François Chollet@fcholletFrançois Chollet 认为测试时训练（TTT）潜力巨大，并希望其走向主流。ARC Prize 2024 将 SOTA 从 33% 提升至 55.5%，创 2020 年以来最大年度增幅，TTT 是自 2019-2020 年上下文学习以来 LLM 泛化能力的最大跃升。冠军为 the ARChitects 团队。
Test-time training was popularized during the ARC Prize 2024 competition, after being explored in particular by @MindsAI_Jack and team. To date, I believe ARC 1-2 are the only datasets where TTT strongly outperforms. It would be interesting if TTT started becoming more mainstream. I believe it has great potential.
来源：François Chollet · x.com
François Chollet 认为测试时训练（TTT）潜力巨大，并希望其走向主流。ARC Prize 2024 将 SOTA 从 33% 提升至 55.5%，创 2020 年以来最大年度增幅，TTT 是自 2019-2020 年上下文学习以来 LLM 泛化能力的最大跃升。冠军为 the ARChitects 团队。
Test-time training was popularized during the ARC Prize 2024 competition, after being explored in particular by @MindsAI_Jack and team. To date, I believe ARC 1-2 are the only datasets where TTT strongly outperforms. It would be interesting if TTT started becoming more mainstream. I believe it has great potential.
来源：François Chollet· x.com