Search

Emotions, shaped by past experiences, significantly influence decision-making and goal pursuit. Traditional cognitive-behavioral techniques for personal development rely on mental imagery to envision ideal selves, but may be less effective for individuals who struggle with visualization. This paper introduces Emotional Self-Voice (ESV), a novel system combining emotionally expressive language models and voice cloning technologies to render customized responses in the user's own voice. We investigate the potential of ESV to nudge individuals towards their ideal selves in a study with 60 participants. Across all three conditions (ESV, text-only, and mental imagination), we observed an increase in resilience, confidence, motivation, and goal commitment, but the ESV condition was perceived as uniquely engaging and personalized. We discuss the implications of designing generated self-voice systems as a personalized behavioral intervention for different scenarios.

AI is increasingly used to enhance images and videos, both intentionally and unintentionally. As AI editing tools become more integrated into smartphones, users can modify or animate photos into realistic videos. This study examines the impact of AI-altered visuals on false memories--recollections of events that didn't occur or deviate from reality. In a pre-registered study, 200 participants were divided into four conditions of 50 each. Participants viewed original images, completed a filler task, then saw stimuli corresponding to their assigned condition: unedited images, AI-edited images, AI-generated videos, or AI-generated videos of AI-edited images. AI-edited visuals significantly increased false recollections, with AI-generated videos of AI-edited images having the strongest effect (2.05x compared to control). Confidence in false memories was also highest for this condition (1.19x compared to control). We discuss potential applications in HCI, such as therapeutic memory reframing, and challenges in ethical, legal, political, and societal domains., Comment: 22 pages, 11 figures, 2 tables

This paper introduces Text2Tradition, a system designed to bridge the epistemological gap between modern language processing and traditional dance knowledge by translating user-generated prompts into Thai classical dance sequences. Our approach focuses on six traditional choreographic elements from No. 60 in Mae Bot Yai, a revered Thai dance repertoire, which embodies culturally specific knowledge passed down through generations. In contrast, large language models (LLMs) represent a different form of knowledge--data-driven, statistically derived, and often Western-centric. This research explores the potential of AI-mediated systems to connect traditional and contemporary art forms, highlighting the epistemological tensions and opportunities in cross-cultural translation., Comment: 8 pages, 3 figures

This study investigates psychological factors influencing belief in AI predictions about personal behavior, comparing it to belief in astrology and personality-based predictions. Through an experiment with 238 participants, we examined how cognitive style, paranormal beliefs, AI attitudes, personality traits, and other factors affect perceived validity, reliability, usefulness, and personalization of predictions from different sources. Our findings reveal that belief in AI predictions is positively correlated with belief in predictions based on astrology and personality psychology. Notably, paranormal beliefs and positive AI attitudes significantly increased perceived validity, reliability, usefulness, and personalization of AI predictions. Conscientiousness was negatively correlated with belief in predictions across all sources, and interest in the prediction topic increased believability across predictions. Surprisingly, cognitive style did not significantly influence belief in predictions. These results highlight the "rational superstition" phenomenon in AI, where belief is driven more by mental heuristics and intuition than critical evaluation. We discuss implications for designing AI systems and communication strategies that foster appropriate trust and skepticism. This research contributes to our understanding of the psychology of human-AI interaction and offers insights for the design and deployment of AI systems.

