Model-based reinforcement learning agents utilizing transformers have shown improved sample efficiency due to their ability to model extended context, resulting in more accurate world models. However, for complex reasoning and planning tasks, these methods primarily rely on continuous representations. This complicates modeling of discrete properties of the real world such as disjoint object classes between which interpolation is not plausible. In this work, we introduce discrete abstract representations for transformer-based learning (DART), a sample-efficient method utilizing discrete representations for modeling both the world and learning behavior. We incorporate a transformer-decoder for auto-regressive world modeling and a transformer-encoder for learning behavior by attending to task-relevant cues in the discrete representation of the world model. For handling partial observability, we aggregate information from past time steps as memory tokens. DART outperforms previous state-of-the-art methods that do not use look-ahead search on the Atari 100k sample efficiency benchmark with a median human-normalized score of 0.790 and beats humans in 9 out of 26 games. We release our code at https://pranaval.github.io/DART/.

In recent decades, robotics research has expanded significantly, encompassing a wide array of applications spanning from industrial robotics [1, 2] to social robotics[3, 4, 5]. In this work, we focus on social robots, specifically designed for human interaction, which have gained increasing attention due to their potential roles in healthcare, elderly care, and various service industries [6, 7, 8] such as education, museum and finance. This surge in interest has led to extensive research endeavours aimed at enhancing the quality of human-robot interaction (HRI) by refining robot systems to mimic human-like behaviours [9, 10, 11], and exploring the impact of social attributes on HRI dynamics [12, 13, 14] and the influence of the physical appearance of social robots [15, 16, 17, 18]. Large Language Models (LLMs) represent a pivotal advancement in artificial intelligence, trained on vast corpora of textual data, possessing the ability to comprehend intricate linguistic nuances, infer contextual meanings, and generate coherent responses. Their versatility has rendered them indispensable across a spectrum of industries, from healthcare to finance to entertainment. Notably, the integrations of LLMs and robotics have emerged as a transformative trend, offering new avenues for enhancing robot capabilities??. This paper presents a novel robotics system deployed in the social robot Nadine, which comprises three key modules: perception, interaction, and robot control modules. The perception module takes the role of understanding multiple modalities encompassing the user's query and the environmental visual cues.

Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architecture for few-shot learning that consists of three components: a classifier, an auxiliary network, and a bridge network. While the classifier performs the main classification task, the auxiliary network learns to predict language representations from the same input, and the bridge network transforms high-level features of the auxiliary network into modulation parameters for layers of the few-shot classifier using conditional batch normalization. The bridge should encourage a form of lightweight semantic alignment between language and vision which could be useful for the classifier. However, after evaluating the proposed approach on two popular few-shot classification benchmarks we find that a) the improvements do not reproduce across benchmarks, and b) when they do, the improvements are due to the additional compute and parameters introduced by the bridge network. We contribute insights and recommendations for future work in multi-modal meta-learning, especially when using language representations.

Humans have an innate drive to seek out causality. Whether fuelled by curiosity or specific goals, we constantly question why things happen, how they are interconnected, and many other related phenomena. To develop AI agents capable of addressing this natural human quest for causality, we urgently need a comprehensive dataset of natural causal questions. Unfortunately, existing datasets either contain only artificially-crafted questions that do not reflect real AI usage scenarios or have limited coverage of questions from specific sources. To address this gap, we present CausalQuest, a dataset of 13,500 naturally occurring questions sourced from social networks, search engines, and AI assistants. We formalize the definition of causal questions and establish a taxonomy for finer-grained classification. Through a combined effort of human annotators and large language models (LLMs), we carefully label the dataset. We find that 42% of the questions humans ask are indeed causal, with the majority seeking to understand the causes behind given effects. Using this dataset, we train efficient classifiers (up to 2.85B parameters) for the binary task of identifying causal questions, achieving high performance with F1 scores of up to 0.877. We conclude with a rich set of future research directions that can build upon our data and models.

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that primarily affects the aging population by impairing cognitive and motor functions. Early detection of AD through accessible methodologies like magnetic resonance imaging (MRI) is vital for developing effective interventions to halt or slow the disease's progression. This study aims to perform a comprehensive analysis of machine learning techniques for selecting MRI-based biomarkers and classifying individuals into healthy controls (HC) and unstable controls (uHC) who later show mild cognitive impairment within five years. The research utilizes MRI data from the Alzheimer's Disease Neuroinformatics Initiative (ADNI) and the Open Access Series of Imaging Studies 3 (OASIS-3), focusing on both HC and uHC participants. The study addresses the challenges of imbalanced data by testing classification methods on balanced and unbalanced datasets, and harmonizes data using polynomial regression to mitigate nuisance variables like age, gender, and intracranial volume. Results indicate that Gaussian Naive Bayes and RusBoost classifiers shows an optimal performance, achieving accuracies of up to 76.46% and 72.48% respectively on the ADNI dataset. For the OASIS-3 dataset, Kernel Naive Bayes and RusBoost yield accuracies ranging from 64.66% to 75.71%, improving further in age-matched datasets. Brain regions like the entorhinal cortex, hippocampus, lateral ventricle, and lateral orbitofrontal cortex are identified as significantly impacted during early cognitive decline. Despite limitations such as small sample sizes, the study's harmonization approach enhances the robustness of biomarker selection, suggesting the potential of this semi-automatic machine learning pipeline for early AD detection using MRI.

