Projection-based reduced order models (PROMs) have shown promise in representing the behavior of multiscale systems using a small set of generalized (or latent) variables. Despite their success, PROMs can be susceptible to inaccuracies, even instabilities, due to the improper accounting of the interaction between the resolved and unresolved scales of the multiscale system (known as the closure problem). In the current work, we interpret closure as a multifidelity problem and use a multifidelity deep operator network (DeepONet) framework to address it. In addition, to enhance the stability and accuracy of the multifidelity-based closure, we employ the recently developed "in-the-loop" training approach from the literature on coupling physics and machine learning models. The resulting approach is tested on shock advection for the one-dimensional viscous Burgers equation and vortex merging using the two-dimensional Navier-Stokes equations. The numerical experiments show significant improvement of the predictive ability of the closure-corrected PROM over the un-corrected one both in the interpolative and the extrapolative regimes.

While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from causality toward RL. In particular, we divide existing CRL approaches into two categories according to whether their causality-based information is given in advance or not. We further analyze each category in terms of the formalization of different models, ranging from the Markov Decision Process (MDP), Partially Observed Markov Decision Process (POMDP), Multi-Arm Bandits (MAB), and Dynamic Treatment Regime (DTR). Moreover, we summarize the evaluation matrices and open sources while we discuss emerging applications, along with promising prospects for the future development of CRL.

Chain of thought prompting successfully improves the reasoning capabilities of large language models, achieving state of the art results on a range of datasets. However, these reasoning capabilities only appear to emerge in models with a size of over 100 billion parameters. In this paper, we explore the transfer of such reasoning capabilities to models with less than 100 billion parameters via knowledge distillation. Specifically, we finetune a student model on the chain of thought outputs generated by a larger teacher model. Our experiments show that the proposed method improves task performance across arithmetic, commonsense and symbolic reasoning datasets. For example, the accuracy of T5 XXL on GSM8K improves from 8.11% to 21.99% when finetuned on PaLM-540B generated chains of thought.

Large-scale data is an essential component of machine learning as demonstrated in recent advances in natural language processing and computer vision research. However, collecting large-scale robotic data is much more expensive and slower as each operator can control only a single robot at a time. To make this costly data collection process efficient and scalable, we propose Policy Assisted TeleOperation (PATO), a system which automates part of the demonstration collection process using a learned assistive policy. PATO autonomously executes repetitive behaviors in data collection and asks for human input only when it is uncertain about which subtask or behavior to execute. We conduct teleoperation user studies both with a real robot and a simulated robot fleet and demonstrate that our assisted teleoperation system reduces human operators' mental load while improving data collection efficiency. Further, it enables a single operator to control multiple robots in parallel, which is a first step towards scalable robotic data collection. For code and video results, see https://clvrai.com/pato

With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few examples. It has been a new trend to explore ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress and challenges of ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques, including training strategies, demonstration designing strategies, as well as related analysis. Finally, we discuss the challenges of ICL and provide potential directions for further research. We hope that our work can encourage more research on uncovering how ICL works and improving ICL.

As people become more aware of their food choices, food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. For example, food recommendation systems analyze recipe instructions to assess nutritional contents and provide recipe recommendations. The recent and remarkable successes of generative AI methods, such as auto-regressive large language models, can lead to robust methods for a more comprehensive understanding of recipes for healthy food recommendations beyond surface-level nutrition content assessments. In this study, we explore the use of generative AI methods to extend current food computation models, primarily involving the analysis of nutrition and ingredients, to also incorporate cooking actions (e.g., add salt, fry the meat, boil the vegetables, etc.). Cooking actions are notoriously hard to model using statistical learning methods due to irregular data patterns - significantly varying natural language descriptions for the same action (e.g., marinate the meat vs. marinate the meat and leave overnight) and infrequently occurring patterns (e.g., add salt occurs far more frequently than marinating the meat). The prototypical approach to handling irregular data patterns is to increase the volume of data that the model ingests by orders of magnitude. Unfortunately, in the cooking domain, these problems are further compounded with larger data volumes presenting a unique challenge that is not easily handled by simply scaling up. In this work, we propose novel aggregation-based generative AI methods, Cook-Gen, that reliably generate cooking actions from recipes, despite difficulties with irregular data patterns, while also outperforming Large Language Models and other strong baselines.

