Sayash Kapoor

Princeton University — United States

Computer Science · Physical Sciences

15h-index1.3kcitations46works10.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Explainable Artificial Intelligence (XAI)(10), Ethics and Social Impacts of AI(7), Advanced Bandit Algorithms Research(5), Artificial Intelligence in Healthcare and Education(4), Adversarial Robustness in Machine Learning(4)

Publications46 total

SEVEN STEPS FOR LOG ANALYSIS SEVEN SIMPLE STEPS FOR LOG ANALYSIS IN AI SYSTEMS
2026Open Access
Seven simple steps for log analysis in AI systems
Zenodo (CERN European Organization for Nuclear Research)·2026Open Access
The 2025 Foundation Model Transparency Index
SuperIntelligence - Robotics - Safety & Alignment·2026Open Access
The 2025 Foundation Model Transparency Index
arXiv (Cornell University)·2025Open Access
Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
arXiv (Cornell University)·2025Open Access
AI Snake Oil
Princeton University Press eBooks·2025
How Generative AI Works and How It Fails
2025Open Access
Bridging Prediction and Intervention Problems in Social Systems
arXiv (Cornell University)·2025Open Access
A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety
arXiv (Cornell University)·2025Open Access
The Reality of AI and Biorisk
2025· 2 cited
The Leaderboard Illusion
arXiv (Cornell University)·2025Open Access
Why an overreliance on AI-driven modelling is bad for science
Nature·2025· 13 cited
International AI Safety Report
arXiv (Cornell University)·2025· 9 citedOpen Access
The Reality of AI and Biorisk
arXiv (Cornell University)·2024· 2 citedOpen Access
Inference Scaling fLaws: The Limits of LLM Resampling with Imperfect Verifiers
arXiv (Cornell University)·2024· 1 citedOpen Access
Foundation Model Transparency Reports
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024· 26 cited
Considerations for governing open foundation models
Science·2024· 21 cited
AI Snake Oil
Princeton University Press eBooks·2024· 1 cited
How large language models can reshape collective intelligence
Nature Human Behaviour·2024· 69 cited
CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
arXiv (Cornell University)·2024· 3 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Arvind Narayanan(27), Rishi Bommasani(13), Shayne Longpre(11), Percy Liang(11), Kevin Klyman(10), Nestor Maslej(6), Peter Henderson(6), L. Elisa Celis(5), Nisheeth K. Vishnoi(5), Betty Xiong(5), Jessica Hullman(4), Benedikt Stroebl(4), Farnood Salehi(3), Priyanka Nanayakkara(3), Matthew Salganik(3), Angelina Wang(3), Solon Barocas(3), Ashwin Ramaswami(3), Yacine Jernite(3), Victor Storchan(3)