Current Spoken Dialogue Systems (SDSs) often serve as passive listeners that respond only after receiving user speech. To achieve human-like dialogue, we propose a novel future prediction architecture that allows an SDS to anticipate future affective reactions based on its current behaviors before the user speaks. In this work, we investigate two scenarios: speech and laughter. In speech, we propose to predict the user's future emotion based on its temporal relationship with the system's current emotion and its causal relationship with the system's current Dialogue Act (DA). In laughter, we propose to predict the occurrence and type of the user's laughter using the system's laughter behaviors in the current turn. Preliminary analysis of human-robot dialogue demonstrated synchronicity in the emotions and laughter displayed by the human and robot, as well as DA-emotion causality in their dialogue. This verifies that our architecture can contribute to the development of an anticipatory SDS.

Graph Neural Networks (GNNs) are de facto solutions to structural data learning. However, it is susceptible to low-quality and unreliable structure, which has been a norm rather than an exception in real-world graphs. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree. Particularly, we exploit the one-dimensional structural entropy to maximize embedded information content when auxiliary neighbourhood attributes are fused to enhance the original graph. A new scheme of constructing optimal encoding trees is proposed to minimize the uncertainty and noises in the graph whilst assuring proper community partition in hierarchical abstraction. We present a novel sample-based mechanism for restoring the graph structure via node structural entropy distribution. It increases the connectivity among nodes with larger uncertainty in lower-level communities. SE-GSL is compatible with various GNN models and enhances the robustness towards noisy and heterophily structures. Extensive experiments show significant improvements in the effectiveness and robustness of structure learning and node representation learning.

Objective: To develop machine learning models that can predict the number of COVID-19 cases per day given the last 14 days of environmental and mobility data. Approach: COVID-19 data from four counties around Toronto, Ontario, were used. Data were prepared into daily records containing the number of new COVID case counts, patient demographic data, outdoor weather variables, indoor environment factors, and human movement based on cell mobility and public health restrictions. This data was analyzed to determine the most important variables and their interactions. Predictive models were developed using CNN and LSTM deep neural network approaches. A 5-fold chronological cross-validation approach used these methods to develop predictive models using data from Mar 1 to Oct 14 2020, and test them on data covering Oct 15 to Dec 24 2020. Results: The best LSTM models forecasted tomorrow's daily COVID case counts with 90.7% accuracy, and the 7-day rolling average COVID case counts with 98.1% accuracy using independent test data. The best models to forecast the next 7 days of daily COVID case counts did so with 79.4% accuracy over all days. Models forecasting the 7-day rolling average case counts had a mean accuracy of 83.6% on the same test set. Conclusions: Our findings point to the importance of indoor humidity for the transmission of a virus such as COVID-19. During the coldest portions of the year, when humans spend greater amounts of time indoors or in vehicles, air quality drops within buildings, most significantly indoor relative humidity levels. Moderate to high indoor temperatures coupled with low IRH (below 20%) create conditions where viral transmission is more likely because water vapour ejected from an infected person's mouth can remain longer in the air because of evaporation and dry skin conditions, particularly in a recipient's airway, promotes transmission.

Abstract: Across various species and different scales, certain organisms use their appendages to grasp objects not through clamping but through wrapping. This pattern of movement is found in octopus tentacles, elephant trunks, and chameleon prehensile tails, demonstrating a great versatility to grasp a wide range of objects of various sizes and weights as well as dynamically manipulate them in the 3D space. We observed that the structures of these appendages follow a common pattern - a logarithmic spiral - which is especially challenging for existing robot designs to reproduce. This paper reports the design, fabrication, and operation of a class of cable-driven soft robots that morphologically replicate spiral-shaped wrapping. This amounts to substantially curling in length while actively controlling the curling direction as enabled by two principles: a) the parametric design based on the logarithmic spiral makes it possible to tightly pack to grasp objects that vary in size by more than two orders of magnitude and up to 260 times self-weight and b) asymmetric cable forces allow the swift control of the curling direction for conducting object manipulation. We demonstrate the ability to dynamically operate objects at a sub-second level by exploiting passive compliance. We believe that our study constitutes a step towards engineered systems that wrap to grasp and manipulate, and further sheds some insights into understanding the efficacy of biological spiral-shaped appendages. One-Sentence Summary: Design, fabrication, and operation of spiral soft robots at variable scales that can manipulate objects through wrapping. Main Text: INTRODUCTION Wrapping as a paradigm for grasping and manipulation (1), which are two key objectives in robotics (2, 3), is found in the prehensile tail of chameleons and seahorses with length scales as small as a few millimeters (4), as well as in the tentacles of octopuses and the trunks of elephants as large as a meter (Figure 1A) (5, 6).

