Work for a Member company and need a Member Portal account? Register here with your company email address.
Creative Commons
Attribution-NonCommercial-ShareAlike 4.0 International
Dan Blondell, I2
Advancements in AI have revolutionized how machines perceive and interact with the world. However, almost all current progress has been lim…
Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are p…
Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, thes…
The Global Observatory monitors worldwide impact of AI adoption across cultures, tracking both positive and negative outcomes such as over-…
Workshop dates: September 17-18, 2025Deadline for application : August 1, 2025We aim to develop a series of benchmarks that provide r…
The Atlas of Human-AI Interaction maps comprehensive data on how humans engage with AI systems across various contexts to understand intera…
Self-supervised representation learning (SSL) powers modern AI systems and enables the learning of information rich data representations fr…
Animations designed with the help of a pre-engineered GPT are coded further by the AI to connect with a wearable sensor. The r…
filescape is a next-generation file explorer designed to reimagine the way you interact with your personal files.Files are arrayed as …
Virtual reality, augmented reality, and extended reality present value-creative opportunities for rethinking and reframing customer and use…
We imagine digital twins can be used in any number of ways to gain insights and enable interactions: imagine if you could engage with a tru…
By unifying proprietary data with third-party and contextual data sources, customer-centric leaders in financial services can create e…
If we want AI to engage with us naturally—in classrooms, therapy, eldercare, and beyond—it needs to understand us, with or without words.&n…
Secure and Personalized Music Video Generation using CHARCHAMusic is a deeply personal experience and our aim is to enhance this with…
OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior ChangeMarine ecosystems face unprecede…
Learning robust audio representations currently demands extensive datasets of real-world sound recordings. By applying artificial transfor…
Venture DJ is an AI-powered visual tool that transforms the way you explore your music library. By generating an interactive cloud of your …
Fact-O-Meter is an AI-powered conversational system designed to enhance critical discernment of visual misinformation. It encourages you to…
Dial It Down is an AI-powered video generation tool designed to lower the temperature of polarizing arguments. We let you distill the argum…
People use AI chatbots like ChatGPT in many ways—asking questions, sparking creativity, solving problems, and even for personal interaction…
People often find it difficult to turn their intentions into real actions—a challenge that affects both personal growth and mental wellbein…
In an era where loneliness has been declared an epidemic by the U.S. Surgeon General, older adults face particular vulnerability to social …
AI Agents are coming quickly. How can we build robust systems to make sure we know who AI agents act on behalf of, verify that they are pe…
AI interfaces have evolved, yet they remain largely confined to chat and voice. Gamification offers a new avenue for research and education…
Would you train for a tennis match in chaotic outdoor conditions from day one, or would you first perfect your fundamentals in a controlled…
"Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling," published by the Association for Computat…
Perspective-Aware AI (PAI) is a new approach to AI that goes beyond simply avoiding bias. It focuses on understanding, representing, and in…
Proteins are the workhorses of the cell, powering the biological processes that make life possible. Their precise choreographies catalyze r…
The application of generative AI in physical design presents a novel research area, as these technologies have primarily been utilized for …
In the contemporary media landscape dominated by discourse surrounding AI-generated content, this project inverts the paradigm by examining…
This project's vision is to unify sensors and signals from diverse domains, including physical, health, weather, and more, into a common la…
Education is inherently multimodal—we don’t just learn through words, but also through visuals, interactions, and hands-on experiences. Whi…
ConceptualTales uses generative AI to explain concepts through fiction-inspired analogies. Education, particularly in STEM and social …
