[人人能懂AI前沿] 从检查作业、搭建记忆宫殿到寻找隐藏食谱

我们总说AI有知识，但你想过吗，AI的知识该如何称重、如何存储、又该如何溯源？更进一步，AI能否自我修炼、检查作业，它吃的“数据大餐”又藏着怎样的“秘密食谱”？今天，我们就从五篇最新的论文出发，一起探索AI知识世界的台前与幕后。00:00:24 给AI模型称重，我们终于有了一杆新秤00:06:34 AI的“记忆宫殿”是如何搭建的？00:11:56 AI的自我修炼，如何从“检查作业”中获得智慧00:17:01 AI世界的“亲子鉴定”技术00:22:37 AI的“隐藏食谱”，为什么数据配比比数量更重要？本期介绍的几篇论文：[LG] Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data[New York University & CMU]https://arxiv.org/abs/2607.11883---[LG] MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers[Stanford University]https://arxiv.org/abs/2607.10034---[AI] SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning[University of Illinois Urbana-Champaign & Meta]https://arxiv.org/abs/2607.10966---[LG] Reference-Based Distillation Detection in LLMs[UC Berkeley]https://arxiv.org/abs/2607.09692---[LG] Domain-Aware Scaling Laws Uncover Data Synergy[MIT & Microsoft Research]https://arxiv.org/abs/2607.11052在小宇宙查看该单集文稿