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. For the two weeks that the Hackneys' baby girl lay in a Pittsburgh hospital bed weak from dehydration, her parents rarely left her side, sometimes sleeping on the fold-out sofa in the room. They stayed with their daughter around the clock when she was moved to a rehab center to regain her strength. Finally, the 8-month-old stopped batting away her bottles and started putting on weight again. "She was doing well and we started to ask when can she go home," Lauren Hackney said.

In January 2021, the artificial intelligence research laboratory OpenAI gave a limited release to a piece of software called Dall-E. The software allowed users to enter a simple description of an image they had in their mind and, after a brief pause, the software would produce an almost uncannily good interpretation of their suggestion, worthy of a jobbing illustrator or Adobe-proficient designer – but much faster, and for free. Typing in, for example, "a pig with wings flying over the moon, illustrated by Antoine de Saint-Exupéry" resulted, after a minute or two of processing, in something reminiscent of the patchy but recognisable watercolour brushes of the creator of The Little Prince. A year or so later, when the software got a wider release, the internet went wild. Social media was flooded with all sorts of bizarre and wondrous creations, an exuberant hodgepodge of fantasies and artistic styles. And a few months later it happened again, this time with language, and a product called ChatGPT, also produced by OpenAI. Ask ChatGPT to produce a summary of the Book of Job in the style of the poet Allen Ginsberg and it would come up with a reasonable attempt in a few seconds. Ask it to render Ginsberg's poem Howl in the form of a management consultant's slide deck presentation and it would do that too.

A study was conducted to prove AI software could be used to translate and generate illustrations without any human intervention. This was done with the purpose of showing and distributing it to the external customer, Pratham Books. The project aligns with the company's vision by leveraging the generalisation and scalability of Machine Learning algorithms, offering significant cost efficiency increases to a wide range of literary audiences in varied geographical locations. A comparative study methodology was utilised to determine the best performant method out of the 3 devised, Prompt Augmentation using Keywords, CLIP Embedding Mask, and Cross Attention Control with Editorial Prompts. A thorough evaluation process was completed using both quantitative and qualitative measures. Each method had its own strengths and weaknesses, but through the evaluation, method 1 was found to have the best yielding results. Promising future advancements may be made to further increase image quality by incorporating Large Language Models and personalised stylistic models. The presented approach can also be adapted to Video and 3D sculpture generation for novel illustrations in digital webbooks.

Although the curse of multilinguality significantly restricts the language abilities of multilingual models in monolingual settings, researchers now still have to rely on multilingual models to develop state-of-the-art systems in Vietnamese Machine Reading Comprehension. This difficulty in researching is because of the limited number of high-quality works in developing Vietnamese language models. In order to encourage more work in this research field, we present a comprehensive analysis of language weaknesses and strengths of current Vietnamese monolingual models using the downstream task of Machine Reading Comprehension. From the analysis results, we suggest new directions for developing Vietnamese language models. Besides this main contribution, we also successfully reveal the existence of artifacts in Vietnamese Machine Reading Comprehension benchmarks and suggest an urgent need for new high-quality benchmarks to track the progress of Vietnamese Machine Reading Comprehension. Moreover, we also introduced a minor but valuable modification to the process of annotating unanswerable questions for Machine Reading Comprehension from previous work. Our proposed modification helps improve the quality of unanswerable questions to a higher level of difficulty for Machine Reading Comprehension systems to solve.

We demonstrate formation flying for drone swarm services. A set of drones fly in four different swarm formations. A dataset is collected to study the effect of formation flying on energy consumption. We conduct a set of experiments to study the effect of wind on formation flying. We examine the forces the drones exert on each other when flying in a formation. We finally identify and classify the formations that conserve most energy under varying wind conditions. The collected dataset aims at providing researchers data to conduct further research in swarm-based drone service delivery. Demo: https://youtu.be/NnucUWhUwLs

Runtime-tunable context-dependent network compression would make mobile deep learning adaptable to often varying resource availability, input "difficulty", or user needs. The existing compression techniques significantly reduce the memory, processing, and energy tax of deep learning, yet, the resulting models tend to be permanently impaired, sacrificing the inference power for reduced resource usage. The existing tunable compression approaches, on the other hand, require expensive re-training, seldom provide mobile-ready implementations, and do not support arbitrary strategies for adapting the compression. In this paper we present Mobiprox, a framework enabling flexible-accuracy on-device deep learning. Mobiprox implements tunable approximations of tensor operations and enables runtime adaptation of individual network layers. A profiler and a tuner included with Mobiprox identify the most promising neural network approximation configurations leading to the desired inference quality with the minimal use of resources. Furthermore, we develop control strategies that depending on contextual factors, such as the input data difficulty, dynamically adjust the approximation level of a model. We implement Mobiprox in Android OS and through experiments in diverse mobile domains, including human activity recognition and spoken keyword detection, demonstrate that it can save up to 15% system-wide energy with a minimal impact on the inference accuracy.