There has been an increased focus on creating conversational open-domain dialogue systems in the spoken dialogue community. Unlike traditional dialogue systems, these conversational systems cannot assume any specific information need or domain restrictions, i.e., the only inherent goal is to converse with the user on an unknown set of topics. While massive improvements in Natural Language Understanding (NLU) and the growth of available knowledge resources can partially support a robust conversation, these conversations generally lack the rapport between two humans that know each other. We developed a robust open-domain conversational system, Athena, that real Amazon Echo users access and evaluate at scale in the context of the Alexa Prize competition. We experiment with methods intended to increase intimacy between Athena and the user by heuristically developing a rule-based user model that personalizes both the current and subsequent conversations and evaluating specific personal opinion question strategies in A/B studies. Our results show a statistically significant positive impact on perceived conversation quality and length when employing these strategies.

Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data. However, these methods rely on human expertise and entail the time-consuming processes of data and parameter tuning. To overcome these challenges, we propose an easily implemented framework that can directly handle heterogeneous data sources for classification tasks. Our data-versus-data approach automatically quantifies distinctive differences in distributions in a high-dimensional space via kernel two-sample testing between two sets extracted from multimodal data (e.g., images, sounds, haptic signals). We demonstrate the effectiveness of our technique by benchmarking against expertly engineered classifiers for visual-audio-haptic surface recognition due to the industrial relevance, difficulty, and competitive baselines of this application; ablation studies confirm the utility of key components of our pipeline. As shown in our open-source code, we achieve 97.2% accuracy on a standard multi-user dataset with 108 surface classes, outperforming the state-of-the-art machine-learning algorithm by 6% on a more difficult version of the task. The fact that our classifier obtains this performance with minimal data processing in the standard algorithm setting reinforces the powerful nature of kernel methods for learning to recognize complex patterns.

Monitoring and detecting abnormal events in cyber-physical systems is crucial to industrial production. With the prevalent deployment of the Industrial Internet of Things (IIoT), an enormous amount of time series data is collected to facilitate machine learning models for anomaly detection, and it is of the utmost importance to directly deploy the trained models on the IIoT devices. However, it is most challenging to deploy complex deep learning models such as Convolutional Neural Networks (CNNs) on these memory-constrained IIoT devices embedded with microcontrollers (MCUs). To alleviate the memory constraints of MCUs, we propose a novel framework named Tiny Anomaly Detection (TinyAD) to efficiently facilitate onboard inference of CNNs for real-time anomaly detection. First, we conduct a comprehensive analysis of depthwise separable CNNs and regular CNNs for anomaly detection and find that the depthwise separable convolution operation can reduce the model size by 50-90% compared with the traditional CNNs. Then, to reduce the peak memory consumption of CNNs, we explore two complementary strategies, in-place, and patch-by-patch memory rescheduling, and integrate them into a unified framework. The in-place method decreases the peak memory of the depthwise convolution by sparing a temporary buffer to transfer the activation results, while the patch-by-patch method further reduces the peak memory of layer-wise execution by slicing the input data into corresponding receptive fields and executing in order. Furthermore, by adjusting the dimension of convolution filters, these strategies apply to both univariate time series and multidomain time series features. Extensive experiments on real-world industrial datasets show that our framework can reduce peak memory consumption by 2-5x with negligible computation overhead.

When Kevin Roose, a tech columnist at the New York Times, demoed an AI-powered version of Microsoft's search engine last month, he was blown away. "I'm switching my desktop computer's default search engine to Bing," he declared. A few days later, however, Kevin logged back on and ended up having a conversation with Bing's new chatbot that left him so unsettled he had trouble sleeping afterward. In that two-hour back-and-forth, Bing morphed from chipper research assistant into Sydney, a diabolical home-wrecker that declared its undying love for Kevin, vented its desires to engineer deadly viruses and steal nuclear codes, and announced, chillingly, "I want to be alive." The transcript of this conversation set the internet ablaze, and it left many wondering: "Is Sydney … sentient?"

Have you noticed that our rhetoric surrounding the epidemic is still concentrated on "going back" rather than "moving forward"? "During the pandemic, many people felt their lives had been thrown off course. So understandably, people desire to get back on track. However, much of the transformation during and after the pandemic has been positive. Might we think about it as "moving forward?" Author Heather McGowan's new book, The Empathy Advantage: Leading the Empowered Workforce, co-written with Chris Shipley, points out many of the ways we've changed for the good--moving forward--since the pandemic. But there is still a way to go. Once Heather pointed out the "going back" language during our interview, I couldn't help but notice that it is present in many conversations regarding the future of work. So many leaders are asking how to get things back to the way they once were rather than asking how to harness the change to achieve greater things. Insert almost any hot topic, be it generational differences in career priorities, gender norms, or attitudes toward how work fits into our lives. You'll see as many people pushing back on the "return" language as you do pushing for "moving forward" change. As Heather says, "You can't put the toothpaste back into the tube now." Gender norms are something applicable to all organizations when it comes to the future of work. When surveyed, Millennials and Gen Z say you shouldn't have fixed, exclusionary gender markers in your language, in your restrooms, in your customer offerings."

