incorporating Blended Diffusion into it. Next we propose an optimization-based solution for the inherent inability of this LDM to accurately reconstruct images. Finally, we address the scenario of performing local edits using thin masks. We evaluate our method against the available baselines both qualitatively and quantitatively and demonstrate that in addition to being faster, our method achieves better precision than the baselines while mitigating some of their artifacts.

Bryan Stern and Mark Geist discusses helping Americans out of a war zone after being left behind by the Biden admin. The U.S. has evacuated its first group of American citizens and permanent residents from Sudan since war broke out in the capital weeks ago. The land evacuation started Friday with efforts to bus a large group of Americans to the Red Sea via Port Sudan. Officials revealed Saturday that unmanned aircraft provided armed overwatch as a bus convoy carried 200 to 300 Americans over 500 miles. Smoke is seen in Khartoum, Sudan, Wednesday, April 19, 2023.

Turkish defence firm Baykar aims to begin production of its new unmanned combat aerial vehicle next year which is already attracting international interest, its chairman Selcuk Bayraktar said. Named "Kizilelma", the drone expands the company's product range from slow, ground attack drones to fast and agile autonomous ones that work alongside fighter jets. "It is designed to be a highly autonomous, under human purview of course, air-to-air combat vehicle," said Bayraktar, who led the design of the 15-metre-long (49 feet) jet-powered weapon. "In a sense, the Kizilelma expresses a whole new future for combat aviation." Baykar has come to prominence internationally in recent years because of the company's light drone TB-2, which has been used in Ukraine, Azerbaijan, and North Africa and has been a huge export success, catapulting the firm to becoming one of the largest Turkish defence exporters.

One afternoon not long ago, I sat entering notes into a patient's medical record. She was in her forties, and her labs showed anemia. The causes of anemia range from menstruation to cancer, and so pinpointing the correct underlying diagnosis is critical. Physicians are trained to formulate a full roster of possibilities, known as the differential diagnosis, and then to work down the list systematically. We're taught to cast a wide net--celiac disease, parasitic infections, thalassemia, lead poisoning, liver disease, B12 deficiency, myeloma, sickle-cell disease, G6PD deficiency--because you'll never make a diagnosis if you haven't included it in your differential.

The Home Office plans to use artificial intelligence to reduce the asylum backlog, and is launching a three-day hackathon in the search for quicker ways to process the 138,052 undecided asylum cases. The government is convening academics, tech experts, civil servants and business people to form 15 multidisciplinary teams tasked with brainstorming solutions to the backlog. Teams will be invited to compete to find the most innovative solutions, and will present their ideas to a panel of judges. The winners are expected to meet the prime minister, Rishi Sunak, in Downing Street for a prize-giving ceremony. Inspired by Silicon Valley's approach to problem-solving, the hackathon will take place in London and Peterborough in May.

The Coronavirus Disease 2019 (COVID-19) has had a profound impact on global health and economy, making it crucial to build accurate and interpretable data-driven predictive models for COVID-19 cases to improve public policy making. The extremely large scale of the pandemic and the intrinsically changing transmission characteristics pose a great challenge for effectively predicting COVID-19 cases. To address this challenge, we propose a novel hybrid model in which the interpretability of the Autoregressive model (AR) and the predictive power of the long short-term memory neural networks (LSTM) join forces. The proposed hybrid model is formalized as a neural network with an architecture that connects two composing model blocks, of which the relative contribution is decided data-adaptively in the training procedure. We demonstrate the favorable performance of the hybrid model over its two single composing models as well as other popular predictive models through comprehensive numerical studies on two data sources under multiple evaluation metrics. Specifically, in county-level data of 8 California counties, our hybrid model achieves 4.173% MAPE, outperforming the composing AR (5.629%) and LSTM (4.934%) alone on average. In country-level datasets, our hybrid model outperforms the widely-used predictive models such as AR, LSTM, Support Vector Machines, Gradient Boosting, and Random Forest, in predicting the COVID-19 cases in Japan, Canada, Brazil, Argentina, Singapore, Italy, and the United Kingdom. In addition to the predictive performance, we illustrate the interpretability of our proposed hybrid model using the estimated AR component, which is a key feature that is not shared by most black-box predictive models for COVID-19 cases. Our study provides a new and promising direction for building effective and interpretable data-driven models for COVID-19 cases, which could have significant implications for public health policy making and control of the current COVID-19 and potential future pandemics.

Medical studies frequently require to extract the relationship between each covariate and the outcome with statistical confidence measures. To do this, simple parametric models are frequently used (e.g. coefficients of linear regression) but usually fitted on the whole dataset. However, it is common that the covariates may not have a uniform effect over the whole population and thus a unified simple model can miss the heterogeneous signal. For example, a linear model may be able to explain a subset of the data but fail on the rest due to the nonlinearity and heterogeneity in the data. In this paper, we propose DDGroup (data-driven group discovery), a data-driven method to effectively identify subgroups in the data with a uniform linear relationship between the features and the label. DDGroup outputs an interpretable region in which the linear model is expected to hold. It is simple to implement and computationally tractable for use. We show theoretically that, given a large enough sample, DDGroup recovers a region where a single linear model with low variance is well-specified (if one exists), and experiments on real-world medical datasets confirm that it can discover regions where a local linear model has improved performance. Our experiments also show that DDGroup can uncover subgroups with qualitatively different relationships which are missed by simply applying parametric approaches to the whole dataset.

Never mind using AI to write stories -- Walmart is finding it helpful for landing a good bargain. The retailer tells Bloomberg that it's using a chatbot from Pactum AI to automatically negotiate some supplier deals. The technology is not only saving an average of three percent on contracts, but preferable to the vendors. Three out of four suppliers prefer haggling with the AI over a human, Walmart says. Pactum's system just asks Walmart to set its budget and requirements, such as discounts and payment terms.

If you're a millennial, chances are you remember AIM's SmarterChild, an "intelligent" chatbot that simulated human conversation. Nowadays, ChatGPT's AI-infused chatbot is all the rage, providing smarter and more eloquent answers to just about any question you may have. As someone who bothered the heck out of SmarterChild as a kid, I was nostalgic for a similar experience, so I gave ChatGPT a try. So, did ChatGPT win over this skeptical contrarian? It felt like I was having a conversation with an actual human being, which SmarterChild just simply couldn't emulate during its heyday.

AI strategist Lisa Palmer and privacy consultant Jodi Daniels discuss privacy concerns around the acquisition of biometric data. A significant expansion in Artificial intelligence (AI) facial recognition technology is increasingly being deployed to catch criminals, but experts express concern about the impact on personal privacy and data. According to the Allied Market Research data firm, the facial recognition industry, which was valued at $3.8 billion in 2020, will have grown to $16.7 billion by 2030. Lisa Palmer, an AI strategist, said it is important to understand that an individual's data largely feeds what happens from an AI perspective, especially within a generative framework. While there has been data recorded on citizens for decades, today's surveillance is different because of the quantity and quality of the data recorded as well as how it's being used, according to Palmer.