EPISODE · Mar 10, 2026 · 31 MIN
[人人能懂AI前沿] AI的成长新思路:从难题挑战到无损学习
from AI可可AI生活
我们都希望AI越来越聪明,但怎么才能让它高效成长呢?今天我们要聊的几篇最新论文,就给出了一些非常反直觉的答案:比如,让AI只做“难题”,给它的创作过程派一位“监理”,甚至还要警惕它因为懂得太多而“吃不饱”。更神奇的是,我们还会看到如何让AI学会新本事,却完全不忘旧手艺。准备好了吗?让我们一起看看AI是如何被调教成“学霸”的!00:00:31 想让AI更聪明?你得学会给它出难题00:05:53 如何让AI“心领神会”你的想法?00:12:00 AI的“语义饱腹感”,为什么数据越多,进步越难?00:18:31 AI思考的秘密,为什么“平行世界”里的笨办法,反而是捷径?00:24:27 如何让AI学会新本事,还不忘了旧手艺?本期介绍的几篇论文:[CL] Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems [Microsoft Research] https://arxiv.org/abs/2603.07779 ---[LG] Diffusion Controller: Framework, Algorithms and Parameterization [Google Research] https://arxiv.org/abs/2603.06981 ---[LG] Scale Dependent Data Duplication [Stanford University & EPFL] https://arxiv.org/abs/2603.06603 ---[LG] Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference [Microsoft Research & MIT] https://arxiv.org/abs/2603.07887 ---[LG] Grow, Don't Overwrite: Fine-tuning Without Forgetting [Google Research & University of Wisconsin-Madison] https://arxiv.org/abs/2603.08647 在小宇宙查看该单集文稿
Embed this episode
Ready to play
[人人能懂AI前沿] AI的成长新思路:从难题挑战到无损学习
No transcript for this episode yet
Similar Episodes
No similar episodes found.