AI assistants are not used in a vacuum—they operate inside hospitals, banks, classrooms, and brands, each with its own rules. This paper introduces Pluralistic Behavior Suite (PBSUITE), a testbed to see whether language models can stick to your custom policies over multi-turn conversations. * 300 realistic behavioral policies across 30
AI
Meet LiveStar — an AI co‑host for live streams that understands what’s happening on screen and speaks up at the right moment. Most video AIs do great offline, but stumble live: they process frames slowly and interrupt or fall behind. LiveStar fixes that with: * Adaptive streaming decoding: keeps a
AI
Predictive maintenance means fixing equipment before it fails. But in the auto industry, messy maintenance logs—full of typos, missing fields, near-duplicates, and wrong dates—can derail the machine-learning models that power those predictions. This study tests large language model (LLM) agents as smart cleaners for those logs. The team
AI
Criminal justice data often record charges and outcomes—but not what actually happened. Yet many continental European verdicts spell out the facts. This study shows we can automatically pull those fact sections from public Slovak court decisions. The team tested two tools: 1) smart pattern‑matching that recognizes how courts
AILiteracy
Artificial intelligence is now part of everyday tools. How should community colleges teach it to non-STEM students? Researchers tested AI User, a no-code, scenario-based online curriculum, with four focus groups of community college instructors. * Instructors loved exploratory, real-world tasks that let students experiment safely with AI. * They preferred interactive demonstrations
UrbanPlanning
Cities need AI that can explain itself Most planning AI spots patterns in data. The next leap is AI that helps choose sites, allocate budgets, and balance trade-offs—while showing its work. This paper introduces the Agentic Urban Planning AI Framework built on new reasoning methods like Chain-of-Thought, ReAct, and
AudioAI
Remixes, sped-up clips, and heavy compression make it hard to trace where music on social platforms comes from. This study introduces more robust neural audio fingerprints—compact “IDs” for audio—that can still recognize a song after it’s been distorted. * Music-first brains: Instead of training from scratch, the model
AI
As AI shapes decisions everywhere, learners beyond computer science need practical AI literacy. But too often, lessons are code-heavy or lecture-only—hard to access and easy to remember. A new study of AI User, a modular, no-code web curriculum, shows another path. Researchers reviewed Projects 5–8 on natural language,
Most AI 'literacy' tests still grade you on math and code. But in real jobs, success looks more like choosing the right tool, interpreting model output, and flagging ethical risks. A team working with a US Navy robotics training program built a task-oriented assessment: scenario questions that simulate
AR that spots parts, so you don’t have to Researchers present an AI-assisted AR workflow that recognizes components in real time and overlays step-by-step instructions directly on your workspace. * See it, place it: A bounding box highlights the right part and shows exactly where it should go. * No pre-sorting:
AI
Ever heard of the “lottery ticket” idea in AI? It says big neural nets hide small subnetworks that can perform just as well. This paper proves a strong version of that for the heart of Transformers: multi-head attention (MHA). * The big claim: Inside a randomly initialized MHA, there exists a
AI
Ever heard of the “lottery ticket” idea in AI? It says big neural nets hide small subnetworks that can perform just as well. This paper proves a strong version of that for the heart of Transformers: multi-head attention (MHA). * The big claim: Inside a randomly initialized MHA, there exists a