EPISODE · Apr 20, 2026 · 28 MIN
[人人能懂AI前沿] 从目标牵引、经验进化到群体学习
from AI可可AI生活
你有没有想过,AI也会陷入“高水平重复”的舒适区陷阱?学习新知识后,它为什么会像我们一样“健忘”?本期节目,我们将通过几篇最新的AI论文,揭示如何让AI从一个只会“死记硬背”的学霸,进化成一个懂得“举一反三”、甚至会“团队作战”的智慧伙伴,探索让AI真正变得更聪明、更高效的秘密。00:00:27 你是在“精进”,还是在“高水平地重复”?00:04:49 AI上课后,为什么反而把以前会的给忘了?00:11:08 让AI左右互搏,速度翻倍的秘密00:16:02 你的“人工智障”客服,终于有救了?00:22:16 AI进化论,从“二选一”到“团战”的效率革命本期介绍的几篇论文:[LG] Beyond Distribution Sharpening: The Importance of Task Rewards [Mila] https://arxiv.org/abs/2604.16259 ---[CL] Why Fine-Tuning Encourages Hallucinations and How to Fix It [Hebrew University of Jerusalem & Technion – Israel Institute of Technology & University of Illinois Urbana-Champaign] https://arxiv.org/abs/2604.15574 ---[LG] Faster LLM Inference via Sequential Monte Carlo [Cornell University & MIT] https://arxiv.org/abs/2604.15672 ---[CL] PolicyBank: Evolving Policy Understanding for LLM Agents [Google Cloud] https://arxiv.org/abs/2604.15505 ---[CL] GroupDPO: Memory efficient Group-wise Direct Preference Optimization [CMU & Google Deepmind & Google] https://arxiv.org/abs/2604.15602 在小宇宙查看该单集文稿
Embed this episode
Ready to play
[人人能懂AI前沿] 从目标牵引、经验进化到群体学习
No transcript for this episode yet
Similar Episodes
No similar episodes found.