This study explores the effects on your brain of using LLMs like ChatGPT in everyday tasks. Brain activity of 55 students aged 18-25 was re…
People inherently use experiences of their past while imagining their future, a capability that plays a crucial role in mental health. …
Crossroads is an interactive social game where players dig deep into each other's past experiences by collaboratively generating and r…
Children today are more digitally connected than ever before, with increasing exposure to tablets, social media, and smartphones. As techno…
The EMPATHICSTORIES++ dataset is collected from a month-long in-the-wild deployment of 41 participants (across 269 sessions with 53 hours o…
Background: Empathy is a driving force in our connection to others, our mental well-being, and resilience to challenges. With the rise of…
Empathy serves as a cornerstone in enabling prosocial behaviors, and can be evoked through sharing of personal experiences in stories.…
CityFlow is a versatile tool that allows users to design, evaluate, and visualize urban solutions through an llm-integrated, case-based sys…
Language models (LMs) are revolutionizing knowledge retrieval and processing in academia. However, concerns regarding their misuse and erro…
A new way to help people with neurodivergence to manage emotion regulation and understand their stress response.Participants describe their…
This paper introduces WatchThis, a novel wearable device that enables natural language interactions with real-world objects and environment…
In recent years, Generative AI technology has risen in popularity and has been promoted for its creative potential. However, applications o…
In "A HeARTfelt Robot", we designed a social robot interaction for children age 7-11 that helped them practice their social-emotional learn…
This project aimed at enhancing the social-emotional and educational experiences of Arabic-speaking refugee children. The project leverages…
NeuroChat is a neuroadaptive AI tutor that combines generative AI with real-time EEG data to create a personalized, dynamic learning experi…
Conversational AI Powered by Large Language Models Amplifies False Memories in Witness InterviewsThis study examines the impact of AI on hu…
We propose a computational approach to preserve traditional dance as living cultural heritage, exploring the use of technology to capture k…
Foundation models have become invaluable in advancing the medical field. Despite their promise, the strategic deployment of LLMs for effect…
The Machine Ghost in the Human Shell by Kawita Vatanajyankur and Pat Pataranutaporn is set to premier at the 11th Asia Pacific Tr…
PyTutor, is a collaborative initiative between MIT, Georgia State University (GSU), and Quinsigamond Community College (QCC) to leverage ge…
This research aims to address the timely and timeless challenge of human-computer interaction by focusing on designing and studying human-A…
During constituency listening processes (CLPs; e.g., town halls), leaders hear directly from community members about their needs and inter…
Little Language Models is a co-creative AI education microworld for children (ages 8–16) within our CoCo platform. It is especially de…
Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily…
AbstractDespite significant historical progress, discrimination and social stigma continue to impact the lives of LGBTQIA+ individuals. The…
This project seeks to explore and further develop the concept of "Symbiotic Virtuosity," where artificial intelligence (AI) and human music…
The research on Community-based Social Innovation focuses on the reshaping of urban spaces by human social behavior, incorporating an analy…
“Us” aims to help people develop their sense of empathy. It uses machine learning to analyze interlocutors’ signals (e.g., choice of words,…
We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Real…
Urban mobility is changing at an increasingly rapid pace. In this context, stakeholders such as governments and mobility operators ne…
Evolving Cultural Heritage through Collaborative Choreography with Generative Virtual CharactersThis project introduces an approach for tra…
Loneliness is a growing and global issue that affects approximately a third of individuals in industrialized countries. Given the…
As Artificial Intelligence (AI) interventions in education grow, there is an urgent need to co-design AI for education tools with educators…
KnitworkVR is an immersive virtual experience designed to simulate the Living Knitwork Pavilion showcased at Burning Man, through the use o…
Interested in learning more about the Commalla project? Fill out this form!