This paper presents a comprehensive analysis of how AI-generated medical responses are perceived and evaluated by non-experts. A total of 300 participants gave evaluations for medical responses that were either written by a medical doctor on an online healthcare platform, or generated by a large language model and labeled by physicians as having high or low accuracy. Results showed that participants could not effectively distinguish between AI-generated and Doctors' responses and demonstrated a preference for AI-generated responses, rating High Accuracy AI-generated responses as significantly more valid, trustworthy, and complete/satisfactory. Low Accuracy AI-generated responses on average performed very similar to Doctors' responses, if not more. Participants not only found these low-accuracy AI-generated responses to be valid, trustworthy, and complete/satisfactory but also indicated a high tendency to follow the potentially harmful medical advice and incorrectly seek unnecessary medical attention as a result of the response provided. This problematic reaction was comparable if not more to the reaction they displayed towards doctors' responses. This increased trust placed on inaccurate or inappropriate AI-generated medical advice can lead to misdiagnosis and harmful consequences for individuals seeking help. Further, participants were more trusting of High Accuracy AI-generated responses when told they were given by a doctor and experts rated AI-generated responses significantly higher when the source of the response was unknown. Both experts and non-experts exhibited bias, finding AI-generated responses to be more thorough and accurate than Doctors' responses but still valuing the involvement of a Doctor in the delivery of their medical advice. Ensuring AI systems are implemented with medical professionals should be the future of using AI for the delivery of medical advice.

This study examines the impact of AI on human false memories -- recollections of events that did not occur or deviate from actual occurrences. It explores false memory induction through suggestive questioning in Human-AI interactions, simulating crime witness interviews. Four conditions were tested: control, survey-based, pre-scripted chatbot, and generative chatbot using a large language model (LLM). Participants (N=200) watched a crime video, then interacted with their assigned AI interviewer or survey, answering questions including five misleading ones. False memories were assessed immediately and after one week. Results show the generative chatbot condition significantly increased false memory formation, inducing over 3 times more immediate false memories than the control and 1.7 times more than the survey method. 36.4% of users' responses to the generative chatbot were misled through the interaction. After one week, the number of false memories induced by generative chatbots remained constant. However, confidence in these false memories remained higher than the control after one week. Moderating factors were explored: users who were less familiar with chatbots but more familiar with AI technology, and more interested in crime investigations, were more susceptible to false memories. These findings highlight the potential risks of using advanced AI in sensitive contexts, like police interviews, emphasizing the need for ethical considerations.

Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and erode trust in the truth. We examined the impact of deceptive AI generated explanations on individuals' beliefs in a pre-registered online experiment with 23,840 observations from 1,192 participants. We found that in addition to being more persuasive than accurate and honest explanations, AI-generated deceptive explanations can significantly amplify belief in false news headlines and undermine true ones as compared to AI systems that simply classify the headline incorrectly as being true/false. Moreover, our results show that personal factors such as cognitive reflection and trust in AI do not necessarily protect individuals from these effects caused by deceptive AI generated explanations. Instead, our results show that the logical validity of AI generated deceptive explanations, that is whether the explanation has a causal effect on the truthfulness of the AI's classification, plays a critical role in countering their persuasiveness - with logically invalid explanations being deemed less credible. This underscores the importance of teaching logical reasoning and critical thinking skills to identify logically invalid arguments, fostering greater resilience against advanced AI-driven misinformation.

We introduce Purrfect Pitch, a system consisting of a wearable haptic device and a custom-designed learning interface for musical ear training. We focus on the ability to identify musical intervals (sequences of two musical notes), which is a perceptually ambiguous task that usually requires strenuous rote training. With our system, the user would hear a sequence of two tones while simultaneously receiving two corresponding vibrotactile stimuli on the back. Providing haptic feedback along the back makes the auditory distance between the two tones more salient, and the back-worn design is comfortable and unobtrusive. During training, the user receives multi-sensory feedback from our system and inputs their guessed interval value on our web-based learning interface. They see a green (otherwise red) screen for a correct guess with the correct interval value. Our study with 18 participants shows that our system enables novice learners to identify intervals more accurately and consistently than those who only received audio feedback, even after the haptic feedback is removed. We also share further insights on how to design a multisensory learning system.

