按年被提到
20242024 · 1 次2026
AI 安全、伦理与社会影响›AI 的经济与社会影响·arXiv:2410.18982 · cs.AI

O1 Replication Journey: A Strategic Progress Report -- Part 1

Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, Pengfei Liu · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-10-28 · 最近 2025-01-20
2不同的人
2活跃月份
2讨论串
37被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. In response to the announcement of OpenAI's groundbreaking O1 model, we embark on a transparent, real-time exploration to replicate its capabilities while reimagining the process of conducting and communicating AI research. Our methodology addresses critical challenges in modern AI research, including the insularity of prolonged team-based projects, delayed information sharing, and the lack of recognition for diverse contributions. By providing comprehensive, real-time documentation of our replication efforts, including both successes and failures, we aim to foster open science, accelerate collective advancement, and lay the groundwork for AI-driven scientific discovery. Our research progress report diverges significantly from traditional research papers, offering continuous updates, full process transparency, and active community engagement throughout the research journey. Technologically, we proposed the journey learning paradigm, which encourages models to learn not just shortcuts, but the complete exploration process, including trial and error, reflection, and backtracking. With only 327 training samples and without any additional tricks, journey learning outperformed conventional supervised learning by over 8\% on the MATH dataset, demonstrating its extremely powerful potential. We believe this to be the most crucial component of O1 technology that we have successfully decoded. We share valuable resources including technical hypotheses and insights, cognitive exploration maps, custom-developed tools, etc at https://github.com/GAIR-NLP/O1-Journey.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论HarHarVeryFunny · 2025-01

“There are all sorts of ways that additional test time compute can be used to get better results, varying from things like sampling multiple CoT and choosing the best, to explicit tree search (e.g. rStar-Math), to things like "journey learning" as described here: https://arxiv.org/abs/2410.18982?utm_source=substack&utm_medium=email Journey learning is do…”

DeepSeek-R1原评论 ↗
被提交为 story · 1 次