IMPLIED is an implication modeling method that treats fixed-rule implications as an initial guide while learning to infer and revise accepted and rejected action labels over time, and predicts human implications more accurately than the fixed rule approach and LLM baselines, approaching the performance of a human-label...
Qiping Zhang, Kate Candon, Debasmita Ghose et al.· 0 citations
AI-powered gameplay support agents hold promise for game-based learning, yet grounding generative models in structured game data remains an open challenge. We present PEARL (Parallel Education Agent for Reflection and Learning), a dual-component Retrieval-Augmented Generation (RAG) system that combines semantic knowled...
Jia-Hong Li, Sai Siddartha Maram, Atieh Kashani et al.· 0 citations
Do AI assistants help believers reason about moral dilemmas consistently with their faith? We present FaithfulBench, the first benchmark to score AI counsel across traditions by how well it adheres to the user's professed faith. Scenarios are drawn from each tradition's most respected texts, with the faithful answer kn...
M Waleed Kadous, Benjamin Olsen, Walter Scheirer et al.· 0 citations
Architectural design education relies heavily on visual ideation and representation to support collaborative learning in studio environments. Recent advances in generative artificial intelligence (GenAI) and extended reality (XR) offer new opportunities for rapid idea exploration and immersive spatial visualization. Th...
Yao Xiao, Max Chen, Yichen Li et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models (LLMs) are increasingly used as user simulators, but their ability to reproduce evolving individual financial decisions remains unclear. We present a preliminary study in a controlled paper-trading environment with 120 volunteers. Participants used non-redeemable virtual funds under real-time mark...
Jia-Jie He, Jiang-Yuan Hong, Dong-Ling Ni et al.· 0 citations
This study proposes a formal definition of data storytelling in IML, introduces the DIST Pyramid to align data storytelling with IML, and presents the I-P-O Model to describe their interactions, and develops an architecture to explain AI decisions through distinct "What-if" and "Why-not" event-generation processes.
Le-Men Chao, Zi-Xuan Yang, An-Ran Fang et al.· 0 citations
It is found that user hostility varies 13-fold across models, driven largely by who each model attracts rather than by model behaviour: first-turn hostility spreads far wider than post-response hostility, and more than fifteenfold separates the extremes even after deduplicating opening prompts.
Fan-Qi Zeng, Sadid A. Hasan, Chao-Cheng He· 0 citations
The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automa...
Harsh Raj, David Lee, Anas Mahmoud et al.· 0 citations
This study examines the structural dynamics of Truth Social, a politically aligned social media platform, during two major political events: the U.S. Supreme Court's overturning of Roe v. Wade and the FBI's search of Mar-a-Lago. Using a large-scale dataset of user interactions based on re-truths (platform-native repost...
Student-generated metaphors about mathematics can provide insights into students'attitudes, beliefs, identities, and experiences, but expert human assessment through thematic coding of these semantically complex metaphor responses is labor-intensive and difficult to scale. This study examines whether Low-Rank Adaptatio...
Liang Zhang, Stephen Hwang, Yue Ma et al.· 0 citations
Religion is an important part of many people's lives, with reading from religious texts being among the most common and important regular practices. Modern technology has changed the way this religious reading takes place, but the interaction of technology with religious reading has not been studied in detail. In this...
Teancum Price, Musa Blake, James Prather et al.· 0 citations
Immersive video differs from conventional flat 2D video in that it is experienced as 180-degree stereoscopic video on a head-mounted display, thereby eliciting bodily and spatial subjective experience. Previous studies have shown that viewing and interpersonal distance affect Presence; however, it remains insufficientl...
Koichi Toida, H. Hiranuma, Shimpei Miura et al.· arXiv.org· 3 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.