Adults who are minimally verbal with autism spectrum disorder (mvASD) have pronounced speech difficulties linked to impaired motor skills. Existing research and clinical assessments primarily use indirect methods such as standardized tests, video-based facial features, and handwriting tasks, which may not directly target speech-related motor skills. In this study, we measure activity from eight facial muscles associated with speech using surface electromyography (sEMG), during carefully designed tasks. The findings reveal a higher power in the sEMG signals and a significantly greater correlation between the sEMG channels in mvASD adults (N=12) compared to age and gender-matched neurotypical controls (N=14). This suggests stronger muscle activation and greater synchrony in the discharge patterns of motor units. Further, eigenvalues derived from correlation matrices indicate lower complexity in muscle coordination in mvASD, implying fewer degrees of freedom in motor control.

We present PhysioLLM, an interactive system that leverages large language models (LLMs) to provide personalized health understanding and exploration by integrating physiological data from wearables with contextual information. Unlike commercial health apps for wearables, our system offers a comprehensive statistical analysis component that discovers correlations and trends in user data, allowing users to ask questions in natural language and receive generated personalized insights, and guides them to develop actionable goals. As a case study, we focus on improving sleep quality, given its measurability through physiological data and its importance to general well-being. Through a user study with 24 Fitbit watch users, we demonstrate that PhysioLLM outperforms both the Fitbit App alone and a generic LLM chatbot in facilitating a deeper, personalized understanding of health data and supporting actionable steps toward personal health goals.

We introduce "Future You," an interactive, brief, single-session, digital chat intervention designed to improve future self-continuity--the degree of connection an individual feels with a temporally distant future self--a characteristic that is positively related to mental health and wellbeing. Our system allows users to chat with a relatable yet AI-powered virtual version of their future selves that is tuned to their future goals and personal qualities. To make the conversation realistic, the system generates a "synthetic memory"--a unique backstory for each user--that creates a throughline between the user's present age (between 18-30) and their life at age 60. The "Future You" character also adopts the persona of an age-progressed image of the user's present self. After a brief interaction with the "Future You" character, users reported decreased anxiety, and increased future self-continuity. This is the first study successfully demonstrating the use of personalized AI-generated characters to improve users' future self-continuity and wellbeing.

Programming a robotic is a complex task, as it demands the user to have a good command of specific programming languages and awareness of the robot's physical constraints. We propose a framework that simplifies robot deployment by allowing direct communication using natural language. It uses large language models (LLM) for prompt processing, workspace understanding, and waypoint generation. It also employs Augmented Reality (AR) to provide visual feedback of the planned outcome. We showcase the effectiveness of our framework with a simple pick-and-place task, which we implement on a real robot. Moreover, we present an early concept of expressive robot behavior and skill generation that can be used to communicate with the user and learn new skills (e.g., object grasping)., Comment: Published in VLMNM 2024 - Workshop, ICRA 2024

People have to remember an ever-expanding volume of information. Wearables that use information capture and retrieval for memory augmentation can help but can be disruptive and cumbersome in real-world tasks, such as in social settings. To address this, we developed Memoro, a wearable audio-based memory assistant with a concise user interface. Memoro uses a large language model (LLM) to infer the user's memory needs in a conversational context, semantically search memories, and present minimal suggestions. The assistant has two interaction modes: Query Mode for voicing queries and Queryless Mode for on-demand predictive assistance, without explicit query. Our study of (N=20) participants engaged in a real-time conversation demonstrated that using Memoro reduced device interaction time and increased recall confidence while preserving conversational quality. We report quantitative results and discuss the preferences and experiences of users. This work contributes towards utilizing LLMs to design wearable memory augmentation systems that are minimally disruptive., Comment: 18 pages, 9 figures, project page at https://www.media.mit.edu/projects/memoro/overview

AI-based virtual assistants are increasingly used to support daily ideation tasks. The values or bias present in these agents can influence output in hidden ways. They may also affect how people perceive the ideas produced with these AI agents and lead to implications for the design of AI-based tools. We explored the effects of AI agents with different values on the ideation process and user perception of idea quality, ownership, agent competence, and values present in the output. Our study tasked 180 participants with brainstorming practical solutions to a set of problems with AI agents of different values. Results show no significant difference in self-evaluation of idea quality and perception of the agent based on value alignment; however, ideas generated reflected the AI's values and feeling of ownership is affected. This highlights an intricate interplay between AI values and human ideation, suggesting careful design considerations for future AI-supported brainstorming tools.

