ICML 2026 Oral Papers Show Poor Reproducibility; Researcher Vows Not to Hire Those with <50% Reproducible Papers

ChenhaoTan · x · 2026-08-06

A viral article on AI research reproducibility reveals that many ICML 2026 oral papers cannot be fully reproduced. In response, researcher Gabriel B. commits to never hiring anyone with over 50% of their papers not fully reproducible, based on GitHub issues and code release. This highlights growing concerns about reproducibility in AI research.

Original post →

More from Research

Research channel →