Get started
Author

Kunvar Thaman

Observed name: Thaman, Kunvar
Institution: Stanford University
Observed institution: Stanford University
OpenAlex ID: A5114331535
A benchmark of expert-level academic questions to assess AI capabilities
2026 · Long Phan, Alice Gatti, et al. · Nature · 995
PDF
Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
2026 · Thaman, Kunvar · arXiv (Cornell University) · 38
PDF
Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts
2024 · Haimes, Jacob, Wenner, Cenny, et al. · arXiv (Cornell University) · 17
PDF
Roz: A Taste Test for World Model Latents
2026 · Ge, Kenneth, Sheth, Dhruv, et al. · arXiv (Cornell University)
PDF
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
2026 · Barth, Julia, Sommer, Armin, et al. · arXiv (Cornell University)
PDF
Works count: 5
Citation count: 1,050
H-index: 3
I10-index: 3
Year
Topic
Type