Search results for Microsoft Research
AI & Enterprise
KAIST develops AI that reads intentions from brainwaves without words
Researchers have developed AI technology that identifies a person’s intentions through brainwaves and adjusts its own behaviour without spoken or physical cues. KAIST said the team led by Sang Wan Lee developed a brain-computer interface technique called Neural Value Alignment with Microsoft Research Asia. The system distinguishes different brainwave signals linked to goal errors and action-method errors, then uses deep learning to interpret EEG in real time and revise AI behaviour accordingly.
AI & Enterprise
Tech Insight: Why AI UIs need redesign beyond the chat window
Product designer Maxim Kich argues that AI interfaces need a fundamental redesign because advanced model capabilities are still confined to messenger-style chat windows. He says long conversations bury ideas and make context hard to retain. Citing research, he notes that language and thought differ, and linear chat does not match how thinking works. He points to alternative UI experiments and argues memory systems should be improved before interfaces.
AI & Enterprise
KAIST develops AI system to diagnose time reasoning errors using database
KAIST said on Monday a research team led by professor Eui-jong Hwang developed a system that automatically evaluates and diagnoses large language models\' time reasoning, in joint research with Microsoft Research. The team introduced temporal database design theory to AI evaluation, enabling a database to automatically generate 13 types of complex time-based questions and automate the process from answer derivation to verification. It also introduced a metric to validate dates and periods, improving detection of temporal hallucinations by 21.7 percent on average.
