ReVision is presented, an AI-based tool that decomposes visual and textual references into editable conceptual interpretations and visual motifs, enables their recombination across conceptual and visual spaces, and renders each direction as divergent visual-form variations, supporting more divergent exploration during...
Preliminary empirical evidence that single-observation queries are insufficient for evaluations of LLM refusal behaviors is presented, with reliable quantification of refusals required between 15 and 25 repeated queries, well above the single-observation standard common in existing evaluations.
Emma Lurie, Stephanie T. Wang, Sorelle A. Friedler et al.· 0 citations
A mixed-methods investigation to characterize and mitigate memory misalignment from user perspectives, which highlights the tension between supervisory agency and interaction overhead, and advocates for friction-aware memories that balance user oversight with conversation smoothness.
Jing-Ruo Chen, Shu-Ning Zhang, Er-Yue Xu et al.· 0 citations
On Twin-2K-500, OwnWords predicts ordinal survey answers more closely than the written memory, but does not improve exact-choice accuracy and lowers it in one of two samples.
Tian-Zhu Qin, L. Yang, Lee-Wei Jun et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Automated PDF accessibility checkers provide useful conformance evidence, but a clean report is not a complete accessibility oracle. PDFa11yMut measures mutation-specific checker behavior by applying paired structure-level transformations to reference-suite baselines, verifying intended deltas and non-target invariants...
It is shown that when Q&A is embedded within ongoing care, reliability depends on more than what the system knows medically, and proposes a design space for situated medical assistance that connects what the assistant and patient can each reliably establish to the form of assistance provided.
Shreya Bali, Riku Arakawa, J. Lehman et al.· 0 citations
The effects of scent-delivery within virtual reality (VR) environments by using fan-mediated olfactory devices are explored, indicating that scent-delivery feedback influenced spatial behavior in distinct ways across the two studies.
Siyeon Bak, Junho Kim, Dong-Yun Han et al.· 0 citations
VocalEyes is built, a speaker-aware AR captioning system that creates named voice profiles from natural self-introductions that shows how in-conversation registration can preserve speaker attribution across live captions and meeting records in scripted small-group meetings.
Yu-Xiao Wang, Xu-Long Tang, Chen Chen et al.· 0 citations
Results show that olfactory cues can support recognition of encountered locations during navigation, while ventilation was associated with reduced residual interference and improved usability, however, longer ventilation did not clearly improve recognition accuracy in repeated navigation.
Dong-Yun Han, Heecheol Kim, Siyeon Bak et al.· 0 citations
A preregistered, three-country randomized experiment on out-of-context image misinformation, manipulating a correction's channel affordances (synchronicity, bandwidth) across four conditions shows engagement mechanisms do not substitute for slow AI literacy.
Kokil Jaidka, I. Mujtahid, Peng Qi et al.· 0 citations
Environmental interfaces are introduced: designed environmental conditions that shape human-AI relationships through ambient, holistic, and evaluative pathways rather than explicit functional interaction, pointing to a broader transition from designing interfaces for operating intelligent systems to designing environme...
Ke-Qi Chen, Run-Jia Tan, Xin-Yi Fu et al.· 0 citations
The first user-centric benchmark grounded in real user feedback signals for evaluating preference alignment and dialogue generation is presented, demonstrating that user feedback prediction is a learnable capability and revealing different aspects that influence user experience.
Mengze Hong, Xia Zeng, Zeyang Lei et al.· arXiv.org· 1 citation
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.