Limassol
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
People are relying on AI agents to assist them with various tasks.
Hierarchical Selective Classification
Next, we develop algorithms for performing HSC (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
People are relying on AI agents to assist them with various tasks.
Watch: Moment freediver sets new world record with breath-defying 126m plunge
Russian freediver Alexey Molchanov plunged 126m (413ft) in a single breath to set a new world record at the AIDA Freediving World Championships in Limassol, Cyprus. He descended deep below the Mediterranean Sea with nothing but a headlight, two fins and a rope as a guide, in a feat considered one of the most technically challenging freedive categories. Mr Molchanov broke his own 2024 world record of 125m, during which he held his breath for a staggering four minutes and 32 seconds. The BBC's Russia editor, Steve Rosenberg, reports from joint manoeuvres by Russia and Belarus, as part of the Zapad 2025 (West 2025) military drills. 'Looks like a toy, but it's real': BBC examines a downed Russian drone Drones like this one were shot down over Polish airspace in the early hours of Wednesday.
Dude, where's my utterance? Evaluating the effects of automatic segmentation and transcription on CPS detection
Venkatesha, Videep, Bradford, Mariah, Blanchard, Nathaniel
Collaborative Problem-Solving (CPS) markers capture key aspects of effective teamwork, such as staying on task, avoiding interruptions, and generating constructive ideas. An AI system that reliably detects these markers could help teachers identify when a group is struggling or demonstrating productive collaboration. Such a system requires an automated pipeline composed of multiple components. In this work, we evaluate how CPS detection is impacted by automating two critical components: transcription and speech segmentation. On the public Weights Task Dataset (WTD), we find CPS detection performance with automated transcription and segmentation methods is comparable to human-segmented and manually transcribed data; however, we find the automated segmentation methods reduces the number of utterances by 26.5%, impacting the the granularity of the data. We discuss the implications for developing AI-driven tools that support collaborative learning in classrooms.