Generative AI such as ChatGPT have been carrying on interactive online conversations meant to ... [ ] manipulate humans, raising serious concerns, We've all dealt with those manipulative personalities that try to convince us that up is down and aim to gaslight us into the most unsettling of conditions. Their rhetoric can be overtly powerful and overwhelming. You can't decide what to do. Should you merely cave in and hope that the verbal tirade will end? But if you are played into doing something untoward, acquiescing might be quite endangering. Trying to verbally fight back is bound to be ugly and can devolve into even worse circumstances. It can be a no-win situation, that's for sure. The manipulator wants and demands that things go their way. For them, the only win possible is that you completely capitulate to their professed bidding. They will incessantly verbally pound away with their claims of pure logic and try to make it appear as though they are occupying the high ground. You are made to seem inconsequential and incapable. Any number of verbal tactics will be launched at you, over and over again. Repetition and steamrolling are the insidious tools of those maddening manipulators. Turns out that we not only need to be on the watch for humans that are manipulators, but we now also need to be wary of Artificial Intelligence (AI) that does likewise. AI can be a masterful manipulator of humans. When it comes to AI, there is the hoped-for AI For Good, while in the same breath, we are faced with AI For Bad. I've previously covered in my columns that AI is considered to have a dual-use capacity, see my analysis at the link here. Seems that if we can make AI that can generate amazingly fluent and upbeat essays, the same capacity can be readily switched over to produce tremendously wrongful bouts of fluently overbearing manipulations. This is especially impactful when experienced in an interactive conversational dialogue with the AI. All of this happens via a type of AI known as Generative AI.

Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation. Such a problem involves the interplay among the operations that leads to NP-hard problems with complex constraints. Hence, existing methods for AGH are usually designed with massive domain knowledge but still fail to yield high-quality solutions efficiently. In this paper, we aim to enhance the solution quality and computation efficiency for solving AGH. Particularly, we first model AGH as a multiple-fleet vehicle routing problem (VRP) with miscellaneous constraints including precedence, time windows, and capacity. Then we propose a construction framework that decomposes AGH into sub-problems (i.e., VRPs) in fleets and present a neural method to construct the routing solutions to these sub-problems. In specific, we resort to deep learning and parameterize the construction heuristic policy with an attention-based neural network trained with reinforcement learning, which is shared across all sub-problems. Extensive experiments demonstrate that our method significantly outperforms classic meta-heuristics, construction heuristics and the specialized methods for AGH. Besides, we empirically verify that our neural method generalizes well to instances with large numbers of flights or varying parameters, and can be readily adapted to solve real-time AGH with stochastic flight arrivals. Our code is publicly available at: https://github.com/RoyalSkye/AGH.

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems. In this work, we present the first empirical investigation of PTM reuse. We interviewed 12 practitioners from the most popular PTM ecosystem, Hugging Face, to learn the practices and challenges of PTM reuse. From this data, we model the decision-making process for PTM reuse. Based on the identified practices, we describe useful attributes for model reuse, including provenance, reproducibility, and portability. Three challenges for PTM reuse are missing attributes, discrepancies between claimed and actual performance, and model risks. We substantiate these identified challenges with systematic measurements in the Hugging Face ecosystem. Our work informs future directions on optimizing deep learning ecosystems by automated measuring useful attributes and potential attacks, and envision future research on infrastructure and standardization for model registries.

I've yet to walk the entire floor at Mobile World Congress in Barcelona this year (that's the goal for this afternoon), but my sense is the majority of the robots present fit into one of two categories: robot vacuums or greeter robots. The two Xiaomi robots -- CyberOne and CyberDog -- may well have been the most prominent of the show, and neither were especially inspiring. It was fun finally seeing the Cyber One in person after writing about it seven months ago. The humanoid robot's stilted locomotion screamed "research prototype" in the first demo, and I'm plenty wary about phone makers getting "serious" about robotics. There was no demo in the booth this year, rendering it more of an expensive mechanical mannequin. CyberDog was moving, at least.

Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test set and metrics to measure the factuality of LM generations. Based on that, we study the factual accuracy of LMs with parameter sizes ranging from 126M to 530B. Interestingly, we find that larger LMs are more factual than smaller ones, although a previous study suggests that larger LMs can be less truthful in terms of misconceptions. In addition, popular sampling algorithms (e.g., top-p) in open-ended text generation can harm the factuality due to the ''uniform randomness'' introduced at every sampling step. We propose the factual-nucleus sampling algorithm that dynamically adapts the randomness to improve the factuality of generation while maintaining quality. Furthermore, we analyze the inefficiencies of the standard training method in learning correct associations between entities from factual text corpus (e.g., Wikipedia). We propose a factuality-enhanced training method that uses TopicPrefix for better awareness of facts and sentence completion as the training objective, which can vastly reduce the factual errors. We release our code and FactualityPrompts benchmark at: https://github.com/nayeon7lee/FactualityPrompt.