The ability to discern between true and false information is essential to making sound decisions. However, with the recent increase in AI-based disinformation campaigns, it has become critical to understand the influence of deceptive systems on human information processing. In experiment (N=128), we investigated how susceptible people are to deceptive AI systems by examining how their ability to discern true news from fake news varies when AI systems are perceived as either human fact-checkers or AI fact-checking systems, and when explanations provided by those fact-checkers are either deceptive or honest. We find that deceitful explanations significantly reduce accuracy, indicating that people are just as likely to believe deceptive AI explanations as honest AI explanations. Although before getting assistance from an AI-system, people have significantly higher weighted discernment accuracy on false headlines than true headlines, we found that with assistance from an AI system, discernment accuracy increased significantly when given honest explanations on both true headlines and false headlines, and decreased significantly when given deceitful explanations on true headlines and false headlines. Further, we did not observe any significant differences in discernment between explanations perceived as coming from a human fact checker compared to an AI-fact checker. Similarly, we found no significant differences in trust. These findings exemplify the dangers of deceptive AI systems and the need for finding novel ways to limit their influence human information processing.

Our surrounding environment impacts our cognitive-emotional processes on a daily basis and shapes our physical, psychological and social wellbeing. Although the effects of the built environment on our psycho-physiological processes are well studied, virtual environment design with a potentially similar impact on the user, has received limited attention. Based on the influence of space design on a user and combining that with the dynamic affordances of virtual spaces, we present the idea of adaptive virtual neuroarchitecture (AVN), where virtual environments respond to the user and the user's real world context while simultaneously influencing them both in realtime. To show how AVN has been explored in current research, we present a sampling of recent work that demonstrates reciprocal relationships using physical affordances (space, objects), the user's state (physiological, cognitive, emotional), and the virtual world used in the design of novel virtual reality experiences. We believe AVN has the potential to help us learn how to design spaces and environments that can enhance the wellbeing of their inhabitants.

Technology based screentime, the time an individual spends engaging with their computer or cell phone, has increased exponentially over the past decade, but perhaps most alarmingly amidst the COVID-19 pandemic. Although many software based interventions exist to reduce screentime, users report a variety of issues relating to the timing of the intervention, the strictness of the tool, and its ability to encourage organic, long-term habit formation. We develop guidelines for the design of behaviour intervention software by conducting a survey to investigate three research questions and further inform the mechanisms of computer-related behaviour change applications. RQ1: What do people want to change and why/how? RQ2: What applications do people use or have used, why do they work or not, and what additional support is desired? RQ3: What are helpful/unhelpful computer breaks and why? Our survey had 68 participants and three key findings. First, time management is a primary concern, but emotional and physical side-effects are equally important. Second, site blockers, self-trackers, and timers are commonly used, but they are ineffective as they are easy-to-ignore and not personalized. Third, away-from-computer breaks, especially involving physical activity, are helpful, whereas on-screen breaks are unhelpful, especially when they are long, because they are not refreshing. We recommend personalized and closed-loop computer-usage behaviour change support and especially encouraging off-the-computer screentime breaks., Comment: 11 pages, 9 figures, originally published in the proceedings of the Asian CHI Symposium 2021. Association for Computing Machinery, New York, NY, USA, 53 to 60

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth (~100 Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos ("talking-head videos") to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users (n = 242) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at https://github.com/tpulkit/txt2vid.git., Comment: 11 pages, 8 figures, 2 table. Addition of statistical analysis of results. Reorganization and rewriting of text to make it clearer

Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on large-scale uncurated datasets have shown successful transfer to diverse settings. We investigate using pretrained image representations and spatio-temporal attention for state representation learning in Atari. We also explore fine-tuning pretrained representations with self-supervised techniques, i.e., contrastive predictive coding, spatio-temporal contrastive learning, and augmentations. Our results show that pretrained representations are at par with state-of-the-art self-supervised methods trained on domain-specific data. Pretrained representations, thus, yield data and compute-efficient state representations. https://github.com/PAL-ML/PEARL_v1