We are currently in an AI revolution. Big AI models are writing entire books, and generating art sold worth millions. Soon content made fro…
Ultrasound can be used to image soft tissues in vivo for early diagnosis and monitoring of disease progression. However, conventional ultra…
Analogia is a customizable conversation game that guides players to tell emotion-rich personal stories by combining story 'threads' wi…
We recently introduced Ophiuchus, a novel deep learning architecture for modeling protein structures. Ophiuchus is the first autoencod…
Be My Guest! is currently on display at the Vantaa Art Museum, Finland until December 3, 2023 as part of their "SYSTEMS" exhibition.At the …
Through an embodied, spatial audio experience, Collective Echos makes tangible a living library of human experiences.In the face of intensi…
People have to remember an ever-expanding volume of information. To help with this, we developed Memoro, a wearable and audio-based person…
Humanizing Agent-Based Models (h-ABM) emerges as a pioneering technique to simulate real-world behaviors, aiming to seamlessly bridge …
Door-to-door drone package deliveries are taking off across the US. In this work we expose and study a newly emerging privacy is…
Today's children will live in a world saturated with artificial intelligence. Understanding the key idea behind the functioning of intellig…
Fostering students' interests in learning is considered to have many positive downstream effects. Large language models have opened up new …
Empathy is a driving force in our connection to others, our mental well-being, and our resilience to challenges. The human capacity for emp…
Despite living in an increasingly connected world, loneliness and social isolation are prevalent issues today. While social robots have bee…
Dealing with rapidly spreading wildfires is a complex task that involves the coordination of multiple government agencies and on-site crews…
Deciding Across Scales emerges as a cutting-edge approach to decision-making, aiming to influence various sectors and societal levels…
Zero Robotics is an educational program that hosts tournaments to teach middle and high school students to write code and program with robo…
Urban populations around the world are rapidly growing. To improve livability, urban residents must reduce dependency on fossil fuels and p…
City Science researchers are developing a slew of tangible and digital platforms dedicated to solving spatial design and urban planning cha…
People die twice.First, when they die.Then when they are forgotten.Rokusuke Ei (1933-2016)
The COVID-19 pandemic, caused by the novel coronavirus SARS-CoV-2, has elicited a global health crisis of catastrophic proportions. With on…
A world in which thousands of people can construct and release autonomous biological agents is unlikely to flourishProfessor Kevin Esvelt, …
We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in var…
Current methods to assess depression and select appropriate treatments have many limitations and need improvement. Diagnosis is usually bas…
For details and recent updates visit: https://web.mit.edu/deblina-sarkar/Nanoelectronics has the potential to enable radical too…
FlowIO is the first fully-integrated and truly general-purpose, miniature pneumatics development platform for control, actuation, and sensi…
Liquid handling robots are key components of modern biotechnology labs, but they largely function to spare humans from laborious or re…
Voyage Viewer is an online, open source interactive tool especially designed to visualize and study human mobility and migration.
Smartglasses are increasingly popular because the face is an ideal location for continuously monitoring environmental and physiological sig…
A Framework For Designing Augmented Human-Flora Interaction.
Chameleon is a machine learning enhanced sensor system that uses CO2 and PIR sensors to classify room occupancy and use.
With the emergence of social robots in people’s daily lives, their interactions with people need to consider not only engaging with in…
We tackle the question of how to benchmark reconstruction of inputs from deep neural networks representations. This inverse problem is of g…
A revolutionary new piece of civic infrastructure for more inclusive public input.Real Talk for Change is a collaboration between MIT’s Cen…
Although lidar is widely used for mapping the 3D geometry of surfaces, the technology has historically been challenged by specular, or mirr…
Autonomous bicycles have recently been proposed as a new and more efficient approach to bicycle-sharing systems, but how do they compare fr…
The KALM project consists of a multimodal dataset and a wearable system for managing anxiety. With this set of tools we aim to make n…
During facilitated small-group conversations, facilitators have to manage many tasks, including handling the technology, managin…
Three-dimensional Digital Knitting of Intelligent Textile Sensor for Activity Recognition and Biomechanical MonitoringWe present an ap…
The underrepresentation of minoritized groups, particularly African Americans, is the longstanding reality of computing fields. Computing h…
We are building an intelligent musical partner that play duets with you and teaches music. This research teaches us how to design mor…
CommunityLM is a research program from MIT Center for Constructive Communication (CCC) and MIT Media Lab. We are devoted to developing soci…
We explore how AI-systems can effectively assist human reasoning processes by building and evaluating combined human+AI information process…
Could we substitute cars by shared autonomous lightweight vehicles for food delivery? We have developed an agent-based simulation model tha…
Community-scale profiling sensor node for ocean monitoring and community coordination of fishing activities.
