PersonaDual: AI that knows when to personalize—and when not to Personalized answers can feel helpful—but they can also bend the facts. PersonaDual is a new framework that lets one model switch between objective reasoning and personalized reasoning on the fly, based on the question and context. * Two minds
Generative AI is reshaping coursework—but where do students want help, and where do they want control? This case study of online graduate CS students audits student–AI collaboration across 12 academic tasks. Using two back-to-back surveys, it maps current AI capabilities against the level of automation students actually prefer.
Robocon2025
Teaching Basketball Robots to Know Where They Are At Robocon 2025, split-second positioning can be the difference between a swish and a miss. Naren Medarametla and Sreejon Mondal present a real-time localization framework that helps autonomous basketball robots figure out their spot on the court—using only what they see
AI
AI is shaping what we read and decide. But do large language models carry hidden political leanings? A new study proposes a transparent way to audit political bias: ask models to predict how parliaments voted, then compare those predictions to the real records. * Benchmarks: PoliBiasNL (2,701 Dutch motions; 15
VideoEditing
Imagine editing a video as easily as rewriting a sentence. This research explores text-driven video reauthoring—using words to reshape footage. The team introduces two pieces: (1) a generative reconstruction algorithm that reverse-engineers a video into an editable text prompt, and (2) an interactive probe, Rewrite Kit, that lets creators
We talk about AI as a productivity tool. But a new paper argues its biggest near-term impact may be entertainment—memes, music, companions, and endless remixing—already popular with young people and a massive potential revenue stream. As companies seek returns on huge infrastructure bets, “AI for fun” will shape
OperationsResearch
Why it matters Utility crews rarely know exactly how long each job will take. This paper blends machine learning and risk-aware optimization to plan daily routes that stay on time—even when jobs run long. Using eight years of gas meter maintenance data, the author trains a gradient-boosted model (XGBoost)
BCI
EEG-based brain–computer interfaces often stumble in the real world: every person’s brain signals look different, and conditions change from moment to moment. A new approach called Backpropagation-Free Transformations (BFT) helps BCIs adapt on the fly—without costly re-training, extra data, or exposing private signals. How it works * For
AI
TL;DR Long-horizon LLM agents fail when one small error snowballs. Task-Decoupled Planning (TDP) breaks big jobs into a DAG of sub-goals, so planning and fixes stay local—making agents both sturdier and cheaper. How it works: * Supervisor decomposes the task into a directed acyclic graph of sub-goals. * Planner and
AI
Why chatbots forget—and how ES‑Mem fixes it Long chats often make assistants lose the thread. ES‑Mem, a new memory system, keeps conversations coherent by organizing them like humans do. * Breaks talks into “events.” Instead of saving every line, ES‑Mem detects natural boundaries—topics, goals, shifts—so
Physics
Ever wondered how a simple physics idea can power memory in neural networks? This paper revisits the classic Hopfield model—born from spin-glass physics—and shows why it’s a perfect bridge from undergraduate physics to modern AI. * Clear tour: A friendly intro using familiar physics tools (energy, dynamics, stability)
AI
Can AI spot nonsense in pictures? Humans can tell that “A sandwich cuts a chef” is grammatically fine but semantically absurd. Many vision-language models (VLMs) can’t. UAIT (Uncommon-sense Action Image-Text) is a new benchmark that stress-tests whether VLMs truly understand who is doing what to whom—and what’s