At the intersection of technology and science, robotics involves complex engineering to create a robot that performs tasks in a controlled environment and replicates human behavior. Some popular applications of robots include working in a factory, fighting forest fires, serving as surgical assistants, being a companion to the elderly, and detecting landmines in war zones – to name a few. Robots may increase happiness and efficiency and make it easier to perform dangerous tasks. For example, consider a robot performing factory work. A robot does not require breaks and does not slow down at the end of a shift as it gets tired.

At a Labour party conference-adjacent event in September, The World Transformed, Jeremy Corbyn was pictured waving an arm in front of an arcade cabinet bearing the words Thatcher's Techbase. The game – a modified version of 1994's famous infernal shooter, Doom II – sees players hunting down a resurrected, cyborg version of the former prime minister in a labyrinthine fortress. The images kicked off a minor media storm. "Pictured: Jeremy Corbyn plays video game that lets players kill Margaret Thatcher," said The Telegraph; the photos were featured in the Daily Mail, the Express and the Times. They even appeared on Have I Got News for You. Jim Purvis, the game's creator – who took and later tweeted the photos – was somewhat surprised.

Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions. How are these decompositions created and used? Here, we propose and evaluate a normative framework for task decomposition based on the simple idea that people decompose tasks to reduce the overall cost of planning while maintaining task performance. Analyzing 11,117 distinct graph-structured planning tasks, we find that our framework justifies several existing heuristics for task decomposition and makes predictions that can be distinguished from two alternative normative accounts. We report a behavioral study of task decomposition ($N=806$) that uses 30 randomly sampled graphs, a larger and more diverse set than that of any previous behavioral study on this topic. We find that human responses are more consistent with our framework for task decomposition than alternative normative accounts and are most consistent with a heuristic -- betweenness centrality -- that is justified by our approach. Taken together, our results provide new theoretical insight into the computational principles underlying the intelligent structuring of goal-directed behavior.

Hyperspectral pixel intensities result from a mixing of reflectances from several materials. This paper develops a method of hyperspectral pixel unmixing that aims to recover the "pure" spectral signal of each material (hereafter referred to as endmembers) together with the mixing ratios (abundances) given the spectrum of a single pixel. The unmixing problem is particularly relevant in the case of low-resolution hyperspectral images captured in a remote sensing setting, where individual pixels can cover large regions of the scene. Under the assumptions that (1) a multivariate Normal distribution can represent the spectra of an endmember and (2) a Dirichlet distribution can encode abundances of different endmembers, we develop a Latent Dirichlet Variational Autoencoder for hyperspectral pixel unmixing. Our approach achieves state-of-the-art results on standard benchmarks and on synthetic data generated using United States Geological Survey spectral library.

Semantic code search is the task of retrieving a code snippet given a textual description of its functionality. Recent work has been focused on using similarity metrics between neural embeddings of text and code. However, current language models are known to struggle with longer, compositional text, and multi-step reasoning. To overcome this limitation, we propose supplementing the query sentence with a layout of its semantic structure. The semantic layout is used to break down the final reasoning decision into a series of lower-level decisions. We use a Neural Module Network architecture to implement this idea. We compare our model - NS3 (Neuro-Symbolic Semantic Search) - to a number of baselines, including state-of-the-art semantic code retrieval methods, and evaluate on two datasets - CodeSearchNet and Code Search and Question Answering. We demonstrate that our approach results in more precise code retrieval, and we study the effectiveness of our modular design when handling compositional queries.

Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines. As the number of connected devices keeps on growing, the Internet of Things (IoT) market needs to be trustworthy for the end-users. However, existing literature still lacks a systematic and comprehensive survey work on the use of XAI for IoT. To bridge this lacking, in this paper, we address the XAI frameworks with a focus on their characteristics and support for IoT. We illustrate the widely-used XAI services for IoT applications, such as security enhancement, Internet of Medical Things (IoMT), Industrial IoT (IIoT), and Internet of City Things (IoCT). We also suggest the implementation choice of XAI models over IoT systems in these applications with appropriate examples and summarize the key inferences for future works. Moreover, we present the cutting-edge development in edge XAI structures and the support of sixth-generation (6G) communication services for IoT applications, along with key inferences. In a nutshell, this paper constitutes the first holistic compilation on the development of XAI-based frameworks tailored for the demands of future IoT use cases.