A Conversation with the Sun is an artistic exploration by acclaimed Thai auteur and artist Apichatpong Weerasethakul in collaboration…
Mental Machine: Labour in the Self Economy, 2022, is a live performance by Kawita Vatanajyankur made in collaboration with Pat Patara…
This work is recently submitted as a Full Paper to ACM CHI 2023.Corsetto is a full stack system design and platform for upper-body haptics…
In an effort to design alternatives to opinion-based discourse at scale online that exploded with polarization, toxicity, and misinformatio…
@artbhot is a Twitter bot that leverages stable diffusion technology to translate user tweets into images and animations. Access…
Project Captivate have been designed to serve as an easy and reliable platform to measure physiology in the real world. We've desig…
How are our phones and email devices altering our ability to engage deeply in our daily tasks? How important is it to spend time deep…
The landscape in which society interacts with news has evolved due to the advent of the internet and modern communication platforms. Althou…
Advances in machine learning have recently enabled the synthesis of text, images, audio and video data, in what is referred to as Generativ…
Continuing the work of Liquid Movies, we introduce Liquid Learning, an extension for not simply recommending videos but encouraging people …
Say hello to FutureYou!Imagine stepping into a time machine and having a conversation with your future self. What would you ask? What unex…
We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam vid…
X-AR is an augmented reality (AR) system that gives humans "X-Ray Vision" X-AR is a new AR headset that enables users to see things th…
The "dream" has historically been conceived in the West as internal, entirely private, impossibly personal. This is at odds with much of th…
ACM CHI 2025 · Research PublicationApril 2025In a randomized controlled trial study, “Deceptive Explanations by Large Language Models …
Ceramics are ubiquitous, found in household items like toilets and planters, as well as in electronic components such as capacitors and hig…
This work was presented at the ACM CHI 2023 conference. By Joanne Leong, Florian Perteneder, Muhender Raj Rajvee, and…
My name is Raechel Walker. I'm a PhD student in the Personal Robots group. Here is a short description of my Data Activism Program:The Data…
Our Oceans IoT technologies enable new applications in climate and ecological monitoring, aquaculture, energy, and robotic navigation. …
The Atlas of Opportunity is a platform that allows communities to derive insights from their own data. The tool was created in collabo…
Point clouds are an increasingly ubiquitous input modality and the raw signal can be efficiently processed with recent progress in deep lea…
Image-based virtual try-on involves synthesizing perceptually convincing images of a model wearing a particular garment and has garnered si…
By predicting sparse shadow cues, our physics-inspired machine learning algorithm can reconstruct the underlying 3D scene. Abstract. W…
Spoken language is an information-rich medium that combines words with various paralinguistic information such as emotion and prosody. In d…
2D Spintronic and Neuromorphic Devices for Sustainable Artificial Intelligence
The City Science group uses simulations and visualizations to explain to stakeholders, including citizens, the various "what if" scenarios …
Dreaming through Code Designing creative learning workshops for local organizations committed to introducing technology to kids in a n…
FuseBot is a robotic system that can efficiently find and retrieve both RFID tagged and untagged target objects in line-of-sight, non-line-…
The close relationship between touch, gesture, and sound plays a critical role in expressive musical performance. Many acoustic instruments…
Existing upper extremity prosthesis controllers have limited functionality and place high cognitive demands on users, both of which contrib…
Teddy is a cutting edge data collection platform available for both Android and iOS that lets you collect data from study participants in a…
Critical thinking is an essential human skill. Despite the importance of critical thinking, research reveals that our reasoning ability suf…
In January 2023, a team led by MIT PhD Candidate and MIT CCC Research Assistant Belén Saldías hosted several workshops on Human-Center…
While some Human-Computer Integration (HInt) systems have successfully demonstrated that humans and technology can be physically and functi…
With the expansion of intelligent and ubiquitous computers everywhere, we have in many ways become cognitive cyborgs: most of us are insepa…
