Transcendence: Generative Models Can Outperform The Experts That Train ThemJan 1, 2024·Edwin Zhang,Vincent ZhuNaomi Saphra,Anat Kleiman,Benjamin L. Edelman,Milind Tambe,Sham M. Kakade,Eran Malach· 0 min read Cite URLTypeConference paperPublicationNeural Information Processing Systems (NeurIPS)Last updated on Jan 1, 2024Science of Deep Learning AuthorsNaomi SaphraResearch Fellow ← TRAM: Bridging Trust Regions and Sharpness Aware Minimization Jan 1, 2024Understanding biological active sensing behaviors by interpreting learned artificial agent policies Jan 1, 2024 →
,,,,,·
0 min read