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

Double-blind peer review mechanism has become the skeleton of academic research across multiple disciplines including computer science, yet several studies have questioned the quality of peer reviews and raised concerns on potential biases in the process. In this paper, we conduct a thorough and rigorous study on fairness disparities in peer review with the help of large language models (LMs). We collect, assemble, and maintain a comprehensive relational database for the International Conference on Learning Representations (ICLR) conference from 2017 to date by aggregating data from OpenReview, Google Scholar, arXiv, and CSRanking, and extracting high-level features using language models. We postulate and study fairness disparities on multiple protective attributes of interest, including author gender, geography, author, and institutional prestige. We observe that the level of disparity differs and textual features are essential in reducing biases in the predictive modeling. We distill several insights from our analysis on study the peer review process with the help of large LMs. Our database also provides avenues for studying new natural language processing (NLP) methods that facilitate the understanding of the peer review mechanism. We study a concrete example towards automatic machine review systems and provide baseline models for the review generation and scoring tasks such that the database can be used as a benchmark.

Arman Rahmim Departments of Radiology and Physics, University of British Columbia Tyler J. Bradshaw Department of Radiology, University of Wisconsin - Madison Irène Buvat Institut Curie, Université PSL, Inserm, Université Paris-Saclay, Orsay, France Joyita Dutta Department of Biomedical Engineering, University of Massachusetts Amherst Abhinav K. Jha Department of Biomedical Engineering and Mallinckrodt Institute of Radiology, Washington University in St. Louis Paul E. Kinahan Department of Radiology, University of Washington Quanzheng Li Department of Radiology, Massachusetts General Hospital and Harvard Medical School Chi Liu Department of Radiology and Biomedical Imaging, Yale University Melissa D. McCradden Department of Bioethics, The Hospital for Sick Children, Toronto Babak Saboury Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health Eliot Siegel Department of Radiology and Nuclear Medicine, University of Maryland Medical Center, USA John J. Sunderland Departments of Radiology and Physics, University of Iowa Richard L. Wahl Mallinckrodt Institute of Radiology, Washington University in St. Louis Abstract The SNMMI Artificial Intelligence (SNMMI-AI) Summit, organized by the SNMMI AI Task Force, took place in Bethesda, MD on March 21-22, 2022. It brought together various community members and stakeholders from academia, healthcare, industry, patient representatives, and government (NIH, FDA), and considered various key themes to envision and facilitate a bright future for routine, trustworthy use of AI in nuclear medicine. In what follows, essential issues, challenges, controversies and findings emphasized in the meeting are summarized. Introduction The SNMMI Artificial Intelligence (SNMMI-AI) Summit, organized by the SNMMI AI Task Force, took place in Bethesda, MD on March 21-22, 2022. As summarized in Figure 1, various community members and stakeholders from academia, healthcare, industry, patient representatives, and government (NIH, FDA) participated in the AI Summit; and the meeting included rich presentations, roundtable discussion and interactions on key themes to envision and facilitate a bright future for routine, trustworthy use of AI in nuclear medicine.

Due to labor shortage and rising labor cost for the apple industry, there is an urgent need for the development of robotic systems to efficiently and autonomously harvest apples. In this paper, we present a system overview and algorithm design of our recently developed robotic apple harvester prototype. Our robotic system is enabled by the close integration of several core modules, including visual perception, planning, and control. This paper covers the main methods and advancements in deep learning-based multi-view fruit detection and localization, unified picking and dropping planning, and dexterous manipulation control. Indoor and field experiments were conducted to evaluate the performance of the developed system, which achieved an average picking rate of 3.6 seconds per apple. This is a significant improvement over other reported apple harvesting robots with a picking rate in the range of 7-10 seconds per apple. The current prototype shows promising performance towards further development of efficient and automated apple harvesting technology. Finally, limitations of the current system and future work are discussed.