Last month, a new dating app called Volar launched in New York City, with the promise "We go on blind dates. So you don't have to." To sign up, you enter your name and phone number, then submit yourself to a brief interview with a chatbot matchmaker. When I made an account, Volar's bot asked what line of work I was in. "I'm a book critic," I replied.

Climate and weather prediction traditionally relies on complex numerical simulations of atmospheric physics. Deep learning approaches, such as transformers, have recently challenged the simulation paradigm with complex network forecasts. However, they often act as data-driven black-box models that neglect the underlying physics and lack uncertainty quantification. We address these limitations with ClimODE, a spatiotemporal continuous-time process that implements a key principle of advection from statistical mechanics, namely, weather changes due to a spatial movement of quantities over time. ClimODE models precise weather evolution with value-conserving dynamics, learning global weather transport as a neural flow, which also enables estimating the uncertainty in predictions. Our approach outperforms existing data-driven methods in global and regional forecasting with an order of magnitude smaller parameterization, establishing a new state of the art.

The proliferation of Large Language Models (LLMs) highlights the critical importance of conducting thorough evaluations to discern their comparative advantages, limitations, and optimal use cases. Particularly important is assessing their capacity to accurately retrieve information included in a given prompt. A model's ability to do this significantly influences how effectively it can utilize contextual details, thus impacting its practical efficacy and dependability in real-world applications. Our research analyzes the in-context recall performance of various LLMs using the needle-in-a-haystack method. In this approach, a factoid (the "needle") is embedded within a block of filler text (the "haystack"), which the model is asked to retrieve. We assess the recall performance of each model across various haystack lengths and with varying needle placements to identify performance patterns. This study demonstrates that an LLM's recall capability is not only contingent upon the prompt's content but also may be compromised by biases in its training data. Conversely, adjustments to model architecture, training strategy, or fine-tuning can improve performance. Our analysis provides insight into LLM behavior, offering direction for the development of more effective applications of LLMs.

Deep neural networks (DNNs) have been successfully applied to earth observation (EO) data and opened new research avenues. Despite the theoretical and practical advances of these techniques, DNNs are still considered black box tools and by default are designed to give point predictions. However, the majority of EO applications demand reliable uncertainty estimates that can support practitioners in critical decision making tasks. This work provides a theoretical and quantitative comparison of existing uncertainty quantification methods for DNNs applied to the task of wind speed estimation in satellite imagery of tropical cyclones. We provide a detailed evaluation of predictive uncertainty estimates from state-of-the-art uncertainty quantification (UQ) methods for DNNs. We find that predictive uncertainties can be utilized to further improve accuracy and analyze the predictive uncertainties of different methods across storm categories.

There is a limitation in the literature of data-driven analyses for the ex-post evaluation of community risk and resilience, particularly using features related to the performance of coupled human-infrastructure systems. To address this gap, in this study we created a machine learning-based method for the ex-post assessment of community risk and resilience and their interplay based on features related to the coupled human-infrastructure systems performance. Utilizing feature groups related to population protective actions, infrastructure/building performance features, and recovery features, we examined the risk and resilience performance of communities in the context of the 2017 Hurricane Harvey in Harris County, Texas. These features related to the coupled human-infrastructure systems performance were processed using the K-means clustering method to classify census block groups into four distinct clusters then, based on feature analysis, these clusters were labeled and designated into four quadrants of risk-resilience archetypes. Finally, we analyzed the disparities in risk-resilience status of spatial areas across different clusters as well as different income groups. The findings unveil the risk-resilience status of spatial areas shaped by their coupled human-infrastructure systems performance and their interactions. The results also inform about features that contribute to high resilience in high-risk areas. For example, the results indicate that in high-risk areas, evacuation rates contributed to a greater resilience, while in low-risk areas, preparedness contributed to greater resilience.

Given the destructive impacts of tropical cyclones, it is critical to have a reliable system for cyclone intensity detection. Various techniques are available for this purpose, each with differing levels of accuracy. In this paper, we introduce two ensemble-based models based on AlexNet architecture to estimate tropical cyclone intensity using visible satellite images. The first model, trained on the entire dataset, is called the global AlexNet model. The second model is a distributed version of AlexNet in which multiple AlexNets are trained separately on subsets of the training data categorized according to the Saffir-Simpson wind speed scale prescribed by the meterologists. We evaluated the performance of both models against a deep learning benchmark model called \textit{Deepti} using a publicly available cyclone image dataset. Results indicate that both the global model (with a root mean square error (RMSE) of 9.03 knots) and the distributed model (with a RMSE of 9.3 knots) outperform the benchmark model (with a RMSE of 13.62 knots). We provide a thorough discussion of our solution approach, including an explanantion of the AlexNet's performance using gradient class activation maps (grad-CAM). Our proposed solution strategy allows future experimentation with various deep learning models in both single and multi-channel settings.

We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded, even when those sentences contain correct ground-truth answers. Additionally, we examine the impacts of factors such as model size, decoding strategy, and instruction tuning on groundedness. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations. This study provides novel insights into the groundedness challenges in LFQA and underscores the necessity for more robust mechanisms in LLMs to mitigate the generation of ungrounded content.

Shin-Etsu Chemical said Tuesday that it will build a new semiconductor materials plant in the city of Isesaki, Gunma Prefecture, at a cost of some 83 billion. The plant, slated to be completed by 2026, will make photoresists, including extreme ultraviolet resists used for state-of-the-art chips for generative artificial intelligence systems, and other semiconductor-related materials. The investment includes the cost to buy a 150,000-square-meter site for the factory. It will be the Japanese company's first new domestic production base since its plant in the city of Kamisu, Ibaraki Prefecture, was built in 1970. The Isesaki plant will also carry out research and development in the future. Currently, the company makes photoresists and related products at its plants in the prefectures of Niigata and Fukui, both along the Sea of Japan, and in Taiwan.

The intricate nature of time series data analysis benefits greatly from the distinct advantages offered by time and frequency domain representations. While the time domain is superior in representing local dependencies, particularly in non-periodic series, the frequency domain excels in capturing global dependencies, making it ideal for series with evident periodic patterns. To capitalize on both of these strengths, we propose ATFNet, an innovative framework that combines a time domain module and a frequency domain module to concurrently capture local and global dependencies in time series data. Specifically, we introduce Dominant Harmonic Series Energy Weighting, a novel mechanism for dynamically adjusting the weights between the two modules based on the periodicity of the input time series. In the frequency domain module, we enhance the traditional Discrete Fourier Transform (DFT) with our Extended DFT, designed to address the challenge of discrete frequency misalignment. Additionally, our Complex-valued Spectrum Attention mechanism offers a novel approach to discern the intricate relationships between different frequency combinations. Extensive experiments across multiple real-world datasets demonstrate that our ATFNet framework outperforms current state-of-the-art methods in long-term time series forecasting.

Mark your calendars: Tesla CEO Elon Musk suggested this afternoon that his electric automaker is going all-in on autonomous vehicle tech--and that Tesla's robotaxi will be unveiled on August 8. The announcement, posted by Musk on X Friday afternoon, capped off a weird day of reports and counter-reports that sent Tesla's stock on a roller-coaster ride, slipping down 6 points on the day before recovering in after-hours trading. Earlier in the day, Reuters reported that Tesla had canceled long-gestating plans to develop an affordable electric vehicle for the masses. The "next generation" vehicle is widely thought to be key to the electric automaker's survival, especially as competition heats up in the EV space. Instead, the news agency reported, Tesla would focus on building a robotaxi, which would use much of the same hardware as the low-cost vehicle.