End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize imperceptible attacks on full-duplex agents as optimization over additive perturbations confined beneath the psychoacoustic masking threshold of the c...
ContraVis is presented, a visual analytics system for human-in-the-loop contradiction analysis in legal contracts that models contracts as typed paragraph graphs that combine explicit contractual references with semantic relationships between paragraphs.
Luis Santé, Paula Lima, M. Rocha et al.· 0 citations
This survey connects Articulated, Inner and Perceived tasks to the neural populations they engage, the representations available to decoders and the outputs those representations can support, and outlines a prospective five-level trajectory from commands and language to meaning, scenarios and bidirectional cognitive ex...
Yi-Qian Yang, Yi-Qun Duan, Chen-Yu Liu et al.· 1 citation
It is argued that the appropriateness of a response offset, whether delayed silence or anticipatory overlap, is conditional on the speaker's latent intent, identifiable only from that speaker's behavior.
Kian Shamsaie, Iman Modarressi· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A customer-facing AI powered triaging agent that leverages large language models to conduct multi-turn conversations, ask relevant questions, and classify cases for accurate, policy-guided routing, making it embedded in the customer journey is developed.
Alankar Atreya, Stefan Sylvius Wanger, Devesh Batra et al.· arXiv.org· 0 citations
This work shows that LLMs can be used to strategically target expert attention, shortening months of codebook revision to days without sacrificing labeling performance.
Ze-Yu He, Zhu-Qian Zhou, Kirk P. Vanacore et al.· 0 citations
Safety Nudges is introduced, a browser-based tool that provides lightweight, in situ flags when concerning behavior is detected in chatbot conversations, suggesting that user facing safety nudges can complement model-level safeguards by helping people critically evaluate AI responses in context.
Varshini Elangovan, J. Wedgwood, Chhavi Yadav et al.· 0 citations
BizChat was extended, an AI-powered business-planning tool, with an evaluation module that links each generated claim to the entrepreneur's original input, and interface scaffolds like claim-to-input links primed attendees with concrete, personal evaluations.
Qi Zhao, Marjory Pineda, Ketul Chhaya et al.· 0 citations
Visual data analysis involves both open-ended exploration and targeted question answering. Visualization authoring tools support this process by enabling users to create visualizations for these tasks. With the rise of large language models (LLMs), substantial effort has been devoted to developing visualization authori...
Yuki Ueno, Bretho Danzy III, Zhuojun Jiang et al.· 0 citations
This study empirically investigates how practitioners prioritize explainability relative to four competing factors: accuracy, compliance, cost, and speed, and reveals that these priorities are structured not as a simple trade-off, but as a system of distinct prerequisites and constraints.
Patricia Marcella Evite, E. Svetlova, Doina Bucur· arXiv.org· 2 citations
Effective communication of robot touch intent is essential for safe and predictable physical human-robot interaction. While intent communication has been widely studied, existing approaches lack the spatial specificity and semantic depth necessary to efficiently convey robot touch intent. We present Mirror Skin, a ceph...
David Wagmann, Matti Krüger, Chao Wang et al.· 0 citations
PRIMMDebug consists of an online tool that takes students through the steps of a pedagogical process based on PRIMM, a framework for teaching programming, and encourages written articulation throughout the debugging process and limits students'ability to run and edit code at certain stages.
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…
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
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.”
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
MIT News · Artificial Intelligence· news.mit.eduOct 22, 2026
“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.