Self-supervised or weakly supervised models trained on large-scale datasets have shown sample-efficient transfer to diverse datasets in few-shot settings. We consider how upstream pretrained models can be leveraged for downstream few-shot, multilabel, and continual learning tasks. Our model CLIPPER (CLIP PERsonalized) uses image representations from CLIP, a large-scale image representation learning model trained using weak natural language supervision. We developed a technique, called Multi-label Weight Imprinting (MWI), for multi-label, continual, and few-shot learning, and CLIPPER uses MWI with image representations from CLIP. We evaluated CLIPPER on 10 single-label and 5 multi-label datasets. Our model shows robust and competitive performance, and we set new benchmarks for few-shot, multi-label, and continual learning. Our lightweight technique is also compute-efficient and enables privacy-preserving applications as the data is not sent to the upstream model for fine-tuning.

Egocentric visual context detection can support intelligence augmentation applications. We created a wearable system, called PAL, for wearable, personalized, and privacy-preserving egocentric visual context detection. PAL has a wearable device with a camera, heart-rate sensor, on-device deep learning, and audio input/output. PAL also has a mobile/web application for personalized context labeling. We used on-device deep learning models for generic object and face detection, low-shot custom face and context recognition (e.g., activities like brushing teeth), and custom context clustering (e.g., indoor locations). The models had over 80\% accuracy in in-the-wild contexts (~1000 images) and we tested PAL for intelligence augmentation applications like behavior change. We have made PAL is open-source to further support intelligence augmentation using personalized and privacy-preserving egocentric visual contexts.

Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment. Sequential and parallel ensemble techniques have shown improved performance of ML systems in multi-modal settings by leveraging the feature sets together. We propose an uncertainty-aware boosting technique for multi-modal ensembling in order to focus on the data points with higher associated uncertainty estimates, rather than the ones with higher loss values. We evaluate this method on healthcare tasks related to Dementia and Parkinson's disease which involve real-world multi-modal speech and text data, wherein our method shows an improved performance. Additional analysis suggests that introducing uncertainty-awareness into the boosted ensembles decreases the overall entropy of the system, making it more robust to heteroscedasticity in the data, as well as better calibrating each of the modalities along with high quality prediction intervals. We open-source our entire codebase at https://github.com/usarawgi911/Uncertainty-aware-boosting, Comment: Accepted at IJCNN 2021, to appear in IEEE proceedings. Equal contributions from US, RK and WZ

The problem of missing data has been persistent for a long time and poses a major obstacle in machine learning and statistical data analysis. Past works in this field have tried using various data imputation techniques to fill in the missing data, or training neural networks (NNs) with the missing data. In this work, we propose a simple yet effective approach that clusters similar input features together using hierarchical clustering and then trains proportionately split neural networks with a joint loss. We evaluate this approach on a series of benchmark datasets and show promising improvements even with simple imputation techniques. We attribute this to learning through clusters of similar features in our model architecture. The source code is available at https://github.com/usarawgi911/Robustness-to-Missing-Features, Comment: To appear at AAAI 2021 Student Abstract

Reliability in Neural Networks (NNs) is crucial in safety-critical applications like healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of NNs in deployment. In this work, we propose an uncertainty-aware boosting technique for multi-modal ensembling to predict Alzheimer's Dementia Severity. The propagation of uncertainty across acoustic, cognitive, and linguistic features produces an ensemble system robust to heteroscedasticity in the data. Weighing the different modalities based on the uncertainty estimates, we experiment on the benchmark ADReSS dataset, a subject-independent and balanced dataset, to show that our method outperforms the state-of-the-art methods while also reducing the overall entropy of the system. This work aims to encourage fair and aware models. The source code is available at https://github.com/wazeerzulfikar/alzheimers-dementia, Comment: To appear at NeurIPS Machine Learning for Health (ML4H) 2020

