What We Learned by Reproducing 2,200 papers from ICML

Large-scale reproduction data tells practitioners which published results actually hold up before they build on them.

• postTencent Hunyuan's EvolveScaler trips up frontier models on evolving factsTencent Hy
• postPredicting which unevaluated model would top a benchmark, then checkingAi2
• articleAgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud AgentJonan Richards, Kosei Horikawa, Youmei Fan, Yutaro Kashiwa, Mairieli Wessel

Checking sign-in…

Loading comments…