Improving the predictive capability and computational cost of dynamical models is often at the heart of augmenting computational physics with machine learning (ML). However, most learning results are limited in interpretability and generalization over different computational grid resolutions, initial and boundary conditions, domain geometries, and physical or problem-specific parameters. In the present study, we simultaneously address all these challenges by developing the novel and versatile methodology of unified neural partial delay differential equations. We augment existing/low-fidelity dynamical models directly in their partial differential equation (PDE) forms with both Markovian and non-Markovian neural network (NN) closure parameterizations. The melding of the existing models with NNs in the continuous spatiotemporal space followed by numerical discretization automatically allows for the desired generalizability. The Markovian term is designed to enable extraction of its analytical form and thus provides interpretability. The non-Markovian terms allow accounting for inherently missing time delays needed to represent the real world. We obtain adjoint PDEs in the continuous form, thus enabling direct implementation across differentiable and non-differentiable computational physics codes, different ML frameworks, and treatment of nonuniformly-spaced spatiotemporal training data. We demonstrate the new generalized neural closure models (gnCMs) framework using four sets of experiments based on advecting nonlinear waves, shocks, and ocean acidification models. Our learned gnCMs discover missing physics, find leading numerical error terms, discriminate among candidate functional forms in an interpretable fashion, achieve generalization, and compensate for the lack of complexity in simpler models. Finally, we analyze the computational advantages of our new framework.

Open-Domain Question Answering (ODQA) aims at answering factoid questions without explicitly providing specific background documents. In a zero-shot setting, this task is more challenging since no data is available to train customized models like Retriever-Readers. Recently, Large Language Models (LLMs) like GPT-3 have shown their power in zero-shot ODQA with direct prompting methods, but these methods are still far from releasing the full powerfulness of LLMs only in an implicitly invoking way. In this paper, we propose a Self-Prompting framework to explicitly utilize the massive knowledge stored in the parameters of LLMs and their strong instruction understanding abilities. Concretely, we prompt LLMs step by step to generate multiple pseudo QA pairs with background passages and explanations from scratch and then use those generated elements for in-context learning. Experimental results show our method surpasses previous SOTA methods significantly on three widely-used ODQA datasets, and even achieves comparable performance with some Retriever-Reader models fine-tuned on full training data.

Google Bard, the search giant's ChatGPT rival, is already available in 180 countries and territories. But even though it's been widely available for months and was the centerpiece of Google's recent I/O event, it's missing one big region. The 450 million people living in the European Union are still unable to access Bard, or any of the company's other generative AI technologies. It's a move that has surprised lawmakers, and even Google won't say why it's holding back. Brando Benifei, the MEP leading the negotiations on Europe's new artificial intelligence rules, is not sure why the bloc had been excluded, describing the omission of the EU from Bard's rollout as a "big issue."

In this paper, we present ChatPLUG, a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format. Different from other open-domain dialogue models that focus on large-scale pre-training and scaling up model size or dialogue corpus, we aim to build a powerful and practical dialogue system for digital human with diverse skills and good multi-task generalization by internet-augmented instruction tuning. To this end, we first conduct large-scale pre-training on both common document corpus and dialogue data with curriculum learning, so as to inject various world knowledge and dialogue abilities into ChatPLUG. Then, we collect a wide range of dialogue tasks spanning diverse features of knowledge, personality, multi-turn memory, and empathy, on which we further instruction tune \modelname via unified natural language instruction templates. External knowledge from an internet search is also used during instruction finetuning for alleviating the problem of knowledge hallucinations. We show that \modelname outperforms state-of-the-art Chinese dialogue systems on both automatic and human evaluation, and demonstrates strong multi-task generalization on a variety of text understanding and generation tasks. In addition, we deploy \modelname to real-world applications such as Smart Speaker and Instant Message applications with fast inference. Our models and code will be made publicly available on ModelScope: https://modelscope.cn/models/damo/ChatPLUG-3.7B and Github: https://github.com/X-PLUG/ChatPLUG .

From Armageddon to the Day After Tomorrow, there have been plenty of Hollywood movies about how our world might end. But if there is to be a global apocalypse, what might be to blame for wiping out all life on Earth? A wandering black hole, giant asteroid impact and nuclear war could all trigger such disaster, as could the rise of killer robots or the reversal of our planet's magnetic field. Many of these might seem far-fetched but with the Doomsday Clock being placed at a record 90 seconds to midnight this year – and scientists warning that humanity's continued existence is at greater risk than ever before – the threat is now all to real. So how exactly would these devastating possibilities come about? End of days: Ff there is to be a global apocalypse, what might be to blame for wiping out all life on Earth?

The rapid proliferation of information in the digital era underscores the importance of accurate historical representation and interpretation. While artificial intelligence has shown promise in various fields, its potential for historical fact-checking and gap-filling remains largely untapped. This study evaluates the performance of three large language models LLMs GPT 3.5, GPT 4, and GoogleBARD in the context of predicting and verifying historical events based on given data. A novel metric, Distance to Reality (DTR), is introduced to assess the models' outputs against established historical facts. The results reveal a substantial potential for AI in historical studies, with GPT 4 demonstrating superior performance. This paper underscores the need for further research into AI's role in enriching our understanding of the past and bridging historical knowledge gaps.

In this study, we propose a new method for combining in situ buoy measurements with Earth system models (ESMs) to improve the accuracy of temperature predictions in the ocean. The technique utilizes the dynamics and modes identified in ESMs to improve the accuracy of buoy measurements while still preserving features such as seasonality. Using this technique, errors in localized temperature predictions made by the MPAS-O model can be corrected. We demonstrate that our approach improves accuracy compared to other interpolation and data assimilation methods. We apply our method to assimilate the Model for Prediction Across Scales Ocean component (MPAS-O) with the Global Drifter Program's in-situ ocean buoy dataset.

In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples. The possibility to parameterise an LLM through such in-context examples widens their capability at a much lower cost than finetuning. We extend this line of reasoning and present a method which further expands the capabilities of an LLM by embedding it within an algorithm or program. To demonstrate the benefits of this approach, we present an illustrative example of evidence-supported question-answering. We obtain a 6.4\% improvement over the chain of thought baseline through a more algorithmic approach without any finetuning. Furthermore, we highlight recent work from this perspective and discuss the advantages and disadvantages in comparison to the standard approaches.

An apparent drone attack on the Kremlin this week has sparked fears of an escalation in Russia's brutal war in Ukraine. On Wednesday night, two remotely-operated devices flew towards the domed roof of the Kremlin before being shot down by Russian air defences, exploding but harming no one. After the incident, Moscow Mayor Sergey Sobyanin declared that flying drones by private citizens was now banned in Moscow. Russia said the United States masterminded the attack, claiming Ukraine carried it out. Washington and Kyiv have denied responsibility, insisting that Ukraine's war efforts are purely defensive.

Air raid sirens sounded in Ukraine's Kyiv after residents were subjected to drone attacks, spasms of gunfire and explosions during the fourth attack on the capital in as many days, according to officials. Officials said at least one drone was downed after anti-aircraft units went into action during the raid on Thursday evening, which began just after 8pm (17:00 GMT) and lasted about 20 minutes. Kyiv Mayor Vitali Klitschko said there had been two impacts from downed drones. "During the last air alert, an unmanned aerial vehicle was spotted over Kyiv. The object was shot down by air defence forces," Kyiv city military administration head Serhiy Popko said on Telegram.