![[人人能懂AI前沿] 从概念擦除、元学习到内部电路诊断](https://image.xyzcdn.net/FuDP4HpAp8ezgVZMmEel3mblKCmJ.jpg@middle)
主播
节目简介
来源：小宇宙
想让AI更聪明，我们总觉得要给它看更多、学更多，但如果我告诉你，真正的秘诀恰恰相反呢？本期节目，我们将一起探索几篇最新的AI论文，看看科学家是如何教会AI“选择性遗忘”，又是如何给AI做“脑CT”来判断它是不是在“假装努力”。我们还会聊到，如何打造一个能快速学会任何人大脑“方言”的超级解码器，以及怎样只用1%的精力，就让AI帮你“看完”一部长电影。准备好了吗？让我们一起刷新对AI的认知！
00:00:37 按下删除键之后，东西就真的消失了吗？
00:06:54 造一把“万能钥匙”？不如当个“超级锁匠”
00:11:24 想让AI更博学？先给它少看点书
00:16:21 给AI做个体检，我们怎么知道它不是在瞎蒙？
00:22:01 如何只用1%的精力，看完一部长电影的精华？
本期介绍的几篇论文：
[LG] Is your algorithm unlearning or untraining?
[Google]
https://arxiv.org/abs/2604.07962
---
[LG] Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
[University of Hong Kong]
https://arxiv.org/abs/2604.08537
---
[CL] Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
[Apple & National University of Singapore]
https://arxiv.org/abs/2604.08519
---
[LG] Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
[University of Delaware & George Mason University]
https://arxiv.org/abs/2604.08192
---
[CV] Small Vision-Language Models are Smart Compressors for Long Video Understanding
[Meta AI]
https://arxiv.org/abs/2604.08120
00:00:37 按下删除键之后，东西就真的消失了吗？
00:06:54 造一把“万能钥匙”？不如当个“超级锁匠”
00:11:24 想让AI更博学？先给它少看点书
00:16:21 给AI做个体检，我们怎么知道它不是在瞎蒙？
00:22:01 如何只用1%的精力，看完一部长电影的精华？
本期介绍的几篇论文：
[LG] Is your algorithm unlearning or untraining?
[Google]
https://arxiv.org/abs/2604.07962
---
[LG] Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
[University of Hong Kong]
https://arxiv.org/abs/2604.08537
---
[CL] Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
[Apple & National University of Singapore]
https://arxiv.org/abs/2604.08519
---
[LG] Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
[University of Delaware & George Mason University]
https://arxiv.org/abs/2604.08192
---
[CV] Small Vision-Language Models are Smart Compressors for Long Video Understanding
[Meta AI]
https://arxiv.org/abs/2604.08120
