Construction safety reporting often relies on manual logs and static templates that provide limited feedback and leave daily activities disconnected from relevant regulations. This paper introduces CARES (Conversational AI Reporting for Enhanced Safety), a conversational AI system that integrates regulatory guidance in...
Fan Yang, Jiabin Wu, Yuan Tian et al.· 0 citations
LLMs are rapidly reshaping peer review, making it important to understand how reviewers use them in practice and how different LLM-use policies affect review outcomes. We investigate these questions through a randomized experiment and an anonymous post-survey at ICML 2026, a major machine learning conference involving...
Sunnie S. Y. Kim, Wesley Hanwen Deng, Jennifer Wortman Vaughan et al.· 0 citations
Health misinformation disproportionately harms women, yet interventions rarely address the community norms that sustain false beliefs. We test whether culturally adaptive AI-generated video in which the presenter looks like someone from her community reduces misinformation belief among low-literacy women in suburban In...
Anku Rani, Kokil Jaidka, Shruti Sharma et al.· 0 citations
Clinical data abstraction, the process of distilling structured information from patient records, plays a key role in advancing knowledge about diseases such as cancer. Information extraction (IE) with large language models (LLMs) could accelerate this process, but it is unclear whether current frameworks effectively s...
Venkatesh Sivaraman, Rigney Turnham, George Bonano et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
MuTable is presented, a prototype that reifies transformations as persistent, composable, and reusable modifiers to support in-situ data exploration and can support coordination between representations, rapid exploration, and greater user agency in constructing visualizations.
F. Sun, Devamardeep Hayatpur, E. JaneL et al.· 0 citations
This paper explores how the technologies U.S. election officials depend on also challenge their work. Every election, misleading narratives stem from errors that occur while using election technology, threatening election official safety and eroding faith in elections. We seek to understand the impact of these challeng...
Delaney Gomen, Josiah D. Hester, Naveena Karusala et al.· 0 citations
Multi-stage LLM hiring pipelines (resume improvement, interview question generation, answer feedback) can fabricate credentials, inflate qualifiers, and invent experience. We evaluate two mitigations, prompt guardrails and human-in-the-loop (HITL) checkpoints, against a fully automated baseline. In a controlled experim...
Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team weeks: hunting for context, running statistics, choosing an angle, and designing visuals. Recent agents handle individual steps well: data-sci...
Kevin Qinghong Lin, Batu EI, Yuhong Shi et al.· 0 citations
Full-duplex speech models listen and speak at once, promising always-on assistants. Yet they must also decide when they should speak. Human listeners speak when addressed or when the speaker stops, but also self-select to correct a false claim, supply a missing word, or warn of danger. We ask whether full-duplex models...
Linkai Peng, Baorian Nuchged, Kaiqi Fu et al.· 0 citations
Generative AI (GenAI) applications have achieved rapid consumer adoption, yet little large-scale research examines user-perceived quality, trust, and adoption barriers. We present one of the first cross-application analyses of app store reviews for six major GenAI applications (ChatGPT, Gemini, Microsoft Copilot, Claud...
A myoelectric interface needs calibration from the user before it will function. Earlier work has treated calibration as a quantity, but has not asked the question of what a device should do with the calibration repetitions once they have been collected. This paper views personalizing the cross-user encoder as a design...
A unified, modality-agnostic, hierarchical Transformer-based architecture to process heterogeneous biosignal modalities within a single model is developed and EEG is the strongest single modality, ranking highest in IQ, GAME, and the pooled ALL setting.
Stefanos Gkikas, Christian Arzate Cruz, Calvin Joseph et al.· 9 citations
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 30, 2026
Able to defeat top-ranked human players and more efficient than other models, the new system could help decision-makers in military maneuvers or business negotiations.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