The most meaningful connections between people are often formed through expression of shared vulnerability and emotional experiences. Despi…
When people listen to stories, the words are colored with emotions conveyed through prosodic features beyond the text alone. Visual font d…
Resonance at low frequencies strongly influences a room's perception of sound, which can enhance or deteriorate the acoustic experience. Pr…
Machine learning in acoustics is an emerging field with great potential yet to be explored. Previous research includes predicting acoustic …
An essential element of K-12 AI literacy is educating learners about the ethical and societal implications of AI systems. Previous work in …
Recognizing and interpreting group behaviors is much more challenging than that of individual behaviors. Firstly, the system must perform w…
Our work aims to advance the socially intelligent behavior of social embodied artificial intelligence (AI) agents in real-world social inte…
Emotional wellbeing is an important indicator of overall health and poor emotional wellbeing can equally adversely affect one's overal…
Fostering students’ interest in learning has many positive downstream effects. It can make students more persistent and impact student…
Generating customized, memorable visuals and stories to support memory. Mnemonics are strategies used to remember information better (…
Immersive Scope is an immersive environment designed to help people visualize complex urban designs in a more engaging and accessible …
In a Proof-of-Work blockchain such as Bitcoin mining hashrate is increasing in the block reward. An increase in hashrate reduces network vu…
Latent Lab - Navigating Innovation: Interactive Data Exploration & InspirationLatent Lab is an AI-driven, graphical knowledge expl…
The Generative Land Use project aims to revolutionize urban planning by developing a cutting-edge algorithm that generates the ideal land u…
Computer-mediated forms of communication (i.e., social media, texting) have quickly become the predominant way that we keep in touch w…
We seek to empower everyone to become conscientious consumers, ethical engineers, creative problem solvers, and informed advocates for resp…
How can we make embodied agents have multimodal conversation with individual and group users that is not only natural, but also relational,…
An embodied virtual agent is a promising oracle for delivering appropriate just-in time interventions. We aim to build a system and design …
We create and employ ethical design frameworks to work towards equitable and inclusive HRI research and technologies.
Swarms of robots will revolutionize many applications, from targeted material delivery to farming. However, the characteristics that make t…
We are building autonomous agents that are socially and emotionally saturated in single-person (child-robot) or multi-party (child-parent-r…
The Ddog project features a Spot robot from Boston Dynamics and a Brain-Computer Interface (BCI) system powered by AttentivU, a pair of wi…
Press: - MIT News: Using reflections to see the world from new points of view- TechXplore, EuropaPress, La Nacion …
Tod Machover’s first opera (he has now composed many more groundbreaking ones) was VALIS, and it made history when it premiered for the 10t…
We take as a starting point for our work the recent scholarship by Sasha Costanza-Chock, Design Justice, in which she described design jus…
Social robots equipped with AI and designed with users’ social, emotional, and relational interactions in mind are increasingly being highl…
Artificial intelligence (AI) agents in an embodied form, such as Jibo, Amazon Alexa, and Google Home, are increasingly becoming part of our…
In a series of design workshops, the HRI Equitable Design framework from previous work (see Ostrowski et al. 2022) was expanded to a worksh…
A massive audit of 1800+ AI text datasets, tracing their provenance and composition from origin to creation.The race to train language mode…
AbstractAs conversational agents powered by large language models become more human-like, users are starting to view them as companions rat…
Ultrasound is widely used for tissue imaging such as breast cancer diagnosis; however, fundamental challenges limit…
A modular, membrane protein design based biomimetic sensing system named RESENSA (Receptor S-layer Electrical Nano Sens…
CircuitScout is a DIY probe system designed to simplify the process of testing PCBs, by automatically probing desired signals. Through an i…
Understanding the link between urban planning and commuting flows is crucial for guiding urban development and policymaking. This research,…