The integration of NLG tools in education has generated many questions (Rospigliosi, 2023) and a growing interest among researchers. For instance, Gero et al. (2022) found NLG tools could support science writing by inspiring writers with sentences about scientific concepts; and Guo et al. (2023) found students could interact with chatbots to better prepare for classroom debates. Particularly in the context of language learning (Haristiani, 2019) NLG tools might provide language learners with real-time feedback and support in various language tasks (Chen et al., 2021). Besides, researchers have found NLG tool-based activities can positively influence English as a foreign language (EFL) students' willingness to engage in English language (Tai & Chen, 2020; Lee et al., 2023). However, individual EFL students may perceive the affordances of using NLG tools differently and some may even perceive affordances as constraints (Jeon, 2022). For EFL students to effectively interact with NLG tools to complete language tasks, it appears students will not only need strategies but also the right NLG tools (Woo et al., 2023). Activity theory (AT; Engeström, 1987) provides a framework to analyze how language learners interact with NLG tools as a mediated activity system. The present qualitative study applies AT to explore the rules governing the use of NLG tools by EFL students to write short stories. By analyzing EFL students' written reflections for the rules they have developed to interact with NLG tools, the study can provide insights into human-AI collaboration in education, improving pedagogy and tool design.

This study explores the concept of creativity and artificial intelligence (AI) and their recent integration. While AI has traditionally been perceived as incapable of generating new ideas or creating art, the development of more sophisticated AI models and the proliferation of human-computer interaction tools have opened up new possibilities for AI in artistic creation. This study investigates the various applications of AI in a creative context, differentiating between the type of art, language, and algorithms used. It also considers the philosophical implications of AI and creativity, questioning whether consciousness can be researched in machines and AI's potential interests and decision-making capabilities. Overall, we aim to stimulate a reflection on AI's use and ethical implications in creative contexts.

The design of distributed autonomous systems often omits consideration of the underlying network dynamics. Recent works in multi-agent systems and swarm robotics alike have highlighted the impact that the interactions between agents have on the collective behaviours exhibited by the system. In this paper, we seek to highlight the role that the underlying interaction network plays in determining the performance of the collective behaviour of a system, comparing its impact with that of the physical network. We contextualise this by defining a collective learning problem in which agents must reach a consensus about their environment in the presence of noisy information. We show that the physical connectivity of the agents plays a less important role than when an interaction network of limited connectivity is imposed on the system to constrain agent communication. Constraining agent interactions in this way drastically improves the performance of the system in a collective learning context. Additionally, we provide further evidence for the idea that `less is more' when it comes to propagating information in distributed autonomous systems for the purpose of collective learning.

Lifelogs are descriptions of experiences that a person had during their life. Lifelogs are created by fusing data from the multitude of digital services, such as online photos, maps, shopping and content streaming services. Question answering over lifelogs can offer personal assistants a critical resource when they try to provide advice in context. However, obtaining answers to questions over lifelogs is beyond the current state of the art of question answering techniques for a variety of reasons, the most pronounced of which is that lifelogs combine free text with some degree of structure such as temporal and geographical information. We create and publicly release TimelineQA1, a benchmark for accelerating progress on querying lifelogs. TimelineQA generates lifelogs of imaginary people. The episodes in the lifelog range from major life episodes such as high school graduation to those that occur on a daily basis such as going for a run. We describe a set of experiments on TimelineQA with several state-of-the-art QA models. Our experiments reveal that for atomic queries, an extractive QA system significantly out-performs a state-of-the-art retrieval-augmented QA system. For multi-hop queries involving aggregates, we show that the best result is obtained with a state-of-the-art table QA technique, assuming the ground truth set of episodes for deriving the answer is available.