This paper introduces the concept of augmented conversation, which aims to support co-located in-person conversations via embedded speech-driven on-the-fly referencing in augmented reality (AR). Today computing technologies like smartphones allow quick access to a variety of references during the conversation. However, these tools often create distractions, reducing eye contact and forcing users to focus their attention on phone screens and manually enter keywords to access relevant information. In contrast, AR-based on-the-fly referencing provides relevant visual references in real-time, based on keywords extracted automatically from the spoken conversation. By embedding these visual references in AR around the conversation partner, augmented conversation reduces distraction and friction, allowing users to maintain eye contact and supporting more natural social interactions. To demonstrate this concept, we developed \system, a Hololens-based interface that leverages real-time speech recognition, natural language processing and gaze-based interactions for on-the-fly embedded visual referencing. In this paper, we explore the design space of visual referencing for conversations, and describe our our implementation -- building on seven design guidelines identified through a user-centered design process. An initial user study confirms that our system decreases distraction and friction in conversations compared to smartphone searches, while providing highly useful and relevant information.

We introduce RealitySummary, a mixed reality reading assistant that can enhance any printed or digital document using on-demand text extraction, summarization, and augmentation. While augmented reading tools promise to enhance physical reading experiences with overlaid digital content, prior systems have typically required pre-processed documents, which limits their generalizability and real-world use cases. In this paper, we explore on-demand document augmentation by leveraging large language models. To understand generalizable techniques for diverse documents, we first conducted an exploratory design study which identified five categories of document enhancements (summarization, augmentation, navigation, comparison, and extraction). Based on this, we developed a proof-of-concept system that can automatically extract and summarize text using Google Cloud OCR and GPT-4, then embed information around documents using a Microsoft Hololens 2 and Apple Vision Pro. We demonstrate real-time examples of six specific document augmentations: 1) summaries, 2) comparison tables, 3) timelines, 4) keyword lists, 5) summary highlighting, and 6) information cards. Results from a usability study (N=12) and in-the-wild study (N=11) highlight the potential benefits of on-demand MR document enhancement and opportunities for future research.

We introduce Augmented Physics, a machine learning-powered tool designed for creating interactive physics simulations from static textbook diagrams. Leveraging computer vision techniques, such as Segment Anything and OpenCV, our web-based system enables users to semi-automatically extract diagrams from physics textbooks and then generate interactive simulations based on the extracted content. These interactive diagrams are seamlessly integrated into scanned textbook pages, facilitating interactive and personalized learning experiences across various physics concepts, including gravity, optics, circuits, and kinematics. Drawing on an elicitation study with seven physics instructors, we explore four key augmentation techniques: 1) augmented experiments, 2) animated diagrams, 3) bi-directional manipulatives, and 4) parameter visualization. We evaluate our system through technical evaluation, a usability study (N=12), and expert interviews (N=12). The study findings suggest that our system can facilitate more engaging and personalized learning experiences in physics education.

Voice activity detection (VAD) is the task of detecting speech in an audio stream, which is challenging due to numerous unseen noises and low signal-to-noise ratios in real environments. Recently, neural network-based VADs have alleviated the degradation of performance to some extent. However, the majority of existing studies have employed excessively large models and incorporated future context, while neglecting to evaluate the operational efficiency and latency of the models. In this paper, we propose a lightweight and real-time neural network called MagicNet, which utilizes casual and depth separable 1-D convolutions and GRU. Without relying on future features as input, our proposed model is compared with two state-of-the-art algorithms on synthesized in-domain and out-domain test datasets. The evaluation results demonstrate that MagicNet can achieve improved performance and robustness with fewer parameter costs.

Artificial neural networks are often used to identify features of crop plants. However, training their models requires many annotated images, which can be expensive and time-consuming to acquire. Procedural models of plants, such as those developed with Lindenmayer-systems (L-systems) can be created to produce visually realistic simulations, and hence images of plant simulations, where annotations are implicitly known. These synthetic images can either augment or completely replace real images in training neural networks for phenotyping tasks. In this paper, we systematically vary amounts of real and synthetic images used for training in both maize and canola to better understand situations where synthetic images generated from L-systems can help prediction on real images. This work also explores the degree to which realism in the synthetic images improves prediction. We have five different variants of a procedural canola model (these variants were created by tuning the realism while using calibration), and the deep learning results showed how drastically these results improve as the canola synthetic images are made to be more realistic. Furthermore, we see how neural network predictions can be used to help calibrate L-systems themselves, creating a feedback loop.