// PERSON
Jesse Farebrother
ROLE RESEARCHERAT MILAMENTIONS 2LAST SEEN JUNE 11, 2026
// BIO
Co-author on WEAVER, brings expertise in deep RL and rigorous evaluation methodology.
// RECENT MENTIONS
// SIGNALS
2 SIGNALS
01
product·arXiv Physical AI·JUNE 11, 2026
“WEAVER achieves a Pearson correlation of ρ=0.870 between simulated and real-world success rates... finetuning on synthetic data closely matches that on real data, with only a 4% average performance gap”
Source→02
mention·arXiv Physical AI·JUNE 11, 2026
“Jesse Farebrother, Mila – Québec AI Institute / McGill University, Why notable: Co-author with background in deep RL and evaluation methodology.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.