output
20162026
most citedWhen Will AI Exceed Human Performance? Evidence from AI Experts

222 citations

Showing 2025Show all

6 papers · 1 filter

cs.AI2025★ 1 cited

Extending FKG.in: Towards a Food Claim Traceability Network

Saransh Kumar Gupta, Rizwan Gulzar Mir, Lipika Dey +3

The global food landscape is rife with scientific, cultural, and commercial claims about what foods are, what they do, what they should not do, or should not do. These range from r…

cs.CV2025

Understanding Driving Risks using Large Language Models: Toward Elderly Driver Assessment

Yuki Yoshihara, Linjing Jiang, Nihan Karatas +3

This study investigates the potential of a multimodal large language model (LLM), specifically ChatGPT-4o, to perform human-like interpretations of traffic scenes using static dash…

quant-ph2025★ 13 cited

Ultralong Room-Temperature Qubit Lifetimes of Covalent Organic Frameworks

Zhecheng Sun, Weibin Ni, Denan Li +3

Molecular electron spin qubits offer atomic-level tunability and room-temperature quantum coherence. Their integration into engineered solid-state matrices can enhance performance…

cond-mat.mes-hall2025★ 3 cited

Rectification and bolometric terahertz radiation detectors based on perforated graphene structures exhibiting plasmonic resonant response

V. Ryzhii, C. Tang, M. Ryzhii +2

We propose and evaluate the characteristics of the terahertz (THz) detectors based on perforated graphene layers (PGLs). The PGL structures constitute the interdigital in-plane arr…

eess.AS2025

Automatic Live Music Song Identification Using Multi-level Deep Sequence Similarity Learning

Aapo Hakala, Trevor Kincy, Tuomas Virtanen

This paper studies the novel problem of automatic live music song identification, where the goal is, given a live recording of a song, to retrieve the corresponding studio version…

cs.LG2025★ 23 cited

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…