Understanding and quantifying uncertainty in black box Neural Networks (NNs) is critical when deployed in real-world settings such as healthcare. Recent works using Bayesian and non-Bayesian methods have shown how a unified predictive uncertainty can be modelled for NNs. Decomposing this uncertainty to disentangle the granular sources of heteroscedasticity in data provides rich information about its underlying causes. We propose a conceptually simple non-Bayesian approach, deep split ensemble, to disentangle the predictive uncertainties using a multivariate Gaussian mixture model. The NNs are trained with clusters of input features, for uncertainty estimates per cluster. We evaluate our approach on a series of benchmark regression datasets, while also comparing with unified uncertainty methods. Extensive analyses using dataset shits and empirical rule highlight our inherently well-calibrated models. Our work further demonstrates its applicability in a multi-modal setting using a benchmark Alzheimer's dataset and also shows how deep split ensembles can highlight hidden modality-specific biases. The minimal changes required to NNs and the training procedure, and the high flexibility to group features into clusters makes it readily deployable and useful. The source code is available at https://github.com/wazeerzulfikar/deep-split-ensembles, Comment: 9 pages including references, + 10 pages appendix

Alzheimer's disease is estimated to affect around 50 million people worldwide and is rising rapidly, with a global economic burden of nearly a trillion dollars. This calls for scalable, cost-effective, and robust methods for detection of Alzheimer's dementia (AD). We present a novel architecture that leverages acoustic, cognitive, and linguistic features to form a multimodal ensemble system. It uses specialized artificial neural networks with temporal characteristics to detect AD and its severity, which is reflected through Mini-Mental State Exam (MMSE) scores. We first evaluate it on the ADReSS challenge dataset, which is a subject-independent and balanced dataset matched for age and gender to mitigate biases, and is available through DementiaBank. Our system achieves state-of-the-art test accuracy, precision, recall, and F1-score of 83.3% each for AD classification, and state-of-the-art test root mean squared error (RMSE) of 4.60 for MMSE score regression. To the best of our knowledge, the system further achieves state-of-the-art AD classification accuracy of 88.0% when evaluated on the full benchmark DementiaBank Pitt database. Our work highlights the applicability and transferability of spontaneous speech to produce a robust inductive transfer learning model, and demonstrates generalizability through a task-agnostic feature-space. The source code is available at https://github.com/wazeerzulfikar/alzheimers-dementia, Comment: To appear in INTERSPEECH 2020

Personalized Active Learner (PAL) is a wearable system for real-time, personalized, and context-aware health and cognition support. PAL's system consists of a wearable device, mobile app, cloud database, data visualization web app, and machine learning server. PAL's wearable device uses multi-modal sensors (camera, microphone, heart-rate) with on-device machine learning and open-ear audio output to provide real-time and context-aware cognitive, behavioral and psychological interventions. PAL also allows users to track the long-term correlations between their activities and physiological states to make well-informed lifestyle decisions. In this paper, we present and open-source PAL's system so that people can use it for health and cognition support applications. We also open-source three fully-developed example applications using PAL for face-based memory augmentation, contextual language learning, and heart-rate-based psychological support. PAL's flexible, modular and extensible platform combines trends in data-driven medicine, mobile psychology, and cognitive enhancement to support data-driven and empowering health and cognition applications.

We present the first real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG. We employ real-time adaptation of a single channel Electroencephalography (EEG) to infer from a Time-Distributed 1-D Deep Convolutional Neural Network. Polysomnography (PSG)-the gold standard for sleep staging, requires a human scorer and is both complex and resource-intensive. Our work demonstrates an end-to-end on-smartphone pipeline that can infer sleep stages in just single 30-second epochs, with an overall accuracy of 83.5% on 20-fold cross validation for five-class classification of sleep stages using the open Sleep-EDF dataset., Comment: Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216