EPISODE · Apr 13, 2026 · 29 MIN
[人人能懂AI前沿] 从思想引导、言行一致到世界模型
from AI可可AI生活
你有没有想过,我们能像做微创手术一样,在AI思考的瞬间“拨乱反正”,引导它向善吗?或者,让昂贵的AI训练学会“温故知新”,把扔掉的经验变废为宝?本期节目,我们将一起探索几篇最新论文,看看科学家们如何教会AI遵守自己立下的规矩,如何让它既会“看路”又会“造景”,甚至,如何为它补上一堂生动的物理课,让它的想象力更符合现实。准备好了吗?让我们马上出发!00:00:34 给AI的大脑装一个“概念导航”00:06:53 AI训练的高效秘诀,好东西值得再用一次00:12:07 如何看穿一个AI的“人设”?00:16:56 AI新思路,想看清世界,先学会走路00:23:07 为什么AI生成的视频总感觉“假”?答案藏在物理学里本期介绍的几篇论文:[LG] Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs [University of Pennsylvania & Amazon] https://arxiv.org/abs/2604.08846 ---[LG] Efficient RL Training for LLMs with Experience Replay [FAIR at Meta] https://arxiv.org/abs/2604.08706 ---[CL] Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies [Microsoft] https://arxiv.org/abs/2604.09189 ---[CV] Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories [Meta AI] https://arxiv.org/abs/2604.09429 ---[CV] PhysInOne: Visual Physics Learning and Reasoning in One Suite [vLAR Group] https://arxiv.org/abs/2604.09415 在小宇宙查看该单集文稿
Embed this episode
Ready to play
[人人能懂AI前沿] 从思想引导、言行一致到世界模型
No transcript for this episode yet
Similar Episodes
No similar episodes found.