Category
2,089 papers
A longitudinal experiment in an undergraduate learning analytics course, in which 17 student teams collaborated with a persistent LLM-based teammate across weekly sessions, identified distinct patterns unfolding across three timescales.
Large language models (LLMs) are increasingly used for informal mental health support, yet the privacy implications of conversational interaction remain poorly understood. Prior LLM privacy research has focused largely on model-side risks such as memorization and adversarial extraction, leaving personal information inf...
Autonomous delivery robots increasingly share residential spaces with companion animals, yet navigation behavior is rarely designed with animal welfare in mind. This paper presents a pilot study evaluating a curve-out maneuver, a laterally arcing pass-by trajectory triggered at the dog's alert distance, proposed as a c...
Augmented reality (AR) can support vocabulary learning by placing mnemonic cues in the physical contexts where new words are encountered. Prior work has augmented real objects with bilingual labels, audio, keywords, and 3D visualisations of those keywords interacting with the objects, but these cues are typically prede...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and pr...
Patients often arrive at brief, time-constrained clinical visits unsure of what to expect or ask, and millions of adults now turn to general-purpose AI chatbots to prepare beforehand. Yet whether conversational AI improves visit readiness remains unclear. We designed a large language model (LLM)-based visit preparation...
The results indicate that user-side detection is not a viable defense and motivate system-level countermeasures such as cryptographic content provenance.
JudgeGPT and RogueGPT are presented, a dual-axis framework that decouples ''authenticity'' from ''attribution'' to investigate the mechanisms of human susceptibility and suggest that ''pre-bunking'' interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy inform...
As generative artificial intelligence (AI) becomes more capable and widely used, understanding when and how humans should work with these systems is becoming increasingly important. However, the empirical evidence in this space offers conflicting recommendations, which leaves individuals and organizations without clear...
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up...
AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks information its task requires, such as an unstated preference, constraint, or specification. It can ask the human to clarify, or it can search for the information itself, f...
The implemented prototype separates deterministic planning from large language model generation, represents content and delivery parameters explicitly, shapes each script through a four-phase attention taper, validates structural and lexical constraints, performs a bounded error-aware retry, and quarantines unresolved...
AI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It converts developer intent into a Verus specification, proves AI-generated code meets it for every input, and uses tests where proofs aren't practical. Developers review intent, not every line. The post Formally verifying agent-written full-stack web apps with PDD Kit appeared first o…
Data Mining & Modeling
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
During the School of Humanities, Arts, and Social Sciences’ 75th Anniversary Symposium, President Sally Kornbluth said “MIT has never needed your particular insight and guidance more than we do now.”
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
“X-Hinges” helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
