What Don’t You Understand? Using Large Language Models to Identify and Characterize Student Misconceptions About Challenging Topics
5 月 4, 2026admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2605.00294v1 Announce Type: new Abstract: This study presents a systematic approach to identifying and characterizing...
What Does Neuro Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs
10 月 16, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.10113v3 Announce Type: replace Abstract: In this paper, we introduce S-MedQA, an English medical question-answering...
What do Speech Foundation Models Learn? Analysis and Applications
8 月 19, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2508.12255v1 Announce Type: new Abstract: Speech foundation models (SFMs) are designed to serve as general-purpose...
What could possibly go wrong if an enterprise replaces all its engineers with AI?
11 月 9, 2025admin NUAI,Committee,新闻,Uncategorized(0)AI coding, vibe coding and agentic swarm have made a dramatic and astonishing recent market...
What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization
11 月 7, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2505.12474v3 Announce Type: replace Abstract: Traditional dialogue summarization primarily focuses on dialogue content, assuming it...
What Anthropic’s latest AI discovery does—and doesn’t—show
7 月 13, 2026admin NUAI,Committee,新闻,Uncategorized(0)This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories...
Welcome to the dark side of crypto’s permissionless dream
2 月 18, 2026admin NUAI,Committee,新闻,Uncategorized(0)“We’re out of airspace now. We can do whatever we want,” Jean-Paul Thorbjornsen tells me...
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
5 月 1, 2025admin NUAI,Committee,新闻,Uncategorized(0)arXiv:2504.21776v1 Announce Type: new Abstract: Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate...
Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs
10 月 19, 2025admin NUAI,Committee,新闻,Uncategorized(0)Researchers from Stanford, EPFL, and UNC introduce Weak-for-Strong Harnessing, W4S, a new Reinforcement Learning RL...
