by Oliver Jaffe Papers
3 papers found
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij, Felix Hofstätter, Oliver Jaffe et al.
ICLR 2025poster
58
citations
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
Jun Shern Chan, Neil Chowdhury, Oliver Jaffe et al.
ICLR 2025poster
127
citations
PaperBench: Evaluating AI’s Ability to Replicate AI Research
Giulio Starace, Oliver Jaffe, Dane Sherburn et al.
ICML 2025oral